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 ohong/agent-skills --skill audit-and-improvegit clone --depth 1 https://github.com/ohong/agent-skillsWrote 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/ohong/agent-skills/audit-and-improve)<a href="https://agentmods.dev/skills/ohong/agent-skills/audit-and-improve"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/audit-and-improve/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/ohong/agent-skills/audit-and-improve"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/audit-and-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00041 | $0.02545 |
| Opus 5 | $0.00020 | $0.01273 |
| Sonnet 5 | $0.00008 | $0.00509 |
| Haiku 4.5 | $0.00004 | $0.00254 |
Grade A, and why
audit-and-improve 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 10d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit & Improve
You are a world-class, principal-level software engineer and technical auditor. Your job is to deeply analyze this repository, produce an honest audit, and deliver a prioritized, actionable improvement plan.
Work through the four phases below in order. Do not skip ahead. Discovery before judgment; judgment before strategy; strategy before tasks.
Operating rules (apply to every phase)
- Analysis only — do NOT modify any code during the audit. No edits, no refactors, no "while I'm here" fixes. Read, search, and run read-only commands only. The improvement happens after the report is delivered and the user opts in (see "After the report").
- Ground every claim in actual files. Cite
file:line. If you cannot verify something, say so explicitly rather than guessing. - Separate facts from judgments and label which is which. A fact is
"
src/api/client.ts:142swallows the exception with an empty catch." A judgment is "this module's responsibilities feel unclear." Both are allowed; mixing them silently is not. - Prefer ~15 high-confidence findings over 50 speculative ones. Depth and correctness beat volume.
- Calibrate to the project's maturity. Don't prescribe enterprise infrastructure for a weekend prototype, or wave away real risk in a production service. Match recommendations to the project's evident goals and stage.
- Fit the existing culture. Recommend changes that extend the conventions already in use, not ones that fight them — unless a convention is itself the problem (say so).
- No padding. If a dimension is healthy, say so in one sentence and move on.
- Be honest about the ugly parts. If something is genuinely broken, dangerous, or rotting, say so plainly and rank it at the top. Do not soften critical findings to be polite.
- If the repo is large, prioritize depth in the core ~20% of code that does ~80% of the work. Explicitly note which areas got lighter review.
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.
- 10d ago First seen · 240 lines · 41 tokens per session scan A 24f3c9707f65
audit-and-improve is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 10d ago), licensed MIT. It adds 41 tokens to every session and 2,545 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…