recipe-eval-skill

recipe-eval-skill is a skill for Claude Code from shinpr/rashomon. It costs 39 tokens per session (1,146 once invoked), scanned A, original, MIT.

A workflow for creating or updating Claude Code skills, which are instruction sets for coding agents, and then testing their effectiveness. It compares results from different skill versions using repeated blind tests.

In plain words
What is it for?
Use it to create or improve a skill, run quality checks, execute test tasks, and compare the original with the revised version.
Why use it?
It separates skill writing from skill review and shows whether changes improve results on practical tasks.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Part of the rashomon plugin — 5 skills, 7 agents shipped together

Good fit Use it to create or improve a skill, run quality checks, execute test tasks, and compare the original with the revised version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shinpr/rashomon/recipe-eval-skill
Install

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.

Any agent
npx skills add shinpr/rashomon --skill recipe-eval-skill
Clone the repo
git clone --depth 1 https://github.com/shinpr/rashomon

Made for: Claude Code.

Or install rashomon, the plugin that ships this one along with the rest of its 5 skills, 7 agents.

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.

agentmods badge for recipe-eval-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/shinpr/rashomon/recipe-eval-skill/github.svg)](https://agentmods.dev/skills/shinpr/rashomon/recipe-eval-skill)
Your own site
<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.

agentmods 80×15 button for recipe-eval-skill

Your own site · 80×15
<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>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,146 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce 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

Measured 6d ago against content hash a539ae93d851, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/eval-executor.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/recipe-eval-skill/SKILL.md · 116 lines

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:

Phase A ends with: user-approved skill content (new or modified).

Read the full file on GitHub · 116 lines

Files

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.

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.

  1. 6d ago Changed a539ae93d851
  2. 10d ago First seen · 116 lines · 39 tokens per session scan A 0a3e72fecb8d

Subscribe to this mod's changes

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.

Related

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…

Sorbh/interview-me · 79 tokens

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.

rasros/lx · 48 tokens

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.

FlorianBruniaux/flow-lean · 41 tokens

lfe-inspector

Act as the Inspector for an LFE-compliant project. Use when verifying an implementation against domain truth, validation baselines, or debugging regressions.

StChiotis/Library-First-Engineering · 35 tokens

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…

StChiotis/Library-First-Engineering · 69 tokens

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.

StChiotis/Library-First-Engineering · 56 tokens