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 DjangoPeng/agentic-ai --skill github-secret-auditorgit clone --depth 1 https://github.com/DjangoPeng/agentic-aiWrote 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/djangopeng/agentic-ai/github-secret-auditor)<a href="https://agentmods.dev/skills/djangopeng/agentic-ai/github-secret-auditor"><img src="https://agentmods.dev/badge/skills/djangopeng/agentic-ai/github-secret-auditor/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/djangopeng/agentic-ai/github-secret-auditor"><img src="https://agentmods.dev/badge/skills/djangopeng/agentic-ai/github-secret-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.04952 |
| Opus 5.5 | $0.00028 | $0.01981 |
| Sonnet 5.5 | $0.00014 | $0.00990 |
| Haiku 4.5 | $0.00007 | $0.00495 |
Grade A, and why
github-secret-auditor 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 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.
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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub 密钥泄露巡检 Skill
目标
本 Skill 用于让 OpenClaw 通过 ACP 调度 Claude Code,对授权 GitHub 仓库执行密钥泄露巡检、安全修复、验收、推送修复 commit,并通过飞书发送巡检报告。
核心原则:
- OpenClaw 负责任务编排、ACP 调度、仓库准备、验收、commit、push 和飞书报告。
- Claude Code 负责在目标仓库内执行代码级搜索、修复和验证。
- 不允许 OpenClaw 跳过 Claude Code 手工替代巡检或修复。
- 本 Skill 的默认且唯一调度通道是 ACP。不要把 Claude Code CLI 作为本 Skill 的常规降级路径。
- Claude Code 只负责巡检、修改和本地验证;默认禁止 Claude Code 在子会话内执行
git commit、git push、创建 PR 或其他发布动作。commit 与 push 只能由 OpenClaw 在验收通过后执行。
适用场景
当用户提出以下需求时使用本 Skill:
- 巡检某个 GitHub 仓库是否存在 API Key、Token、密码、Webhook URL、私钥等泄露风险。
- 根据仓库实际泄露面自动修复,例如删除误提交凭证、改为环境变量/配置注入、替换为安全占位符或补充忽略规则。
- 只在修复确实需要时更新
.env.example、.gitignore、README 或同类配置说明文件。 - 验收通过后自动推送普通修复 commit 到授权 GitHub 仓库。
- 通过飞书发送巡检报告。
- 通过 ACP 让 OpenClaw 调度 Claude Code 完成代码级任务。
快速启动
给 OpenClaw/龙虾的一句话启动模板见 templates/run_skill_prompt.md。
用户只需提供目标 GitHub 仓库,OpenClaw 必须自动按默认任务流完成巡检、修复、验收、commit、push 和飞书报告。不要要求用户手动复制 session、手动执行 ACP 命令、手动拼接 prompt 或手动验收。
最小用户入口示例:
请使用 github-secret-auditor Skill 全自动巡检并修复 https://github.com/DjangoPeng/agentic-ai.git
OpenClaw 必须先读取本 SKILL.md,再执行默认任务流。后台自动化默认使用 OpenClaw Sessions API:
sessions_spawn(runtime="acp", agentId="claude", mode="run", thread=false, cwd=<repo_path>, prompt=<task_prompt>)
sessions_send(sessionKey=<childSessionKey>, prompt=<contextual_followup_prompt>)
飞书交互演示可使用 /acp ... slash command;后台自动化不要依赖聊天命令,也不要把 /acp ... 当 shell 命令执行。
除非任务失败或用户明确要求调试细节,最终回复只展示巡检结果、修复结果、commit、push 状态、风险摘要和风险备注;不要把 sessions_spawn、sessions_send 参数作为用户需要操作的步骤暴露出来。
用户入口与默认行为
当用户只提供 repo_url 或说“巡检这个仓库”时,OpenClaw 不要反问执行细节,直接使用以下默认值:
{
"branch": "main",
"mode": "audit_fix_push_report",
"allow_auto_fix": true,
"allow_push": true,
"runner": "acp_sessions",
"repo_path": "/srv/openclaw-runner/repos/<repo-name>"
}
只有缺少仓库授权、ACP runtime 不可用、GitHub 权限不足、工作区存在未提交修改或安全边界不明确时,才返回 failed 并说明阻塞原因。
用户面向的完成标准是看到飞书巡检报告和最终结果;OpenClaw 内部负责完整执行以下动作:
读取 Skill -> 准备仓库 -> 生成任务包 -> sessions_spawn 调度 Claude Code -> 等待输出 -> 必要时 sessions_send 补漏 -> 验收 Diff -> commit -> push -> 飞书报告
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.
- 1mo ago First seen · 391 lines · 71 tokens per session scan A 3ddf0106dee5
github-secret-auditor is a skill published in the GitHub repository DjangoPeng/agentic-ai (153 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 4,952 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
horizon
Install, configure, run, customize, schedule, and extend Horizon, the profile-driven news radar. Use for first-time Horizon installation, source selection and onboarding, generating or reading daily digests, tuning processing profiles and digest limits, setting up delivery and scheduled runs, diagnosing pipeline…
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.
update-setup
A one-time setup wizard for creating a personalised upgrade guide for a workspace. It checks for an existing guide, identifies the current version and installation clues, and requires confirmation of the installation method before writing a new guide.