engifoundry

engifoundry is a skill for Claude Code, Codex from caoyuan-fire/engi-foundry-skill. It costs 65 tokens per session (493 once invoked), scanned A, original, Apache-2.0.

A project-startup skill that checks for an EngiFoundry configuration file and selects the matching instructions when that file exists. EngiFoundry is a set of project-specific engineering rules and workflows.

In plain words
What is it for?
It is for initializing, routing, or carrying out engineering work under an EngiFoundry project setup.
Why use it?
It prevents the agent from applying project-specific rules when the project has not opted into them, while loading them automatically when configured.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the engifoundry-bundle plugin — 10 skills, 1 hook, 1 MCP server shipped together

Good fit It is for initializing, routing, or carrying out engineering work under an EngiFoundry project setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caoyuan-fire/engi-foundry-skill/engifoundry
Install

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.

Any agent
npx skills add caoyuan-fire/engi-foundry-skill --skill engifoundry
Clone the repo
git clone --depth 1 https://github.com/caoyuan-fire/engi-foundry-skill

Made for: Claude Code, Codex.

Or install engifoundry-bundle, the plugin that ships this one along with the rest of its 10 skills, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for engifoundry

README.md
[![agentmods](https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry/github.svg)](https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry)
Your own site
<a href="https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry/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.

agentmods 80×15 button for engifoundry

Your own site · 80×15
<a href="https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00493
Opus 5 $0.00032 $0.00246
Sonnet 5 $0.00013 $0.00099
Haiku 4.5 $0.00006 $0.00049

Measured 10d ago against content hash 4589457d4fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

engifoundry 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.

skills/engifoundry/SKILL.md · 25 lines

What it actually says

EngiFoundry Entry

Inject this entry once at the start of every session. Apply its rules to every user turn.

  1. At session start, check exactly <project-root>/engifoundry.config.json once. Do not search for it.
  2. If it exists, read engifoundry-router/SKILL.md in full before responding to the user.
  3. If it does not exist, remain uninitialized and inspect only whether the request explicitly contains $engifoundry, engifoundry, engi, or foundry as a case-insensitive identifier.
  4. For an explicit request to initialize, scaffold, onboard, connect, migrate, or upgrade a project for EngiFoundry, load engifoundry-init/SKILL.md.
  5. For an explicit request to use EngiFoundry for actionable engineering work without initialization intent, load engifoundry-router/SKILL.md in unconfigured fallback mode. Initialization may be suggested as an optional way to enable project preferences and heavyweight contracts, but it is never a prerequisite for this work.
  6. Otherwise bypass EngiFoundry silently and handle the request normally. Merely discussing or asking about EngiFoundry is not actionable engineering work.
  7. After Init completes, check exactly <project-root>/engifoundry.config.json once again. If it now exists, immediately read engifoundry-router/SKILL.md in full. Do not require a new session.

Reading only Router metadata or a summary is forbidden. The Router governs every user turn after it is loaded.

Initialization and actionable-work matching are semantic, not fixed commands. Initialization language without an explicit EngiFoundry identifier must never activate EngiFoundry.

Never scan for configuration. Never recognize any other filename, location, or project signal. Do not validate configuration content or project records; Init and Node skills own those rules.

Do nothing else. Never route, infer, govern, plan, execute, verify, deliver, or load Node skills from this entry.

Files

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.

Changes

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.

  1. 10d ago First seen · 25 lines · 65 tokens per session scan A 4589457d4fa0

Subscribe to this mod's changes

engifoundry is a skill published in the GitHub repository caoyuan-fire/engi-foundry-skill (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 65 tokens to every session and 493 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.

Related

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…

julilaoshi/julilaoshi-design · 68 tokens

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…

ljunnan24-hash/x-insight-cards · 121 tokens

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…

handsomeZR-netizen/zhuoyu-workshop-skill · 81 tokens

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.

wgwtest/project-engineering-strategy · 46 tokens

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…

leo-lilinxiao/codex-autoresearch · 80 tokens

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.

mengke-wang/xiaohongshu-ai-workbench · 168 tokens