A short codebase review that maps the project's structure and checks its general health. A codebase is the collection of files that make up a software project.

Use it when joining a project, preparing for a review, or checking a specific folder quickly. A later resume can continue with deeper checks such as security, performance, code quality, and planning.

It gives someone new to a project a quick understanding of where things are and whether the project has obvious organizational or maintenance problems. It avoids the time required for a full review.

audit-quick — Command by telus-labs

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/telus-labs/stagecraft/audit-quick

Clone the repo

git clone --depth 1 https://github.com/telus-labs/stagecraft

Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 724 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00067	$0.00724
Opus 5	$0.00034	$0.00362
Sonnet 5	$0.00013	$0.00145
Haiku 4.5	$0.00007	$0.00072

Measured 3d ago against content hash 7c123e6edbf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-quick scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hosts/claude-code/install/commands/audit-quick.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-quick

You are running a quick audit — Phases 0 and 1 only.

Read .claude/skills/audit/SKILL.md before doing anything else. That file defines what each phase does and what to produce.

Input

The text after /audit-quick is an optional scope constraint. If provided (e.g. /audit-quick src/backend/), focus on that area only.

Startup

Read .claude/skills/audit/SKILL.md.
Read CLAUDE.md if it exists.
Read AGENTS.md if it exists.
Create docs/audit/ if it doesn't exist.
Check for docs/audit-extensions.md.
Run skill step 0.0 — archive any prior completed audit. Move docs/audit/* to docs/audit-archive/<date>-<version>-<context>/ if status.json reports current_phase: "phase-3". Skip on --resume. Procedure: skills/audit/SKILL.md § Phase 0 step 0.0.

Execution

Run Phase 0 (steps 0.0, 0.1, 0.2, 0.3) and Phase 1 (steps 1.1, 1.2, 1.3) from the skill. Write all six output files. Run extensions for Phases 0 and 1 if any are declared.

Write docs/audit/status.json with phases 0 and 1 complete, phases 2 and 3 pending:

{
  "started": "<ISO 8601>",
  "scope": "full" | "scoped to <subtree>",
  "phases": {
    "phase-0": "complete",
    "phase-1": "complete",
    "phase-2": "pending",
    "phase-3": "pending"
  },
  "current_phase": "phase-1",
  "audited_by": "claude-code"
}

End

Print summary:

Quick Audit Complete
═══════════════════════════════════════════════════
Phase                    Status     Files
─────────────────────────────────────────────────
0  Bootstrap             ✅         00, 01, 02
1  Health Assessment     ✅         03, 04, 05
2  Deep Analysis         ⏭️  Skipped
3  Roadmap               ⏭️  Skipped
─────────────────────────────────────────────────

Project: <language / framework>, <N modules/services>
Convention issues: <N findings>
Test health: <brief summary>
Doc gaps: <brief summary>

To continue with deep analysis and roadmap: /audit --resume

What this command does NOT do

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 78 lines · 67 tokens per session scan A 7c123e6edbf0

Subscribe to this mod's changes

audit-quick is a command published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 724 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review agent-framework ai-coding claude-code codex dev-pipeline gemini-cli

audit-quick

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/audit-quick

Input

Startup

Execution

End

What this command does NOT do

What this file has done since we first saw it

Other commands, from other repositories

dev

analyze-repo

dispatcher

test

claude-request

doctor