SLOPSHOPPER

post-merge-cleanup

/cleanup after a PR merges: switch to the default branch, pull, and delete the merged branch and its worktree, after one confirmation.

newcommandtoastprocess
★ 1v0.1.0no licenseupdated 2026-10-08seanrobertwright/claude-mods/mods/post-merge-cleanup
A shopper browsing a rack in a slop shop
Preview · a replayed session in a sandbox
claude · ~/work/app · post-merge-cleanup
› fix the failing auth test and add an audit log call ● post-merge-cleanup: post-merge-cleanup: start-up check: JSON Parse error: Unexpected EOF ⏺ Read(src/auth.ts) ⎿ Read 6 lines ⏺ Update(src/auth.ts) ⎿ Added 2 lines, removed 1 line ⏺ Bash(bun test) ⎿ 3 pass, 1 fail ● Done. refresh now rejects expired claims and logs an audit event. ✻ Worked for 42s · done 4:20 PM › /cleanup ⎿ post-merge-cleanup: Cleanup failed: JSON Parse error: Unexpected EOF ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── › ? for shortcuts
README

🧩 claude-mods

Small TypeScript mods that live inside Claude Code: a pane that knows your next step, one-click replies, a rate-limit countdown that resumes for you, your repo's pull requests and issues beside the conversation, a shelf of paths you use every day, presets that switch the model and the effort with one press, a chime when a long turn ends, a guard for the Office file you left open, a question before a commit or push on the default branch, a question before Claude reads a .env or key file, a list of the files this session made, a list of the ones it read, a check that keeps banned claims out of a pull request, a gate that runs your checks and hands back only the failures, a nudge to fetch fresh tab IDs when a browser tab is gone, a name for the session from its first prompt, and one dialog for every mod's settings.

Claude Code 2.1.289+ 20 mods TypeScript strict Checks: tsc, ESLint, validate, test

claude-mods is one developer's personal toolbox of Claude Code mods, shared as a plugin marketplace so anyone can install them. The mods are built for the author's own workflow first, and you are a welcome guest: install one, install all twenty, or read the source and write your own.

What is a mod?

A mod is a plugin of function hooks: TypeScript that runs inside Claude Code and changes what it shows (a pane in the side panel, a band of buttons above the prompt, the status line) or what it does between turns. The mod's own code decides when to act, even when what it does is send the model a prompt.

Runs asWho decides when it acts
ModTypeScript function hooks inside Claude CodeThe mod's own code
SkillInstructions the model readsThe model
Plain pluginCommands, agents or shell hooksYou, or a shell script

The mods

ModWhere it showsWhat it does
🧭 whats-nextPane in the side panelLists the next steps of your workflow, each with a prompt ready to paste
⚡ quick-replyBand above the promptOne-click replies, including the options Claude just offered, Pass, Fail and Skip for a verdict, and the next wayfinder ticket
⏳ auto-resumeBand and status lineCounts down to a rate limit's reset, then sends "continue"
🐙 github-panelPane in the side panelThe repo's open pull requests and issues, one click from the browser or from /implement and /wayfinder in the prompt; the issue a /wayfinder run works on, pinned with its next ticket; a toast when your branch's checks turn green or red
📚 shelfBand above the promptNamed folders and files; one click drops a path into what you are typing
🔔 turn-chimeSound and toastTells you when a long turn ends or Claude stops to ask you something
🔒 open-file-guardQuestion dialogAsks you to close a Word, Excel or PowerPoint file before Claude uses it
🌿 branch-guardQuestion dialogAsks you before Claude commits or pushes on the default branch
🔑 env-guardQuestion dialogAsks you before Claude reads a .env or key file, and refuses when no one is there to answer
🩹 bash-quoting-rescueRefused tool callStops a shell command that does not parse, such as an unclosed quote, before any of it runs
📂 outputsPane in the side panelThe files this session made or changed, newest first; click one to open it
🔎 sourcesPane in the side panelThe files Claude read, grouped by where they came from, with a lock to the project folder
📊 hudTwo lines under the promptModel, effort, context window, rate limits, turn timer, tool calls, agents, git state, worktree, cost, session length and folder, each named and in colour
🧹 post-merge-cleanupQuestion dialog and toastAfter a PR merges, /cleanup switches to the default branch, pulls and deletes the branch
🧾 pre-pr-claims-checkRefusal Claude readsRefuses gh pr create and gh pr edit while the pull request cites a file and line, holds a placeholder, or spells out a count
🚦 lint-test-gateBand above the promptRuns your checks on a press and before Claude's git commit, and hands back only the failures
🔄 chrome-tab-self-healNote after a browser tool's errorWhen a Claude in Chrome tab is gone, tells Claude to fetch the current tab IDs before it tries again
🏷 session-auto-namerBand above the promptSuggests a name for the session from its first prompt; one press renames it
🧠 model-effort-presetsBand above the promptPlan and execute presets: one press switches the model and the effort together
⚙ mod-settingsGear on each pane; a dialogChange and save any mod's settings without leaving the session

When more than one mod has a pane open, Claude Code shows them as tabs in the side panel.

🧭 whats-next

A pane listing the next steps of your workflow for the project folder, kept between sessions. A skill of your choosing answers "what's next" in a headless run beside your session, and the mod turns the answer into steps.

What's next                        refresh
updated 3 min ago

Fix the failing parse test
working on it  done
The check is red, so nothing else can merge.

Open a pull request for the fix
Review comes before the next feature starts.

Triage the two new issues
They arrived while you were heads-down.
flowchart LR
    A[Skill answers<br/>what's next] --> B[Steps in the pane]
    B --> C[You read a step's prompt<br/>and send it yourself]
    C --> D[Step glows:<br/>working on it]
    D --> E{Laya, Jev or Haiku:<br/>is the step finished?}
    E -- not yet --> D
    E -- yes --> F[Step leaves the list]
  • You stay in charge. A step's prompt reaches the model only when you read it and send it yourself. Click a step to see its prompt, then paste it, paste it into a fresh session (after your prime command, if you name one), or copy it.
  • It notices when you are done. After each answered turn, a System One model is asked whether the step is finished, as your System One models setting allows, and Haiku when none answers surely enough. A finished step leaves the list. Press d to drop it yourself.
  • The run that asks is read-only. By default it gets only read commands of git and gh plus Read, Glob and Grep. git push, git config, git -c, gh api and --output are always denied.
Command or keyWhat it does
/whats-nextBring the pane to the front
/whats-next refreshAsk the skill again
rRefresh
1 to 9Show that step's prompt in the pane
p, n, cPaste the shown prompt, paste it after /clear (and the prime command, once its turn ends), or copy it
bBack to the list
dMark the active step done
SettingKeyDefaultMeaning
Skillskill/ask-seanThe skill that answers "what's next", written as you would run it: / followed by letters, digits, _, :, . or -
Most stepsmaxSteps5How many steps to ask for (1-9)
Refresh on startrefreshOnStartonAsk for a fresh list when a session starts in a git repository
Tools the headless run may useallowedToolsempty: the read-only setComma-separated permission rules for the headless run
Modelmodelempty: your defaultModel for the headless run, as an alias (haiku) or a full id
Prime commandprimeCommandempty: noneA slash command, with any arguments, run after /clear and before the paste (/lril:prime); the prompt is filled once the turn it starts ends, finished or not. A value that is not one slash command on one line is never run, and the step view says so
System One modelsmodelChoicelocal onlyWhich System One model judges whether a turn finished the active step: local only (Laya on this machine, or Haiku as before), local first (Laya, and TypeSafe's hosted Jev while Laya is unavailable) or hosted first (Jev, and Laya while Jev is unavailable)
Jev API keyjevApiKeyemptyYour key for Jev, from console.typesafe.ai, kept in secure storage. Sent only to https://api.typesafe.ai, and only while System One models allows Jev
Laya portlayaPort8000The port your laya-serve listens on at 127.0.0.1 (1-65535)

/ask-sean is the author's own skill, so point the Skill setting at a skill of yours that answers "what should I do next?" (how to set it):

echo '{"skill": "/next-steps", "maxSteps": "3", "model": "haiku"}' | claude plugin configure whats-next@claude-mods --values-stdin

The read-only set, used while Tools is empty, is Bash(git status:*), Bash(git log:*), Bash(git diff:*), Bash(git show:*), Bash(git rev-parse:*), Bash(git branch --show-current), Bash(git branch -vv), Bash(git remote -v), Bash(gh issue list:*), Bash(gh issue view:*), Bash(gh pr list:*), Bash(gh pr view:*), Bash(gh pr checks:*), Bash(gh run list:*), Read, Glob and Grep.

  • A list you write replaces that set; it does not add to it. To widen the set, write all of it plus your additions.
  • Each rule is a tool name, optionally followed by (...). One rule that is not, such as one starting with -, discards your whole list and the read-only set is used.
  • The run can always call Skill, so a skill that calls another still works. MCP servers load only when a rule names an mcp__ tool.

What the judge sends to a System One model, once after each answered turn while a step is active:

  • To Jev, only while System One models allows it and the folder is not marked local-only: the active step's title, reason and prompt and the last 8,000 characters of Claude's answer. Never the contents of a file the mod read itself.
  • To Laya, which keeps it on this machine: the same, fitted to Laya's small window. The step's prompt is dropped first, then the start of the answer, so the end of the answer, where Claude says whether the work is done, is kept.
  • Sure answers only. "Done" counts at a probability of 0.9 or more and "not done" at 0.1 or less. Anything between, a model that is busy or fails, or no answer within 5 s leaves the step to Haiku, as before.
  • A key it cannot use is named. While System One models allows Jev, a missing key, one that is not a key, or one TypeSafe rejects is named on a line in the pane, and the list stays. A rejected key stays off until the mod reloads.
  • A changed key takes effect once the mod reloads. Saving it in the settings dialog reloads the mod; a key changed any other way waits for the next start of Claude Code.

Needs: the claude CLI on the PATH, and the skill named in the Skill setting. Laya and a Jev key are optional: with neither, the judge is Haiku, as before.

⚡ quick-reply

One row of buttons above the prompt after each answer. When Claude ends on a question, the band offers the choices Claude asked you to pick from, then your replies to a question. After any other answer it offers your other replies. You set both lists in the settings below.

Reply:  [a: Keep the copies]  [b: Add a sync script]  [Yes]  [Go with your recommendation]  [No]
  • A choice's button sends its marker with its label, so the model cannot misread it.
  • A numbered report before a yes-or-no question ("Shall I commit?") is not offered as choices.
  • When the answer recommends something, the "recommend" reply is the highlighted one. Advice against something does not count.
  • The band stays out of the way while Claude is working, and after a subagent's turn.
  • A model can read the ending too. After each answered turn, a System One model is asked how the answer ends, as your System One models setting allows: whether it asks you something, whether its numbered items are choices, and which one it recommends. The band shows its own reading at once, and a sure answer that arrives within 2 s takes its place, so a numbered report closed by "push now or wait?" is not offered as choices.

Verdicts. When Claude asks for a pass/fail verdict on a test or a check, as a UAT or /gsd:verify-work step does ("Pass or fail?", "Did it pass?", "Type pass or describe what's wrong"), the band offers a verdict in place of your replies:

Reply:  [Pass]  [Fail…]  [Skip]

Pass sends "pass" and Skip sends "skip", as your own message. Fail… sends nothing: it puts "Fail: " in the prompt, where you say what went wrong and can paste a screenshot. A test's numbered steps are not offered as choices, and a question that only mentions passing ("Shall I make the tests pass?") gets your usual replies.

Next ticket. When you work a map with the wayfinder skill, the band leads with the next ticket after each turn that closes one or charts the map:

Reply:  [Next ticket: /wayfinder 135]  [Continue]  [Commit and push]

One press runs /clear and then /wayfinder 135, the loop you would otherwise type. It is offered only in a session that ran the wayfinder skill, after a turn whose gh issue close worked; after charting it names the map the turn created. A close made some other way (gh api, the web) is not seen, so no button shows, and once a turn closes the map itself the loop ends.

SettingKeyDefaultMeaning
Replies to a questionquestionReplies`Yes\Go with your recommendation\No`Shown after Claude asks something, separated by `\`; empty shows only the choices Claude offered
Replies otherwiseidleReplies`Continue\Commit and push`Shown after any other answer; empty hides the band then, except for Next ticket
Offer the next wayfinder ticketwayfinderNexttrueAfter a wayfinder turn closes a ticket or charts a map, offer Next ticket
System One modelsmodelChoicelocal onlyWhich System One model reads how each answer ends: local only (Laya on this machine, or the band's own reading as before), local first (Laya, and TypeSafe's hosted Jev while Laya is unavailable) or hosted first (Jev, and Laya while Jev is unavailable)
Jev API keyjevApiKeyemptyYour key for Jev, from console.typesafe.ai, kept in secure storage. Sent only to https://api.typesafe.ai, and only while System One models allows Jev
Laya portlayaPort8000The port your laya-serve listens on at 127.0.0.1 (1-65535)

Each list holds up to six replies. A reply longer than 120 characters is cut short, and a repeat is dropped. For example, to answer questions with your own three replies and hide the band after other answers (how to set it):

echo '{"questionReplies": "Yes|No|Explain that first", "idleReplies": ""}' | claude plugin configure quick-reply@claude-mods --values-stdin

What the band sends to a System One model, once after each answered turn:

  • To Jev, only while System One models allows it and the folder is not marked local-only: the last 8,000 characters of Claude's answer and the labels of the choices found in it. Never the contents of a file the mod read itself.
  • To Laya, which keeps it on this machine: the answer's closing lines that fit Laya's small window, where the question is, and at most 9 labels of at most 40 characters.
  • Sure answers only. Each part of the reading counts only when the model is sure of it, at 0.9 or more (0.1 or less for "these are not choices"). Anything less, a model that is busy or fails, a reading Laya reports as cut, or no answer within 2 s leaves the band's own reading. So does a reading that arrives after your next prompt.
  • A key it cannot use is named. While System One models allows Jev, a missing key, one that is not a key, or one TypeSafe rejects is named on a dim line under the replies, until your next prompt. A rejected key stays off until the mod reloads.

Laya and a Jev key are optional: with neither, the band reads each answer as before.

⏳ auto-resume

When a turn dies on a rate limit or an overloaded API, auto-resume counts down to the reset and sends "continue" for you. Go to lunch, and come back to finished work.

⏳ rate limited:  sending "continue" in 1 h 12 min  [Resume now]  [Cancel]
  • The countdown shows above the prompt and in the status line.
  • Send a prompt of your own and it steps aside: you took over.
  • It gives up after too many resumes in a row without a successful answer.
CommandWhat it does
/auto-resumeSay what is waiting, if anything
/auto-resume nowSend the resume now
/auto-resume cancelCancel the wait
/auto-resume in <minutes>Schedule a resume yourself (1 to 1440)
SettingKeyDefaultMeaning
Resume prompttextcontinueWhat is sent when the wait is over; empty sends continue
Grace after reset (s)graceSeconds60Extra seconds to wait past the limit's reset time (0-900)
Retry overloaded/server errorsretryOverloadedonAlso resume after an overloaded or server error, backing off from one minute
Most retries in a rowmaxRetries5Give up after this many resumes without a successful answer (1-20)

For example, to send a longer prompt and wait two minutes past the reset (how to set it):

echo '{"text": "continue where you left off", "graceSeconds": "120"}' | claude plugin configure auto-resume@claude-mods --values-stdin

🐙 github-panel

A GitHub pane beside What's next listing the repo's open pull requests and issues. Click one to open it in the browser. Under each issue, implement and wayfinder put /implement or /wayfinder and the issue's URL in the prompt. Nothing is sent. While a /wayfinder effort is under way, its issue is pinned at the top, with the next ticket to take.

octocat/hello-world                refresh
updated just now

Decide how shared code is copied unpin
3 done · 1 takeable · 1 claimed · 2 blocked
next: Pick the drift check decision
work next

Pull requests 2                        all
#41 Add a drift check for copied guards
  draft · @octocat
#40 Bring the asked pane to the front
  ✗ checks failing · @hubot           fix

Issues 2                               all
#39 Share the headless-session check
  blocked by #12 · ready… implement wayfinder
#12 Decide how shared code is copied
  needs-triage · @hubot implement wayfinder
  • An issue blocked by an open issue has a red line under it. Hover it to see what blocks it.
  • In a narrow pane the implement and wayfinder buttons take a line of their own.
  • The lists refresh on a timer, after a turn once they are a minute old, and on r.
  • The pull request of the branch you are on is watched: when its checks turn green or red, a toast says "Checks passed on #40" or "Checks failed on #40". The first refresh, and the first after you switch branch, only notes where the checks stand.
  • While that pull request's checks fail, its row has a fix button. It fills the prompt box with the failed checks' names, the last 40 lines of the failed run's log, and "Fix it." Nothing is sent: you read it and send it yourself. The log is fetched only when you press fix; when gh cannot fetch it, such as while the run is still going, the prompt holds the names alone.
  • Running /wayfinder on an issue of this repo (/wayfinder 12, /wayfinder #12 or the issue's URL) pins that issue and brings the pane to the front. Anything else, such as prose or another repo's issue, pins nothing. The pin is kept for the repo across sessions, one at a time: a run on another issue replaces it. It goes when you press unpin, or once the issue is closed.
  • The pinned issue's sub-issues are its tickets, each counted once: closed ones are done, open ones with an open blocker are blocked, assigned ones are claimed, and the rest are takeable. next is the first takeable ticket in the order the issue lists its sub-issues, with its wayfinder: type label; click it to open it on GitHub. With nothing takeable it says so; an issue with no sub-issues yet says no tickets yet.
  • work next fills /wayfinder and the pinned issue's URL into the prompt, without sending it, so the skill takes the frontier ticket fresh when it runs.
  • The pinned issue is read in the same refresh as the lists. When a refresh fails, the last section stays and the error shows.
Command or keyWhat it does
/githubBring the pane to the front and refresh it
rRefresh
allOpen the whole list on GitHub
implement, wayfinderFill the command and the issue's URL into the prompt, without sending it
fixFill a request to fix the current branch's failing checks into the prompt box
unpinDrop the pinned issue
work nextFill /wayfinder and the pinned issue's URL into the prompt, without sending it
SettingKeyDefaultMeaning
Most items per listlimit30How many open pull requests and issues to list each (1-100)
Refresh every (minutes)refreshMinutes5How often to refresh (0-120); 0 refreshes only on open, after turns and on r
Implement button fillsimplementCommand/implementThe slash command the implement button fills before the issue's URL; empty hides the button
Wayfinder button fillswayfinderCommand/wayfinderThe slash command the wayfinder and work next buttons fill before the issue's URL, and the skill whose runs pin an issue; empty hides the button and turns pinning off

A command must start with / and hold no spaces. Any other value falls back to the default, and a message says so when the session starts. A button is labelled with its command, without the /.

For example, to list fifty of each and stop the timer (how to set it):

echo '{"limit": "50", "refreshMinutes": "0"}' | claude plugin configure github-panel@claude-mods --values-stdin

Needs: the GitHub CLI, logged in, and a folder with a GitHub remote.

📚 shelf

A row of named folders and files above the prompt, for the paths you type again and again. Click a name and its path lands at the cursor in what you are typing. Nothing is sent.

Shelf:  [brand]  [records]  [kb]
  • A path with a space arrives in double quotes, ready to use.
  • The shelf is the same in every project folder and every session.
  • When the names do not fit one row, the band shows those that do and counts the rest; /shelf always lists them all.
CommandWhat it does
/shelfList the shelf with each path
/shelf add <name> [path]Put a path on the shelf; with no path, the project folder
/shelf remove <name>Take one off

The shelf has no settings: you fill it with /shelf add.

/shelf add brand "N:/Marketing/Brand Kit"
/shelf add records N:/RECORDS
/shelf add kb
/shelf remove brand
  • A name is one word of up to 24 characters. Adding a name already on the shelf, whatever its capitals, replaces that entry where it stands.
  • The path is k
Source 3 files
hooks/register.ts 214 lines
1import { atom, update } from 'claude-code'
2import type { EngineInterface, ProcessRunResult, Register } from 'claude-code'
3
4import {
5  decide,
6  isSamePath,
7  lastLine,
8  missingRequirement,
9  NEEDS_GH,
10  NEEDS_GIT,
11  NOT_A_REPO,
12  parsePrs,
13  parseWorktrees,
14  pickPr,
15  PR_FIELDS,
16  question,
17  summary,
18} from './plan'
19import type { Checkout, Facts, PullRequest, Step } from './plan'
20
21const COMMAND = 'cleanup'
22const GO = 'Go'
23const CANCEL = 'Cancel'
24/** A pull or a prune talks to the remote; give it longer than the 30 s default. */
25const STEP_TIMEOUT_MS = 120_000
26/** The start-up suggestion stays long enough to read the command in it. */
27const SUGGEST_MS = 8_000
28
29const hasChecked = atom({ plugin: 'post-merge-cleanup', key: 'hasChecked' } as const, false)
30
31/** A requirement the mod lacks, carrying the sentence that names it. */
32class Missing extends Error {}
33
34/**
35 * Whether any surface shows the session right now. Asked before the start-up
36 * check, never kept. Each mod carries its own copy (ADR-0001).
37 */
38async function isShown($: EngineInterface): Promise<boolean> {
39  return (await $.session.surfaces()).length > 0
40}
41
42/** Runs git or gh by bare name; one that cannot start is a missing requirement. */
43async function run($: EngineInterface, argv: readonly string[], cwd?: string): Promise<ProcessRunResult> {
44  try {
45    return await $.process.run(argv, cwd === undefined ? {} : { cwd })
46  } catch (error) {
47    // A timeout rejects too; tell it from a missing tool by whether the tool starts at all.
48    const tool = argv[0] ?? ''
49    if (!(await canStart($, tool))) throw new Missing(tool === 'gh' ? NEEDS_GH : NEEDS_GIT)
50    throw error
51  }
52}
53
54async function canStart($: EngineInterface, tool: string): Promise<boolean> {
55  try {
56    await $.process.run([tool, '--version'])
57    return true
58  } catch {
59    return false
60  }
61}
62
63/** Runs a command that must succeed and answers its trimmed output. */
64async function ask($: EngineInterface, argv: readonly string[], cwd?: string): Promise<string> {
65  const result = await run($, argv, cwd)
66  if (result.exitCode !== 0) {
67    if (argv[0] === 'gh') {
68      const missing = missingRequirement(result.exitCode, result.stderr)
69      if (missing !== undefined) throw new Missing(missing)
70    }
71    throw new Error(`${argv.slice(0, 3).join(' ')} failed: ${lastLine(result.stderr) || `exit ${result.exitCode}`}`)
72  }
73  return result.stdout.trim()
74}
75
76async function defaultBranch($: EngineInterface): Promise<string> {
77  return ask($, ['gh', 'repo', 'view', '--json', 'defaultBranchRef', '--jq', '.defaultBranchRef.name'])
78}
79
80async function findPr($: EngineInterface, branch: string): Promise<PullRequest | undefined> {
81  const json = await ask($, ['gh', 'pr', 'list', '--head', branch, '--state', 'all', '--limit', '10', '--json', PR_FIELDS])
82  return pickPr(parsePrs(json))
83}
84
85/** The local branch's tip, or '' when there is no such branch. */
86async function tipOf($: EngineInterface, branch: string): Promise<string> {
87  const result = await run($, ['git', 'rev-parse', '--verify', '--quiet', `refs/heads/${branch}`])
88  return result.exitCode === 0 ? result.stdout.trim() : ''
89}
90
91async function isClean($: EngineInterface, cwd?: string): Promise<boolean> {
92  return (await ask($, ['git', 'status', '--porcelain'], cwd)) === ''
93}
94
95/** Everything decide() needs, read from git and gh; nothing here changes the checkout. */
96async function gather($: EngineInterface, args: string): Promise<Facts> {
97  const top = await run($, ['git', 'rev-parse', '--show-toplevel'])
98  if (top.exitCode !== 0) throw new Missing(NOT_A_REPO)
99  const sessionPath = top.stdout.trim()
100  const currentBranch = await ask($, ['git', 'branch', '--show-current'])
101  const branch = args.trim() === '' ? currentBranch : args.trim()
102  const base = await defaultBranch($)
103  if (branch === '' || branch === base) {
104    return { branch, currentBranch, defaultBranch: base, pr: undefined, tip: '', isTreeClean: true, checkout: undefined }
105  }
106
107  const [pr, tip, isTreeClean, worktrees] = await Promise.all([
108    findPr($, branch),
109    tipOf($, branch),
110    isClean($),
111    ask($, ['git', 'worktree', 'list', '--porcelain']).then(parseWorktrees),
112  ])
113  const index = worktrees.findIndex(worktree => worktree.branch === branch)
114  let checkout: Checkout | undefined
115  if (index >= 0) {
116    const path = worktrees[index]!.path
117    const isSession = isSamePath(path, sessionPath)
118    const isMain = index === 0
119    // Only a worktree that would be removed needs its own check.
120    checkout = { path, isMain, isSession, isClean: isSession || isMain ? true : await isClean($, path) }
121  }
122  return { branch, currentBranch, defaultBranch: base, pr, tip, isTreeClean, checkout }
123}
124
125/** Runs the steps in order, stopping at the first failure; answers what to tell the person. */
126async function carryOut($: EngineInterface, branch: string, steps: readonly Step[]): Promise<string> {
127  for (const step of steps) {
128    let result: ProcessRunResult
129    try {
130      result = await $.process.run(step.argv, { timeoutMs: STEP_TIMEOUT_MS })
131    } catch (error) {
132      return `Cleanup stopped at "${step.todo}": ${error instanceof Error ? error.message : String(error)}`
133    }
134    if (result.exitCode !== 0) {
135      return `Cleanup stopped at "${step.todo}": ${lastLine(result.stderr) || lastLine(result.stdout) || `exit ${result.exitCode}`}`
136    }
137  }
138  return summary(branch, steps)
139}
140
141async function cleanup($: EngineInterface, args: string): Promise<string> {
142  const facts = await gather($, args)
143  const decision = decide(facts)
144  if ('refuse' in decision) return decision.refuse
145
146  let answer: string
147  try {
148    answer = await $.ui.ask(question(decision.pr, decision.steps), { options: [GO, CANCEL], header: 'Cleanup' })
149  } catch {
150    // Dismissed, or nobody to ask (a -p run).
151    return 'Cleanup cancelled; nothing was changed.'
152  }
153  if (answer !== GO) return 'Cleanup cancelled; nothing was changed.'
154
155  const said = await carryOut($, facts.branch, decision.steps)
156  $.ui.toast(said)
157  return said
158}
159
160/** The start-up check: one look at the session's branch, and a toast when its PR has merged. */
161async function suggest($: EngineInterface): Promise<void> {
162  const branch = await ask($, ['git', 'branch', '--show-current'])
163  if (branch === '') return
164  const [base, pr] = await Promise.all([defaultBranch($), findPr($, branch)])
165  if (branch === base || pr?.state !== 'MERGED') return
166  $.ui.toast(`PR #${pr.number} for ${branch} merged. Run /${COMMAND} to switch to ${base}, pull and delete the branch.`, {
167    timeoutMs: SUGGEST_MS,
168  })
169}
170
171/** Runs the start-up check once per session, and only while a surface shows it. */
172async function checkOnce($: EngineInterface): Promise<void> {
173  if (!(await isShown($))) return
174  let isFirst = false
175  await update($, hasChecked, was => {
176    isFirst = !was
177    return true
178  })
179  if (isFirst) await suggest($)
180}
181
182/** Quiet on failure: a missing gh is named when the person runs /cleanup, not at start. */
183function logQuietly($: EngineInterface): (error: unknown) => void {
184  return error => $.ui.log(`post-merge-cleanup: start-up check: ${error instanceof Error ? error.message : String(error)}`, { to: 'debug' })
185}
186
187export const register: Register = on => {
188  on('session.start', async ($, e, next) => {
189    await $.command.register({
190      name: COMMAND,
191      description: 'After a PR merges: switch to the default branch, pull, and delete the branch and its worktree',
192      argumentHint: '[branch]',
193    })
194    const done = await next(e)
195    void checkOnce($).catch(logQuietly($))
196    return done
197  })
198
199  // A session that started headless checks once when a surface first shows it.
200  on('session.attach', async ($, e, next) => {
201    const done = await next(e)
202    void checkOnce($).catch(logQuietly($))
203    return done
204  })
205
206  on('command.run', { command: COMMAND }, async ($, e) => {
207    try {
208      return { text: await cleanup($, e.args) }
209    } catch (error) {
210      return { text: error instanceof Missing ? error.message : `Cleanup failed: ${error instanceof Error ? error.message : String(error)}` }
211    }
212  })
213}
214
hooks/plan.ts 188 lines
1/** The fields asked of `gh pr list`; parsePrs reads these. */
2export const PR_FIELDS = 'number,state,headRefOid'
3
4export type PullRequest = {
5  number: number
6  state: 'OPEN' | 'CLOSED' | 'MERGED'
7  /** The commit the PR's head pointed at: for a merged PR, the commit it merged. */
8  headRefOid: string
9}
10
11/** One entry of `git worktree list --porcelain`; `branch` is '' for a detached head. */
12export type Worktree = { path: string; branch: string }
13
14/** Where the branch to clean up is checked out, if anywhere. */
15export type Checkout = {
16  path: string
17  /** The main checkout: the first worktree git lists. It is never removed. */
18  isMain: boolean
19  /** The checkout this session runs in. */
20  isSession: boolean
21  /** Nothing staged, unstaged or untracked; only asked of a worktree that would be removed. */
22  isClean: boolean
23}
24
25/** What the mod found before deciding: every answer is git's or gh's. */
26export type Facts = {
27  /** The branch to clean up: the argument, or the session's branch. */
28  branch: string
29  /** The session's branch; '' for a detached head. */
30  currentBranch: string
31  defaultBranch: string
32  pr: PullRequest | undefined
33  /** The local branch's tip; '' when there is no such local branch. */
34  tip: string
35  /** The session's tree has nothing staged, unstaged or untracked. */
36  isTreeClean: boolean
37  checkout: Checkout | undefined
38}
39
40/** One git command of the cleanup, run in the session's folder. */
41export type Step = {
42  /** What it will do, for the question. */
43  todo: string
44  /** What it did, for the closing toast. */
45  done: string
46  argv: string[]
47}
48
49export type Decision = { refuse: string } | { pr: number; steps: Step[] }
50
51function isRecord(value: unknown): value is Record<string, unknown> {
52  return typeof value === 'object' && value !== null && !Array.isArray(value)
53}
54
55/** Parses `gh pr list --json PR_FIELDS`, dropping malformed rows; throws on output that is not a list. */
56export function parsePrs(json: string): PullRequest[] {
57  const rows: unknown = JSON.parse(json)
58  if (!Array.isArray(rows)) throw new Error('gh pr list did not answer a list')
59  return rows.flatMap((row): PullRequest[] => {
60    if (!isRecord(row)) return []
61    const { number, state, headRefOid } = row
62    if (typeof number !== 'number' || typeof headRefOid !== 'string') return []
63    if (state !== 'OPEN' && state !== 'CLOSED' && state !== 'MERGED') return []
64    return [{ number, state, headRefOid }]
65  })
66}
67
68/** The PR that speaks for a branch: a merged one first, then an open one, then any. gh lists the newest first. */
69export function pickPr(prs: readonly PullRequest[]): PullRequest | undefined {
70  return prs.find(pr => pr.state === 'MERGED') ?? prs.find(pr => pr.state === 'OPEN') ?? prs[0]
71}
72
73/** Parses `git worktree list --porcelain`: blocks of `worktree <path>`, then `branch refs/heads/<name>` or `detached`. */
74export function parseWorktrees(porcelain: string): Worktree[] {
75  const worktrees: Worktree[] = []
76  for (const line of porcelain.split(/\r?\n/)) {
77    if (line.startsWith('worktree ')) worktrees.push({ path: line.slice('worktree '.length), branch: '' })
78    const last = worktrees[worktrees.length - 1]
79    if (line.startsWith('branch refs/heads/') && last !== undefined) last.branch = line.slice('branch refs/heads/'.length)
80  }
81  return worktrees
82}
83
84/** Whether two paths git printed name the same folder: slashes folded, and case too for a Windows drive path. */
85export function isSamePath(a: string, b: string): boolean {
86  const fold = (path: string) => {
87    const slashed = path.replace(/\\/g, '/').replace(/\/+$/, '')
88    return /^[a-z]:\//i.test(slashed) ? slashed.toLowerCase() : slashed
89  }
90  return fold(a) === fold(b)
91}
92
93/**
94 * Decides from the facts: a refusal naming the first check that failed, or the
95 * steps to run. Nothing here changes the checkout; the steps run only after the
96 * person says Go.
97 */
98export function decide(facts: Facts): Decision {
99  const { branch, currentBranch, defaultBranch, pr, tip, checkout } = facts
100  if (branch === '') return { refuse: 'Not on a branch. Run /cleanup <branch> to name the branch to clean up.' }
101  if (branch === defaultBranch) return { refuse: `${branch} is the default branch; there is nothing to clean up.` }
102  if (pr === undefined) return { refuse: `${branch} has no pull request, so nothing was changed.` }
103  if (pr.state === 'OPEN') return { refuse: `PR #${pr.number} for ${branch} is still open, so nothing was changed.` }
104  if (pr.state === 'CLOSED') {
105    return { refuse: `PR #${pr.number} for ${branch} was closed without merging, so nothing was changed.` }
106  }
107  if (tip === '') return { refuse: `There is no local branch ${branch}, so there is nothing to delete.` }
108  if (tip !== pr.headRefOid) {
109    return {
110      refuse: `${branch} has commits that are not in PR #${pr.number}: its tip is not the commit the PR merged. Push or drop them first.`,
111    }
112  }
113  if (checkout?.isSession === true && !checkout.isMain) {
114    return {
115      refuse: `This session runs inside ${branch}'s own worktree. Run /cleanup ${branch} from the main checkout.`,
116    }
117  }
118  if (checkout?.isMain === true && !checkout.isSession) {
119    return { refuse: `${branch} is checked out in the main checkout at ${checkout.path}. Run /cleanup there.` }
120  }
121  if (!facts.isTreeClean) {
122    return { refuse: 'The working tree has uncommitted or untracked changes. Commit, stash or remove them first.' }
123  }
124  if (checkout !== undefined && !checkout.isSession && !checkout.isClean) {
125    return {
126      refuse: `The worktree at ${checkout.path} has uncommitted or untracked changes. Commit, stash or remove them first.`,
127    }
128  }
129
130  const steps: Step[] = []
131  if (currentBranch !== defaultBranch) {
132    steps.push({ todo: `switch to ${defaultBranch}`, done: `switched to ${defaultBranch}`, argv: ['git', 'switch', defaultBranch] })
133  }
134  steps.push({ todo: `pull ${defaultBranch}`, done: `pulled ${defaultBranch}`, argv: ['git', 'pull', '--ff-only'] })
135  if (checkout !== undefined && !checkout.isSession) {
136    steps.push({
137      todo: `remove the worktree at ${checkout.path}`,
138      done: `removed the worktree at ${checkout.path}`,
139      argv: ['git', 'worktree', 'remove', checkout.path],
140    })
141  }
142  // -D, not -d: a squash merge leaves the branch unmerged in git's eyes. The tip check above is what makes it safe.
143  steps.push({
144    todo: `delete ${branch} (PR #${pr.number} merged)`,
145    done: `deleted ${branch}`,
146    argv: ['git', 'branch', '-D', branch],
147  })
148  steps.push({ todo: 'prune remote-tracking branches', done: 'pruned', argv: ['git', 'fetch', '--prune'] })
149  return { pr: pr.number, steps }
150}
151
152/** The one question asked before anything changes. */
153export function question(pr: number, steps: readonly Step[]): string {
154  return `PR #${pr} merged. Clean up: ${steps.map(step => step.todo).join(', ')}?`
155}
156
157/** What the closing toast says. */
158export function summary(branch: string, steps: readonly Step[]): string {
159  return `Cleaned up ${branch}: ${steps.map(step => step.done).join(', ')}.`
160}
161
162/** What the person sees when gh cannot start. */
163export const NEEDS_GH = 'post-merge-cleanup needs the GitHub CLI (gh). Install it from cli.github.com, then run /cleanup again.'
164/** What the person sees when git cannot start. */
165export const NEEDS_GIT = 'post-merge-cleanup needs git. Install it from git-scm.com, then run /cleanup again.'
166/** What the person sees when gh is not logged in. */
167export const NOT_LOGGED_IN = 'gh is not logged in. Run gh auth login in a terminal, then run /cleanup again.'
168/** What the person sees outside a git repository. */
169export const NOT_A_REPO = 'This folder is not a git repository, so there is nothing to clean up.'
170/** What the person sees when the repository has no GitHub remote. */
171export const NOT_A_GITHUB_REPO = 'This repository has no GitHub remote, so gh cannot tell whether a PR merged.'
172
173/** gh's exit code for a command that needs authentication (`gh help exit-codes`). */
174const GH_AUTH_EXIT = 4
175
176/** The requirement a failed gh call names, or undefined when the failure is something else. */
177export function missingRequirement(exitCode: number, stderr: string): string | undefined {
178  if (exitCode === GH_AUTH_EXIT || /gh auth login|not logged in/i.test(stderr)) return NOT_LOGGED_IN
179  if (/no git remotes|none of the git remotes|not a git repository/i.test(stderr)) return NOT_A_GITHUB_REPO
180  return undefined
181}
182
183/** The last non-empty line of a command's output, cut short, for a toast. */
184export function lastLine(output: string): string {
185  const lines = output.trim().split(/\r?\n/)
186  return lines[lines.length - 1]?.slice(0, 200) ?? ''
187}
188
types/index.d.ts 11 lines
1/** Whether this session's start-up check for a merged PR has run: at start, or at the first attach. */
2export type HasChecked = boolean
3
4declare module 'claude-code' {
5  interface PluginState {
6    'post-merge-cleanup': {
7      hasChecked: HasChecked
8    }
9  }
10}
11