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 generate-captured-workflow-from-referencesgit 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/generate-captured-workflow-from-references)<a href="https://agentmods.dev/skills/xiaolai/eou-foundry/generate-captured-workflow-from-references"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/generate-captured-workflow-from-references/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/generate-captured-workflow-from-references"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/generate-captured-workflow-from-references.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 | $0.00085 | $0.02251 |
| Opus 5 | $0.00043 | $0.01125 |
| Sonnet 5 | $0.00017 | $0.00450 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
generate-captured-workflow-from-references 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Captured Workflow from References
Synthesize a Stage 0 captured_workflow for $app from a structured reference set and constraints.
What this skill does
One sentence — synthesize the inputs that D2.4 step 6 ($generate-eou-candidates) needs, plus the per-app constitutional domain_values layer, from a user goal + 5-role reference set + constraints + explicit user contributions.
Inputs required
$app(required) — the app or domain identifier; used in the output filenamecw-{slug}.yml.user_goal(required) — outcome category in plain language ("I want to make X").reference_set(required) — mapping with all 5 role slots filled, each with{ref, why}entries:aspirational— what the user wants to makeanti_reference— similar surface, wrong soulboundary_case— edge of the fieldmainstream_baseline— the median of the fieldoutlier— "I dislike this but it succeeds" (mandatory V1 defense against blind-spot encoding)
constraints(required) — audience, scale, budget, time, risk_tolerance, desired_effect.negative_constraints(required) — what the user rejects explicitly.user_contributed_references(required) — ≥1 reference per role slot that the AI did not propose (V2 anti-abdication enforcement).starter_pack(optional) —engine/starter-packs/{domain}.ymlif present and the user opts in.
Inputs forbidden
- Pre-existing workflow prose — that input belongs to
$generate-eou-candidates, not this skill. If the user can already articulate a workflow, this skill returns theoperational_value_testreject decision and recommends$generate-eou-candidatesdirectly.
Required reading
schemas/captured-workflow.schema.ymldev-docs/06-values-over-rules.mddev-docs/08-stage-0-design.mdengine/meta-eous/generate-captured-workflow-from-references.yml
Stop conditions
Halt and report if any of the following hold:
- Any role slot is empty after best-effort elicitation.
user_contributed_referencesis empty for any slot (V2 violation).- Fewer than 3 surviving
domain_valuesafter inclusion-test filtering. - More than 8 surviving
domain_values(cap mirrors foundry V1–V8 sizing). - Counterfactual swap audit reveals fewer than 3 flips out of 5 tests (the value layer is decoration).
- User can articulate a workflow unaided (skill is the wrong tool; use
$generate-eou-candidatesdirectly). - The app is governance scaffolding only with no real craft domain.
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 · 140 lines · 85 tokens per session scan A 1f1aa25f79f8
generate-captured-workflow-from-references is a skill published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 16d ago), licensed ISC. It adds 85 tokens to every session and 2,251 once invoked, about $0.0004 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…