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 caoyuan-fire/engi-foundry-skill --skill engifoundry-auditgit clone --depth 1 https://github.com/caoyuan-fire/engi-foundry-skillWrote 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/caoyuan-fire/engi-foundry-skill/engifoundry-audit)<a href="https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry-audit"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-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/caoyuan-fire/engi-foundry-skill/engifoundry-audit"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-audit.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 | $0.00052 | $0.00995 |
| Opus 5 | $0.00026 | $0.00498 |
| Sonnet 5 | $0.00010 | $0.00199 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
engifoundry-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 12d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EngiFoundry Audit
Use this classification only after complete Initialization. Read the configured Workflow file and inspect only the new task facts needed for classification. Unconfigured fallback uses the equivalent Router boundary without project preferences or heavyweight execution authority.
Boundary
The Agent applies these rules only to classify new work as inline, direct, package, or blocked. Classification does not execute, plan, split Jobs, edit files, ask for approval, or write durable records. Continue work already bound to a PAK or Job under that identity instead of allocating another one.
Keep only concise observed facts sufficient to support the classification. Do not introduce recommendations or proposed implementation.
Project Relevance
Current-project relevance is the applicability boundary for every classification in this contract. A request is relevant when the user's intent materially concerns the current project, its contents, interfaces, engineering operations, or delivery, or continues work already bound to one of its PAKs or Jobs. The current working directory, an available EngiFoundry configuration, use of engineering tools, and task complexity, risk, or duration do not establish relevance by themselves.
A request that targets another project or has no material relationship to the current project is outside this classification domain. inline, direct, package, and blocked are all inapplicable, and no current-project PAK or other EngiFoundry record is justified. An explicit user request to manage that work through the current project's EngiFoundry runtime overrides this boundary.
Project relevance has precedence over persistence value, execution topology, and configured preferences. Router treats out-of-domain work as an ordinary request rather than as an Audit classification or runtime state.
Decision
Prefer the lightest path that preserves sufficient control. First decide whether a PAK has material persistence value, then whether heavyweight orchestration has material execution value. Risk strengthens safeguards and evidence on the selected path; it changes topology only when those controls require an independent responsibility, acceptance, delegation, or handoff boundary.
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.
- 12d ago First seen · 45 lines · 52 tokens per session scan A 81f1fe2d2f40
engifoundry-audit is a skill published in the GitHub repository caoyuan-fire/engi-foundry-skill (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 52 tokens to every session and 995 once invoked, about $0.0003 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
julilaoshi-design
Public-safe julilaoshi-design workflow for official Pencil MCP execution and the free browser-first julilaoshi-design Web 2.0 editor. Use when a task needs Pencil handshake/canvas edits, .pen execution, screenshot review, or lightweight HTML design-to-web tweaking without redistributing official Pencil or leaking…
x-insight-cards
Run scheduled or manual creator curation that turns recent high-quality X posts into verified image-and-caption packs for Douyin and Xiaohongshu review, with optional private delivery to a pinned WeChat iLink bot review chat or confirmed File Transfer Assistant self-chat. Use when Codex needs to discover, verify…
zhuoyu-workshop
Student project delivery and packaging workflow for Codex. Use when the user needs help with Chinese university student projects, course projects, innovation training projects, competitions, capstones, graduation projects, project defense decks, closing reports, README/GitHub showcase materials, software copyright…
project-engineering-strategy
Use when a software project needs durable cross-session governance for formal documents, WBS or tracker coordination, worktree delivery boundaries, evidence and acceptance states, handoffs, or architecture and design-document control.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
xiaohongshu-conversion-path
A Xiaohongshu conversion-path guide maps how people move from seeing content on Xiaohongshu, a Chinese social-content platform, to taking a next step such as messaging, booking, trying a tool, or buying.