dotclaude-modder · Claude Code mod

README

dotclaude

dotclaude is a Claude Code plugin for software engineering on official extension points. It turns compaction off, sets a 300K context window, asks only before dangerous commands, replaces the coding part of the system prompt with a short output style, and keeps the state of long work in OpenSpec changes and handoff notes across /clear. It optimizes for the most quality per unit of usage quota, not for speed.

The wiki tells what each part does and why. Parts lists each part with its file and bound. Design gives the source of each design claim.

Install

/plugin marketplace add xsyetopz/dotclaude
/plugin install dotclaude@dotclaude

Requirements: Claude Code 2.1.292, Node.js 22.18 or later on PATH, and git. The hooks module uses the mods API of Claude Code, which can change between releases, so this release is tested only on 2.1.292.

Setup

Run /dotclaude:setup and restart Claude Code. A plugin settings file can set only agent and subagentStatusLine, so the skill merges the profile into a settings file that you choose. It shows each change and makes a backup first. It also checks OpenSpec and offers to install it and to run openspec init --tools claude.

Parts

Part	What it does
No compaction	`autoCompactEnabled: false` and `DISABLE_COMPACT=1`, which also turns off `/compact`.
Window	`CLAUDE_CODE_MAX_CONTEXT_TOKENS=300000` and `CLAUDE_CODE_AUTO_COMPACT_WINDOW=300000`. At the limit the session stops, and you run `/clear`.
No auto memory	`autoMemoryEnabled: false`. Handoff notes and OpenSpec hold the state.
System prompt	`CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=1` and the forced `dotclaude` output style, which replaces the built-in coding instructions.
Permissions	Deny secret reads and disk wipes. Ask before force pushes, history rewrites, piped shells, `sudo`, publishes, public `gh` writes, and SQL drops. Allow read-only git and the usual build and test commands.
Sandbox	Bash runs in the sandbox, with network access only to GitHub and the package registries.
Guard	One hooks module asks before a recursive `rm` outside the project, and before the first call to a GitHub repository of another owner with an AI policy.
Status line	Model, effort, context against the window (yellow at 75%, red at 90%), the 5-hour limit, and the active OpenSpec change with its task count.
Agents	`investigator`, `web-researcher`, `implementer`, `debugger`, `reviewer`, `test-runner`.
Skills	`/dotclaude:setup`, `/dotclaude:handoff`.

The plugin has no options. To drop a part of the profile, see the setup skill.

Models and effort

Model	Roles	Effort
Opus 5.5	main session, `reviewer`	default `medium`, `reviewer` `high`
Sonnet 5.5	`investigator`, `web-researcher`, `implementer`, `debugger`	`medium`
Haiku 4.5	`test-runner`	none

The profile sets no effort level, so each model keeps its default. maxEffortLevel is xhigh, so /effort can go up for a hard check.

Long work without compaction

Each turn reads the whole context again, so the size of the context sets the cost of a turn.

For work of more than one session, start an OpenSpec change with /opsx:propose. After /clear, /opsx:apply continues at the first unchecked task.
Before /clear, run /dotclaude:handoff to write the goal, the decisions, and the proof to .claude/handoffs/<slug>.md. Start the next session with @.claude/handoffs/<slug>.md.
Change the model only right after /clear, because a new model starts a new prompt cache. An effort change keeps the cache.

See Handoffs and OpenSpec.

Add-on plugins

Each add-on works without the core plugin.

/plugin install dotclaude-browser@dotclaude
/plugin install dotclaude-jev@dotclaude
/plugin install dotclaude-modder@dotclaude

dotclaude-browser has the drive-web-browser skill. It uses agent-browser, and its backend option selects CloakBrowser for sites with bot detection.
dotclaude-jev has the second-opinion skill, which asks TypeSafe Jev for probabilities on a close call. Export TYPESAFE_API_KEY before Claude Code starts. Each call sends the data of the decision to the TypeSafe API.
dotclaude-modder lets Claude mod a PC game that you own. It is a port of universal-modder by Rehan, and it needs Bun and uv. It adds one skill and the fal MCP server, so install it only where you mod games. For reverse engineering, use the skills in xsyetopz/skills. See Modder.

Update

claude plugin marketplace update dotclaude
claude plugin update dotclaude@dotclaude

Restart Claude Code, because a running session keeps the old hooks and agents.
Read the new entry in CHANGELOG.md. Before 1.0, a release can change or remove behavior without a compatibility layer.
Run /dotclaude:setup again. It shows each change.

0.27.0 is a rebuild that removes most 0.26 parts. See its changelog entry for the list. To try an unreleased checkout, run claude --plugin-dir /path/to/dotclaude/plugins/dotclaude.

Development

just check runs lint, tests, plugin validation, and the hook lab. just sandbox runs Claude Code with this checkout in a separate config. See Development and Sandbox.

License

MIT.

Source 1 files

hooks/module/index.mjs 32 lines

1// The hooks module of dotclaude-modder.
2// It enforces a rule of the `mod-any-game` skill:
3// it denies a Bash call that stops processes by name or by pattern,
4// because the name can also match the shell of Claude or other apps of the user.
5// `um win kill <pid>` stops one process by its PID.
6
7// The first pattern matches `pkill` and `killall` only in command position,
8// so that `grep pkill notes.md` passes.
9const KILL_BY_NAME = [
10  /(?:^|[;&|(`"'\n]|\$\()\s*(?:(?:sudo|env|nohup|exec|command|time)\s+(?:-\S+\s+)*)*(?:pkill|killall)\b/,
11  /\btaskkill\b[^;&|\n]*\/(?:im|fi)\b/i,
12  /\b(?:Stop-Process|spps)\b[^;&|\n]*\s-(?:n|na|nam|name|processname)\b/i,
13  /\|\s*(?:Stop-Process|spps)\b/i,
14  /\bkill\b[^;&|\n]*(?:\$\(|`)\s*(?:pgrep|pidof)\b/,
15  /\|\s*xargs\b[^;&|\n]*\bkill\b/,
16];
17
18export const KILL_REASON =
19  "This command stops processes by name or by pattern. A name can also match your own shell or other apps of the user. Find the PID with `um win ps`, and stop that one process with `um win kill <pid>`.";
20
21/** True when `command` stops processes by name or by pattern. */
22export const killsByName = (command) =>
23  KILL_BY_NAME.some((re) => re.test(command));
24
25export function register(on) {
26  on("tool.call", async (_$, e, next) =>
27    e.tool === "Bash" && killsByName(String(e.command ?? ""))
28      ? { deny: KILL_REASON }
29      : next(e),
30  );
31}
32