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-initgit 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-init)<a href="https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry-init"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-init/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-init"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-init.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 | $0.00037 | $0.01081 |
| Opus 5 | $0.00018 | $0.00541 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
engifoundry-init 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EngiFoundry Init
Own first initialization and every later request whose intent is to modify EngiFoundry configuration. A modification request always restarts the same complete four-question flow; do not ask which field the user wants to change. Existing configuration remains active until the final answer commits its replacement.
For an explicit migration or upgrade request, read migration.md. Migration is Agent-directed: preserve legacy content, rebuild control JSON from inspected project facts, and use the full Init interaction only when reliable preference recovery is not possible.
Start
Resolve the project root from the working directory without scanning for EngiFoundry files. Identify the current host CLI by its canonical command ID, such as codex, claude, gemini, kimi, or cursor-agent.
For first initialization, run scaffold init, then start Configurator status. The scaffold adopts an existing unconfigured-direct fallback tree only when it contains no files outside .engifoundry/packages/ and .engifoundry/artifacts/verification/; it preserves those sparse PAK and Verify records unchanged while adding the complete scaffold. Any other existing root configuration or data tree is a path collision. On a collision or scaffold failure, report the exact paths and stop. For configuration modification, do not run the scaffold; invoke Configurator status once with --init-modify or -InitModify. That flag unconditionally clears only .engifoundry/cache/configurator/ and starts a new modify flow.
Relay Protocol
Configurator JSON is the question and state authority. Do not reconstruct, localize, supplement, skip, reorder, or answer its questions.
From the first Configurator invocation until complete or cancelled, emit no model-authored conversational text. In particular, never expose planning, reasoning, intention, progress, transition, tool, or command narration such as “I should…”, “I will…”, “I’m…”, “正在……”, “接下来……”, or “已完成……”. Run every script action and custom-resolution probe silently. User-visible output is limited to the script-returned fields allowed below; this restriction applies equally to initialization and --init-modify.
What ships with it
20 files 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.
- references/migration.md 5.3 KB
- references/probing.md 8.7 KB
- references/templates/engifoundry.config.json 324 B
- references/templates/executors.json 304 B
- references/templates/executors.schema.json 6.3 KB
- references/templates/initialization.json 105 B
- references/templates/workflows.json 102 B
- references/workspace.md 2.8 KB
- scripts/configure.ps1 34 KB runs code
- scripts/configure.sh 40 KB runs code
- scripts/executor-probe.ps1 2.5 KB runs code
- scripts/executor-probe.sh 3.0 KB runs code
- scripts/init.ps1 9.6 KB runs code
- scripts/init.sh 6.9 KB runs code
- scripts/probe-cache.ps1 5.4 KB runs code
- scripts/probe-cache.sh 5.9 KB runs code
- scripts/selection-catalog.ps1 5.6 KB runs code
- scripts/selection-catalog.sh 5.9 KB runs code
- scripts/verify.ps1 2.6 KB runs code
- scripts/verify.sh 2.8 KB runs code
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 · 51 lines · 37 tokens per session scan A 7be1d262432c
engifoundry-init 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 37 tokens to every session and 1,081 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
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.