What is eou-foundry AGENTS.md?

Repository instructions for eou-foundry, including prerequisites, validation commands, project rules, and the approved vocabulary for its schemas and automation files.

Use them when changing schemas, validation code, skills, rules, metadata, or the local setup required to run the project’s checks.

They help keep schema values and related documentation consistent across validators, skills, rules, and metadata.

How xiaolai/eou-foundry configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to xiaolai/eou-foundry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xiaolai/eou-foundry/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/xiaolai/eou-foundry

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xiaolai/eou-foundry/agents-md/github.svg)](https://agentmods.dev/instructions/xiaolai/eou-foundry/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xiaolai/eou-foundry/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/eou-foundry/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xiaolai/eou-foundry/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/eou-foundry/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,776 This file is loaded in full into every session.

When invoked 1,776 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01776	$0.01776
Opus 5.5	$0.00710	$0.00710
Sonnet 5.5	$0.00355	$0.00355
Haiku 4.5	$0.00178	$0.00178

Measured 1mo ago against content hash 017c1b9e2ad6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eou-foundry AGENTS.md 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.

AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions

eou-foundry

Prerequisites

Python 3.9+ — required by scripts/validate_foundry.py and the helper modules under scripts/.
PyYAML (pip install pyyaml) — the validator reads/writes YAML.
No other runtime dependencies for validation. CI may additionally need gh for ECP submission flows; local development does not.
EOU_FOUNDRY_PLUGIN_PATH environment variable should point at the plugin checkout when running validate_foundry.py outside an installed-plugin context (the validator falls back to installed_plugins.json and then to its own parent directory).

Guidelines

Vocabulary authority chain

schemas/ is the ground truth for all enum values. When vocabulary changes:

Update the schema file (schemas/eou.schema.yml or schemas/ecp.schema.yml)
Update scripts/validate_foundry.py (VALID_FUNCTIONS, VALID_AUTOMATION, VALID_AUTHORITY, VALID_RISK, VALID_STAGE)
Update every skill in skills/ that references the changed enum
Update every matching codex skill in codex/skills/
Update every rule in rules/ that documents the enum
Update any meta-EOU in engine/meta-eous/ that uses the value

Never update vocabulary in only one place — all six layers must stay in sync.

Testing changes

After editing any script, run the validator against the fixture foundry:

python3 scripts/validate_foundry.py tests/fixture-foundry

After editing any SKILL.md, verify the output path it declares matches the path the consuming skill (eou-promote, eou-diagnose, eou-refactor, foundry-audit, audit-candidate-eou-set) reads from.

Skill selection guide

Goal	Use
Synthesize Stage 0 inputs from references (literacy bridge + per-app constitutional layer)	`$generate-captured-workflow-from-references`
Convert workflow → candidate EOUs	`$generate-eou-candidates` (consults `captured_workflow` when present per Rule 96)
Audit a candidate set for readiness	`$audit-candidate-eou-set` (runs Set Value Coverage Test when `captured_workflow` present)
Convert approved candidate → spec	`$eou-specify`
Audit a spec for V2 compliance	`$eou-audit` (runs Value Operationalization Test when `captured_workflow` present per Rule 96)
Audit agentic-judgment invocations (F14–F17 + counterfactual-swap)	`$audit-judgment` (fourth audit layer per D4.1; enforces Rule 97 on EOUs with `judgment_authorized:true`)
Audit the whole foundry	`$foundry-audit`
Validate schemas and registry	`$eou-validate`
Diagnose a failure	`$eou-diagnose`
Generate refactor options	`$eou-refactor`
Propose a structural change	`$ecp-propose`
Promote or retire a spec	`$eou-promote`
Convert incidents → regression cases	`$generate-regression-cases`
Scaffold a new app	`$eou-foundry-init` (Codex-only)

Read the full file on GitHub · 114 lines

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.

1mo ago Changed · +39 tokens per session 017c1b9e2ad6
2mo ago First seen · 114 lines · 1,737 tokens per session scan A a6cf9edd34be

Subscribe to this mod's changes

eou-foundry AGENTS.md is an instructions file published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 1mo ago), licensed ISC. It adds 1,776 tokens to every session, about $0.0071 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 2026-08-31.

eou-foundry AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
eou-foundry AGENTS.mdxiaolai/eou-foundry	Instructions file	10	1mo ago	ISC	A	1,776	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

eou-foundry: Instructions file for Codex