setup-project

name	setup-project
description	Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub, GitLab, Linear, or local markdown), triage label vocabulary, domain doc layout, review configuration, and hook wiring. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, `zoom-out`, or `review` — or if those skills appear to be missing context about the issue tracker, triage labels, domain docs, or review config.
disable-model-invocation	true

Setup Project

Scaffold the per-repo configuration that the engineering skills assume:

• Issue tracker — where issues live (GitHub, GitLab, Linear, or local markdown)
• Triage labels — the strings used for the five canonical triage roles
• Domain docs — where CONTEXT.md and ADRs live, and the consumer rules for reading them
• Review configuration — pre-flight commands, post-fix commands, generated file patterns, and extra reviewer focus areas
• Hook wiring — optional PreToolUse hooks to enforce formatting and guard generated files

This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.

Process

1. Explore

Look at the current repo to understand its starting state. Read whatever exists; don't assume:

• jj git remote list to get the remote URL — or read .git/config as a fallback (jj is co-located with git). Is this a GitHub, GitLab, or other repo?
• Check whether Linear MCP tools are available in the current session (look for tool names containing linear in the MCP tool list).
• AGENTS.md and CLAUDE.md at the repo root — does either exist? Is there already an ## Agent skills section in either?
• CONTEXT.md and CONTEXT-MAP.md at the repo root
• docs/adr/ and any src/*/docs/adr/ directories
• docs/agents/ — does this skill's prior output already exist?
• .scratch/ — sign that a local-markdown issue tracker convention is already in use

2. Present findings and ask

Summarise what's present and what's missing. Then walk the user through the five decisions one at a time — present a section, get the user's answer, then move to the next. Don't dump all five at once.

Assume the user does not know what these terms mean. Each section starts with a short explainer (what it is, why these skills need it, what changes if they pick differently). Then show the choices and the default.

Section A — Issue tracker.

Explainer: The "issue tracker" is where issues live for this repo. Skills like to-issues, triage, and to-prd read from and write to it — they need to know whether to call gh issue create, use Linear MCP tools, write a markdown file under .scratch/, or follow some other workflow you describe. Pick the place you actually track work for this repo.

Default posture: these skills were designed for GitHub. If the remote URL points at GitHub, propose that. If the remote URL points at GitLab (gitlab.com or a self-hosted host), propose GitLab. If Linear MCP tools are available in the session, mention Linear as a strong option. Otherwise (or if the user prefers), offer:

• GitHub — issues live in the repo's GitHub Issues (uses the gh CLI)
• GitLab — issues live in the repo's GitLab Issues (uses the glab CLI)
• Linear — issues live in Linear (uses Linear MCP tools)
• Local markdown — issues live as files under .scratch/<feature>/ in this repo (good for solo projects or repos without a remote)
• Other (Jira, etc.) — ask the user to describe the workflow in one paragraph; the skill will record it as freeform prose

Section B — Triage label vocabulary.

Explainer: When the triage skill processes an incoming issue, it moves it through a state machine — needs evaluation, waiting on reporter, ready for an AFK agent to pick up, ready for a human, or won't fix. To do that, it needs to apply labels (or the equivalent in your issue tracker) that match strings you've actually configured. If your repo already uses different label names (e.g. bug:triage instead of needs-triage), map them here so the skill applies the right ones instead of creating duplicates.

The five canonical roles:

• needs-triage — maintainer needs to evaluate
• needs-info — waiting on reporter
• ready-for-agent — fully specified, AFK-ready (an agent can pick it up with no human context)
• ready-for-human — needs human implementation
• wontfix — will not be actioned

Default: each role's string equals its name. Ask the user if they want to override any. If their issue tracker has no existing labels, the defaults are fine.

Section C — Domain docs.

Explainer: Some skills (improve-codebase-architecture, diagnose, tdd) read a CONTEXT.md file to learn the project's domain language, and docs/adr/ for past architectural decisions. They need to know whether the repo has one global context or multiple (e.g. a monorepo with separate frontend/backend contexts) so they look in the right place.

Confirm the layout:

• Single-context — one CONTEXT.md + docs/adr/ at the repo root. Most repos are this.
• Multi-context — CONTEXT-MAP.md at the root pointing to per-context CONTEXT.md files (typically a monorepo).

Section D — Review configuration.

Explainer: The /review skill runs multiple reviewer agents across your code. To work well, it needs to know what commands to run before reviewing (formatters, generators, linters), what to run after fixing issues (tests, checks), which files are machine-generated (so it can flag changes but not review them line-by-line), and any project-specific focus areas beyond the standard security/performance/correctness/quality/spec reviewers.

Walk through each sub-section:

• Pre-flight commands — formatters, generators, linters to run before review begins. Run in order; abort review if any fail. Examples: nix fmt, npm run lint, go generate ./....
• Post-fix commands — tests, type checks, build commands to run after applying review fixes. Examples: npm test, cargo test, nix flake check.
• Generated file patterns — glob patterns for machine-generated files. Review flags changes to these with a warning but doesn't review them. Examples: *.generated.ts, src/graphql/types.ts, flake.lock.
• Extra reviewer focus areas — project-specific rules beyond the 5 standard reviewers (security, performance, correctness, code quality, spec compliance). Each entry is included in the relevant reviewer agent's brief.

See review-config.md for the template.

Section E — Hook wiring.

Explainer: Claude Code supports hooks — shell commands that run automatically before or after tool calls. We can wire up hooks to enforce the pre-flight commands from Section D (e.g. auto-run formatters after file edits) and to guard generated files (warn before editing them). Hooks go in .claude/settings.json (committed, shared with the team) or .claude/settings.local.json (personal, not committed).

Ask the user:

1. Whether they want hooks at all. If they have no pre-flight commands and no generated file patterns from Section D, skip this.
2. If yes, whether hooks should go to .claude/settings.json (committed) or .claude/settings.local.json (personal).
3. Then configure:
   • Pre-flight hooks: PreToolUse hooks that run formatters/linters after file writes (triggered on write_to_file, edit_file, or equivalent tool names).
   • Generated file guards: PreToolUse hooks that check whether the target file matches a generated file pattern and emit a warning before proceeding.

3. Confirm and edit

Show the user a draft of:

• The ## Agent skills block to add to whichever of CLAUDE.md / AGENTS.md is being edited (see step 4 for selection rules)
• The contents of docs/agents/issue-tracker.md, docs/agents/triage-labels.md, docs/agents/domain.md, docs/agents/review.md
• If hooks were configured, the hooks JSON to add to the chosen settings file

Let them edit before writing.

4. Write

Pick the file to edit:

• If CLAUDE.md exists, edit it.
• Else if AGENTS.md exists, edit it.
• If neither exists, ask the user which one to create — don't pick for them.

Never create AGENTS.md when CLAUDE.md already exists (or vice versa) — always edit the one that's already there.

If an ## Agent skills block already exists in the chosen file, update its contents in-place rather than appending a duplicate. Don't overwrite user edits to the surrounding sections.

The block:

## Agent skills

### Issue tracker

[one-line summary of where issues are tracked]. See `docs/agents/issue-tracker.md`.

### Triage labels

[one-line summary of the label vocabulary]. See `docs/agents/triage-labels.md`.

### Domain docs

[one-line summary of layout — "single-context" or "multi-context"]. See `docs/agents/domain.md`.

### Review configuration

[one-line summary of pre-flight/post-fix commands]. See `docs/agents/review.md`.

Then write the docs files using the seed templates in this skill folder as a starting point:

• issue-tracker-github.md — GitHub issue tracker
• issue-tracker-gitlab.md — GitLab issue tracker
• issue-tracker-linear.md — Linear issue tracker
• issue-tracker-local.md — local-markdown issue tracker
• triage-labels.md — label mapping
• domain.md — domain doc consumer rules + layout
• review-config.md — review configuration template

For "other" issue trackers, write docs/agents/issue-tracker.md from scratch using the user's description.

If hooks were configured in Section E, write the hooks JSON to the chosen settings file (.claude/settings.json or .claude/settings.local.json), merging with any existing content.

5. Done

Tell the user the setup is complete and which engineering skills will now read from these files. Mention they can edit docs/agents/*.md directly later — re-running /setup-project is only necessary if they want to switch issue trackers, reconfigure review settings, or restart from scratch.