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 RickyTong1/audit-harness --skill audit-startgit clone --depth 1 https://github.com/RickyTong1/audit-harnessWrote 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/rickytong1/audit-harness/audit-start)<a href="https://agentmods.dev/skills/rickytong1/audit-harness/audit-start"><img src="https://agentmods.dev/badge/skills/rickytong1/audit-harness/audit-start/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/rickytong1/audit-harness/audit-start"><img src="https://agentmods.dev/badge/skills/rickytong1/audit-harness/audit-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Agent Snooping · line 42 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00102 | $0.01081 |
| Opus 5 | $0.00051 | $0.00541 |
| Sonnet 5 | $0.00020 | $0.00216 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
audit-start scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > .claude/runs/${SESSION_ID}/session.json << EOF Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start — 审计会话启动 + Context 恢复
触发方式
/start "任务描述"
为什么需要 /start
每次工作都应该在审计会话中进行。没有会话意味着:
- hooks 产出的审计数据归入自动创建的
auto_session,缺少任务描述 - /end 无法做完整性检查
- 日报中的任务总览缺少描述
/start 的成本极低(创建一个目录 + 一个 JSON 文件),收益是让所有后续操作都有上下文。
执行步骤
1. 创建审计会话
# 1. 生成 session_id
SESSION_ID="adhoc_$(date +%Y%m%d_%H%M)"
# 2. 创建目录
mkdir -p .claude/runs/${SESSION_ID}
# 3. 写入 session.json
cat > .claude/runs/${SESSION_ID}/session.json << EOF
{
"session_id": "${SESSION_ID}",
"task": "用户提供的任务描述",
"start_time": "ISO 8601",
"status": "in_progress",
"expected_record_types": []
}
EOF
# 4. 写入 .current_session(Stop hook 依赖此文件确定归档目标)
echo "${SESSION_ID}" > .claude/runs/.current_session
⚠️ 第 4 步是关键:
.current_session文件是 /start 和 Stop hook 之间的握手协议。 Stop hook 读取此文件来确定 audit_buffer 归档到哪个 session 目录。 如果不写这个文件,Stop hook 会创建一个auto_session,与 /start 的 session 脱节。
2. Context 恢复(如果 .claude/runs/ 目录存在历史数据)
按以下优先级加载:
Level 0 — 索引摘要:
- 读取
.claude/runs/index.json,获取最近 5 条 entry 的 id + task + status
Level 2 — 用户修正(最重要):
- 在最近的
audit_trail.jsonl和audit_blocks.jsonl中搜索user_correction - 这些记录必须最先恢复——丢了会重犯错误
Level 1 — 任务状态:
- 读取最新的
.claude/runs/daily/*_daily.md(如果存在)- §四 异常告警:有没有未解决的问题?
- §六 昨日待办:有没有未完成的任务?
- §七 明日待办:今天该优先做什么?
- 读取最新的
.claude/runs/daily/*_morning_review.md(如果存在)
检查未完成会话:
- 扫描
.claude/runs/adhoc_*/session.json,找status: "in_progress"的会话 - 如果有,提示用户是否继续上次未完成的任务(如果继续,复用旧 session_id 而非创建新的)
3. 输出上下文恢复摘要
审计会话已创建: adhoc_20260320_1400
任务: {用户的任务描述}
上下文恢复摘要(基于 .claude/runs/ 审计记录):
最近活动:
- {最近 3 条完成的任务}
⚠️ 用户修正记录(必须遵守):
- {所有 user_correction 记录}
待解决问题:
- {未关闭的异常/告警}
今日推荐优先级:
- {morning_review 中的推荐}
预期 Record 类型:
[数据] / [变更] / [对话] — 根据任务描述预判
所有后续 [AUDIT] 块请使用 batch_id = {session_id}
4. 注意事项
- 如果
.claude/runs/目录不存在,自动创建,跳过 context 恢复 - 如果没有历史审计数据,正常启动,不报错
- session_id 在整个会话期间保持不变,所有 [AUDIT] 块共享此 id
- 如果已有活跃 session(
.current_session文件存在且对应 session 状态为 in_progress),提示用户是否要结束旧 session 再创建新的
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 · 114 lines · 102 tokens per session scan A fab96114ea1f
audit-start is a skill published in the GitHub repository RickyTong1/audit-harness (472 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 1,081 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…