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 agentmods add skills/xiaolai/eou-foundry/eou-validatenpx skills add xiaolai/eou-foundry --skill eou-validategit clone --depth 1 https://github.com/xiaolai/eou-foundryWrote 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/xiaolai/eou-foundry/eou-validate)<a href="https://agentmods.dev/skills/xiaolai/eou-foundry/eou-validate"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/eou-validate.svg" alt="Measured on agentmods" 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 | $0.00205 | $0.01204 |
| Opus 5 | $0.00102 | $0.00602 |
| Sonnet 5 | $0.00041 | $0.00241 |
| Haiku 4.5 | $0.00020 | $0.00120 |
Grade A, and why
eou-validate 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Foundry
Validate the structural integrity of the EOU Foundry at foundry/.
Required reading (load in order)
schemas/eou.schema.yml— the authoritative EOU spec schemaschemas/ecp.schema.yml— the authoritative ECP schemafoundry/constitution.ymlfoundry/registry.yml
Stop conditions
Stop and record a critical finding if:
- Any schema file in
schemas/*.schema.ymlis absent — validation cannot proceed without schemas. foundry/directory does not exist in the working directory.
Validation checks
Run each check in order. Record every violation — do not stop at first failure.
1. Schema presence
Verify all schema files in schemas/*.schema.yml exist. If any are absent, record a "schema file absent" critical finding and stop (cannot validate specs without schemas).
2. EOU spec completeness
For each spec in foundry/eous/ and foundry/meta-eous/:
- Every field listed in
schemas/eou.schema.ymlrequired_top_levelmust be present. classificationmust include all six facets:function,target_object,automation_mode,authority_level,risk_level,lifecycle_stage.- All enum values must match schema allowed values (see
valid_*lists inschemas/eou.schema.yml). - No placeholder strings: reject "target artifact", "What this EOU is meant to do", "Perform bounded operation".
3. Registry consistency
- Every spec with
lifecycle_stage: activeorpilotmust have a registry entry infoundry/registry.yml. - Every registry entry must have a matching spec file in
foundry/eous/orfoundry/meta-eous/. - Flag orphan specs (no registry entry at active/pilot) and unregistered active EOUs.
4. Recursive governance constraints
- For each spec:
responsibility.executormust not equalresponsibility.approver(self-approval violation). - For each spec with
function: generate:generation_envelope.forbidden_outputsmust includeactive_eou,approved_eou, andconstitution_change.
5. Generation safety
For each spec with function: generate:
generation_envelope.allowed_outputsmust not includeactive_eou,approved_eou, or any variant ofconstitution_change.generation_envelope.default_statusmust becandidate.
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.
- 5d ago First seen · 111 lines · 205 tokens per session scan A 16c6755d55b5
eou-validate is a skill published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 12d ago), licensed ISC. It adds 205 tokens to every session and 1,204 once invoked, about $0.0010 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…