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 xiaolai/eou-foundry --skill eou-diagnosegit 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-diagnose)<a href="https://agentmods.dev/skills/xiaolai/eou-foundry/eou-diagnose"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/eou-diagnose/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/xiaolai/eou-foundry/eou-diagnose"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/eou-diagnose.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 | $0.00024 | $0.00808 |
| Opus 5 | $0.00012 | $0.00404 |
| Sonnet 5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
eou-diagnose 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose EOU Failure
Diagnose the failure described in $target and recommend the minimum repair path.
Required reading
foundry/failure-taxonomy.yml— F1–F12 class definitions and repair heuristicsfoundry/constitution.yml— invariants that constrain repair optionsschemas/incident.schema.yml— validate the input incident report against this schema if it is a structured YAML file
Stop conditions
Halt and request clarification if:
$targetdoes not identify an EOU ID and one cannot be inferred from the content.- The incident report contains no observable failure symptom — only a conclusion or label.
foundry/failure-taxonomy.ymldoes not exist — failure classification cannot proceed without it.
Procedure
- Read
$target(incident report or audit finding) and extract the observable failure symptom. - For each symptom, classify it against the F1–F12 taxonomy. One symptom may match multiple classes — list all that apply, ranked by confidence.
- For each classified failure, identify the minimum repair action using this precedence (smallest blast radius first):
- schema field addition or constraint
- validator strengthening
- stop condition
- regression case
- context manifest repair
- ECP (structural EOU change)
- human approval gate
- EOU split / merge / retire
- Rule out prompt-only explanations: if the failure recurs despite correct inputs, classify as structural (F3–F12), not F1 (prompt ambiguity).
- Write the diagnosis report.
Output
Every diagnosis produces one of two outcomes:
- Change warranted — write the diagnosis report, then use
$ecp-proposeto open an ECP. - No change warranted — write a no-change record to
foundry/audits/incidents/{incident_id}.no-change.ymlwith fields:incident_id,eou_id,diagnosis_summary,decision: no_change,rationale,reviewed_by,reviewed_at,reopen_condition.
A no-change record is not a failure of the diagnosis process. It is evidence that the system reviewed and rejected a change rather than silently ignoring the incident.
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.
- 9d ago First seen · 71 lines · 24 tokens per session scan A d2fb8f1af86d
eou-diagnose is a skill published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 16d ago), licensed ISC. It adds 24 tokens to every session and 808 once invoked, about $0.0001 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.