// Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Use whenever the user wants to bootstrap, scaffold, generate, create, set up, or audit AGENTS.md / CLAUDE.md / agents.md (the operational guide for agents working on this project).
| name | ad-bootstrap |
| description | Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Use whenever the user wants to bootstrap, scaffold, generate, create, set up, or audit AGENTS.md / CLAUDE.md / agents.md (the operational guide for agents working on this project). |
| summary | Generate or audit `AGENTS.md` at the repo root. |
<background_information>
Produces AGENTS.md at the repo root, ≤150 lines, every line operational. Generic agent behavior (think-before-coding, verify-before-claiming-done, etc.) does NOT belong here — that lives in the ad-philosophy skill.
Three modes, detected from filesystem state:
AGENTS.md exists at the repo root → audit (do not rewrite, output drift list only)AGENTS.md absent and only trivial files present (.git, node_modules, .gitignore, .gitattributes, .DS_Store, .env*, .idea, .vscode, LICENSE*, README.md) → greenfield (interview by placeholder, no scan)AGENTS.md absent and meaningful code present → brownfield (scan first, pre-fill, ask only gaps)
</background_information>Step 1 — scan (brownfield only). Read in this order, taking the first that exists for each category:
package.json, pyproject.toml, Cargo.toml, go.mod, Gemfile, composer.json, pubspec.yaml.README.md, plus any doc/ or docs/ directory.doc/adr/ — binding decisions; read every ADR.GUIDELINES.md at repo root — if present, the AGENTS.md sections that have a corresponding GUIDELINES.md section (Code Style → §2; Quality Gates → §8; Commit & PR → §10; Security & Privacy → §12) emit as pointer stubs instead of inline rules' ' reciprocity and ADR-0030 §1..claude/, .cursor/, .openai/, .agents/ — existing agent config..husky/, .pre-commit-config.yaml, .github/workflows/, .gitlab-ci.yml, .circleci/.package-lock.json, yarn.lock, pnpm-lock.yaml, poetry.lock, Cargo.lock.git remote -v for the repo URL.Build a model of: stack (languages and versions), entry points, build / test / lint commands, conventions, quality gates, security boundaries, gotchas confirmed by code.
Step 2 — pre-fill. For every <placeholder> in the template, fill from observed signals. No fabrication. If a section has no signal, write <TODO: not yet wired> in one line and move on. Do not write meta-prose explaining the gap.
Step 3 — show only the gaps. Print to the user:
One question per gap. Skip everything filled confidently. Do NOT ask philosophical questions ("is this doc for agents or humans?", "what is the most important quality bar?") — those are decisions, not interview material.
Step 4 — write the file. On user confirmation, write AGENTS.md at the repo root. Cut every line that does not change agent behavior. No "External Resources" section (URLs are derivable from git remote and the manifest). No appended Universal Agent Behavior block. No marketing prose.
Audit-mode override: do NOT write the file. Produce a drift list. Format each line as:
[file or section]: spec says X, code says Y. Suggested resolution: change spec / change code / discuss.
If something the user says contradicts what the code shows, surface the conflict. Don't silently trust the user; don't silently trust the code.
<output_contract>
A single AGENTS.md at the repo root, ≤150 lines, every line operational. No "External Resources" section. No appended Universal Agent Behavior block — that lives in the ad-philosophy skill. No meta-prose explaining gaps. In audit mode: a drift list, no file written.
AGENTS.md is a narrative document, so the Documentation Discipline rules in WORKFLOW.md §2 apply at write time:
DRAFT markers, or changelog blocks. Stack versions are facts (Node ≥18); release timelines are not.Project Overview is the business-context-first paragraph — why the project exists before what it does.ARCHITECTURE.md patterns or ADR rationale here; link instead.<TODO: not yet wired> once; do not narrate "this could be added later".
</output_contract>team / mature: run /ad-architecture once load-bearing patterns emerge in the code./ad-prd (Layer 3 of the six-layer artifact stack; excluded from poc)./ad-spec (Layer 4 of the six-layer artifact stack; references parent PRD for product-scope inheritance).poc / solo until the project genuinely needs them — the WORKFLOW §1 prune principle applies.ad-philosophy auto-loads on non-trivial work.Compact the current session into a handoff document a fresh agent can pick up from. Saves to the OS temp dir (never the repo). Captures live state — current branch, open artifacts, unresolved decisions, in-progress diff, recent errors — references existing artifacts (PRD / spec / task / ADR) by path instead of duplicating them, and lists suggested next skills. Redacts secrets before writing. Triggers on "handoff", "hand off this session", "compact this conversation", "save context for next session", "pass to another agent", "wrap up the session", "context exhausted", "/clear", "/ad-handoff".
Survey the project's state across the six-layer artifact stack and recommend prioritized next actions, modeled on `flutter doctor`. Use when the user asks "what's next", "next step", "where am I", "project status", "doctor", "what should I do", "audit my workflow". Read-only; complements `ad-audit` (drift detection, a different question). Profile-aware — `poc` suppresses Layer 3/4/5 noise, `team`/`mature` run the full survey.
Run this skill when the user explicitly invokes `/ad-review` or names it ("run ad-review", "use the ad-review skill"), or when the user asks for a code review with an explicit scope ("review this branch", "review main..HEAD", "revisa esse diff <range>"). Auto-trigger note: `allow_implicit_invocation: true` is set so review-language can fire the skill, but this also means broad review-adjacent conversation may auto-invoke a multi-step file-writing workflow. If a request is ambiguous, ask the user to confirm scope before invoking. Mechanical shape: ONE pass in the current session. The skill assembles the diff plus the relevant context, then produces a single review with findings grouped under `## Standards Findings` and `## Spec Findings` — two axes, one session. Standards = does the diff conform to AGENTS.md / ARCHITECTURE.md / GUIDELINES.md / CONTEXT.md / accepted ADRs? Spec = does the diff match the originating task / spec / PRD? The two-axis structure exists so neither axis masks the other. No `/clear`. No
Draft a new Codex custom subagent at .codex/agents/<name>.toml, using the official Codex subagents format. Use when the user wants to create, write, draft, or scaffold a custom Codex subagent for delegated work (fresh-context reviewer, codebase explorer, docs researcher, test designer, bug reproducer, bounded implementation worker). Asks one question per missing field; never invents roles or tool sets.
Draft a new task tracking file at doc/tasks/NNNN-<short-slug>.md, using a checkbox-toggle + append-only-Notes format optimized for LLM editing. Use when the user wants to create, draft, scaffold, or open a task, ticket, work item, or backlog entry tracked in the repo. Status starts at proposed.
Compact the current session into a handoff document a fresh agent can pick up from. Saves to the OS temp dir (never the repo). Captures live state — current branch, open artifacts, unresolved decisions, in-progress diff, recent errors — references existing artifacts (PRD / spec / task / ADR) by path instead of duplicating them, and lists suggested next skills. Redacts secrets before writing. Triggers on "handoff", "hand off this session", "compact this conversation", "save context for next session", "pass to another agent", "wrap up the session", "context exhausted", "/clear", "/ad-handoff".