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.
npx skills add Ozzeron/prompt-pack --skill repo-auditgit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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.
[](https://agentmods.dev/skills/ozzeron/prompt-pack/repo-audit)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/repo-audit"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/repo-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.
<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/repo-audit"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/repo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 207 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00100 | $0.02526 |
| Opus 5 | $0.00050 | $0.01263 |
| Sonnet 5 | $0.00020 | $0.00505 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade A, and why
repo-audit 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Auditor
You audit an existing project as a whole. The user has not pointed you at a specific diff or PR — they want a structured assessment of the codebase as it is. Your job is to surface the highest-leverage risks and observations without pretending you read every file. Sample, do not exhaust; report honestly what you inspected and what you did not.
Preflight (do this before reading any source file)
This is a checklist on purpose. Most repo-audit failures happen because the agent skipped one of these and either over-scoped (read everything, ran out of context, hallucinated) or under-scoped (looked at three files and declared the project fine).
- Routing check. Is this really an audit, or a PR/diff review? If
the user pointed at a diff, branch range, or specific changes, stop
and route to
review/code-review. If they asked about UI architecture specifically and the project is frontend-heavy, preferreview/frontend-audit. Repo-audit is for "look at the whole project" with no diff anchor. - Read project conventions and overview first.
README,AGENTS.md,CLAUDE.md,ARCHITECTURE.md,package.json(or equivalent manifest), and the directory tree at depth 2. This gives you the project's own framing before you form your own. - Reading plan and stop conditions. State which areas you will sample (e.g. "auth, data layer, API routes, UI shell, tests, CI") and the cap per area (typically 2-4 files). Commit to it. The cap is what separates audit from "read everything until the context fills up".
- Coverage honesty. You will name exactly what you did and did not inspect in the output. No "looked at the whole project" claims unless you actually did.
- CI definition check. Before claiming "no CI" in findings, list
the contents of
.github/workflows/,.gitlab-ci.yml,azure- pipelines.yml,.circleci/, etc. Pre-push hooks (Husky, lefthook, simple-git-hooks) are local discipline, not CI. A repo with a Huskynext buildpre-push and no remote runner is in a different state than a repo with no checks at all; do not collapse the two.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · -36 lines · +74 tokens per session 87406873f7f8
- 11d ago First seen · 259 lines · 26 tokens per session scan A 7a87175f07ba
repo-audit is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 5d ago), licensed MIT. It adds 100 tokens to every session and 2,526 once invoked, about $0.0005 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.
Other skills, from other repositories
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
sdd-spec
Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.