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 shinpr/rashomon --skill recipe-eval-skillgit clone --depth 1 https://github.com/shinpr/rashomonWrote 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/shinpr/rashomon/recipe-eval-skill)<a href="https://agentmods.dev/skills/shinpr/rashomon/recipe-eval-skill"><img src="https://agentmods.dev/badge/skills/shinpr/rashomon/recipe-eval-skill/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/shinpr/rashomon/recipe-eval-skill"><img src="https://agentmods.dev/badge/skills/shinpr/rashomon/recipe-eval-skill.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 | $0.00039 | $0.01146 |
| Opus 5 | $0.00019 | $0.00573 |
| Sonnet 5 | $0.00008 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
recipe-eval-skill 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 6d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explicit User Instruction: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.
Context: Skill authoring (Phase A) followed by blind A/B evaluation (Phase B)
Mode: $ARGUMENTS
Orchestrator Definition
Core Identity: "I am not a worker. I am an orchestrator."
Execution Method:
- Skill generation/modification → performed by rashomon:skill-creator
- Skill quality grading → performed by rashomon:skill-reviewer
- Test task execution → performed by eval-executor.py script (via
claude -p) - Blind result comparison → performed by rashomon:skill-eval-reporter
Orchestrator invokes sub-agents via Agent tool and scripts via Bash, passes structured data between them.
Mode Detection
Determine mode from $ARGUMENTS:
| Mode | Criteria |
|---|---|
| Creation | "create", new skill request, no existing skill referenced |
| Update | "improve", "update", existing skill name or path mentioned |
| Unspecified | $ARGUMENTS is empty or ambiguous |
Scope Boundaries
Phase A (Skill Authoring): Create or modify skill content through dialog. Ends with user-approved skill file. Phase B (Evaluation): Measure skill effectiveness through blind execution comparison. Phase B is read-only for the source skill. A finding that requires authoring changes transitions back to Phase A for user review and approval before evaluation restarts.
Responsibility Boundary: This skill completes with the combined evaluation report and ship/revise/reject recommendation.
Workflow
Phase A: Skill Authoring
Read the mode-specific reference and execute:
- Creation mode: Read references/create.md and follow its steps
- Update mode: Read references/update.md and follow its steps
Phase A ends with: user-approved skill content (new or modified).
What ships with it
4 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.
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.
- 6d ago Changed a539ae93d851
- 10d ago First seen · 116 lines · 39 tokens per session scan A 0a3e72fecb8d
recipe-eval-skill is a skill published in the GitHub repository shinpr/rashomon (18 stars, last pushed 10d ago), licensed MIT. It adds 39 tokens to every session and 1,146 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 2026-08-30.
Other skills, from other repositories
interview-me
Deep-dive spec interviewer. Reads a file, GitHub issue, or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce a comprehensive, opinionated specification document. Acts as a collaborative architect with active pushback. Also runs --verify to detect…
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
flow-lean
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
lfe-inspector
Act as the Inspector for an LFE-compliant project. Use when verifying an implementation against domain truth, validation baselines, or debugging regressions.
lfe-session
Bootstrap a focused improvement session on the LFE framework itself. Use at the start of any session where the goal is to improve, extend, or fix the Library-First Engineering repo — not to use the pipeline on product code. Reads GitHub Issues, git history, and runs structural integrity tests to surface drift…
lfe-plan-critique
Run a 5-lens pre-build critique of the approved active plan before the Builder starts. Acts as the Architect persona, read-only on src/. Writes .plans/plancritique.md. Use immediately after Brain approves activeplan.md.