{{project_slug}}-audit

{{project_slug}}-audit is a skill for Claude Code from big-emotion/agent-atelier. It costs 0 tokens per session (2,759 once invoked), scanned C, original, MIT.

A read-only production-readiness audit that checks a repository and its available quality gates, then writes a scored report. Production readiness means whether a project is prepared to run reliably for users, including its domain-specific health and security posture.

In plain words
What is it for?
It is for assessing release readiness, security posture, test and build evidence, and the project's overall score.
Why use it?
It provides evidence about whether a project is ready to ship without changing source code, versions, tags, deployments, or external services. A quick mode uses recent results when running every check would be slow or costly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the project-standard plugin — 6 skills shipped together

Good fit It is for assessing release readiness, security posture, test and build evidence, and the project's overall score.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/big-emotion/agent-atelier/audit
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.

Any agent
npx skills add big-emotion/agent-atelier --skill audit
Clone the repo
git clone --depth 1 https://github.com/big-emotion/agent-atelier

Made for: Claude Code.

Or install project-standard, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for {{project_slug}}-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/big-emotion/agent-atelier/audit/github.svg)](https://agentmods.dev/skills/big-emotion/agent-atelier/audit)
Your own site
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/audit"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for {{project_slug}}-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/audit"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,759 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02759
Opus 5.5 $0.00000 $0.01104
Sonnet 5.5 $0.00000 $0.00552
Haiku 4.5 $0.00000 $0.00276

Measured 1mo ago against content hash 63ad029e4ae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

{{project_slug}}-audit scanned grade C with 1 finding 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 1mo 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- PROJECT-SPECIFIC: append the project-type domains that make this audit meaningful — typically 2 to 4 more rows. Examples from reference repos: a public website added "RGPD / privacy", "RGAA / accessibility", "Perfor
plugins/project-standard/skills/setup/templates/m3-skills/audit.SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{{project_display_name}} Audit

Read-only audit of the project defined in this repo. Produces a scored, evidence-based report and refreshes docs/PRODUCTION-READINESS-AUDIT.md.

This skill never modifies source, never bumps versions, never tags, never pushes, never deploys, never writes to external services. It only reads, runs the repo's own gates, and writes the audit doc. Fixing anything it finds is deferred to normal ticketed work or /{{project_slug}}-release.

When to Activate

  • User asks: "is the project production-ready", "is it ready to ship", "audit {{project_slug}}", "score the project".
  • User asks specifically about security posture, compliance, or overall score.
  • User invokes /{{project_slug}}-audit.

Preconditions

Run from the repo root (package.json with "name": "{{project_slug}}"). If not, stop and tell the user to cd into the repo.

Inputs

Optional argument: --quick — skip the long/costly gates (full test suite, production build, any gate that hits a paid external API). Rely instead on the most recent CI run (gh run list --workflow ci.yml) and the newest local artifacts, and mark any domain scored from stale data as such.

Default: full audit.

Workflow

Step 1 — Snapshot the repo state

Run in parallel via Bash:

  • git status --porcelain — a dirty tree is auditable but must be reported.
  • git log --oneline -15 — recent cadence.
  • git tag --sort=-creatordate | head -5 — no tags yet is expected pre-launch; say so explicitly.
  • jq '{name, version, private, packageManager, scripts}' package.json — version, scripts, package manager.
  • ls .github/workflows/ — workflow surface.
  • ls docs/ — structural map.

Read the full file on GitHub · 170 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.

  1. 1mo ago First seen · 170 lines · 0 tokens per session scan C 63ad029e4ae8

Subscribe to this mod's changes

{{project_slug}}-audit is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,759 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.