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 agentmods add skills/shimo4228/claude-harness/learn-evalnpx skills add shimo4228/claude-harness --skill learn-evalgit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/learn-eval)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/learn-eval"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/learn-eval.svg" alt="Measured on agentmods" 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 | $0.00137 | $0.03444 |
| Opus 5 | $0.00068 | $0.01722 |
| Sonnet 5 | $0.00027 | $0.00689 |
| Haiku 4.5 | $0.00014 | $0.00344 |
Grade A, and why
learn-eval 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 today.
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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn-eval - Extract, Evaluate, then Save
Extract a reusable pattern from the session, gate it, and route every Save to a destination something actually reaches.
What to Extract
Look for:
- Error Resolution Patterns — root cause + fix + reusability
- Debugging Techniques — non-obvious steps, tool combinations
- Workarounds — library quirks, API limitations, version-specific fixes
- Project-Specific Patterns — conventions, architecture decisions, integration patterns
Process
-
Review the session for extractable patterns
-
Identify the most valuable/reusable insight
-
Determine the destination — there is no parking lot.
Every Save must land somewhere that something actually routes to (ADR-0047), so pick one of exactly two:
- Absorb into an existing asset — the pattern belongs inside a skill, rule, or
hooks/README.mdsection that already owns the topic. Name the file and the section. This is the default: an addition to a reachable asset beats a new file. - Promote to a skill — the pattern has its own independent trigger (a user request
that no installed skill answers). Run skill: skill-creator (required by
rules/common/skills.mdbefore writing any skill).
If neither fits, the verdict is Drop, not "park it somewhere for now". A note that nothing points at is reachable only by grep, and grep requires already knowing the content exists — measured over 74 days, the retired
learned/directory was read during real work 12 times across 8 notes, while the audits that judged whether to keep it accounted for 161 of its 184 reads.Global vs project placement (once a destination type is chosen): 正本は
docs/adr/0025-global-vs-project-asset-placement.md。 - Absorb into an existing asset — the pattern belongs inside a skill, rule, or
-
Draft the candidate as a scratch note (the final skill shape belongs to
skill-creator;overlap_candidates.pyreads name / description / Problem / Solution / When to Use):
What ships with it
6 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.
- today Changed · -10 lines c895e843d422
- 5d ago First seen · 264 lines · 137 tokens per session scan A 931adb1360ce
learn-eval is a skill published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 3d ago), licensed MIT. It adds 137 tokens to every session and 3,444 once invoked, about $0.0007 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
zod
Zod v4 best practices, patterns, and API guidance for schema validation, parsing, error handling, and type inference in TypeScript applications. Covers safeParse, object composition, refinements, transforms, codecs, branded types, v3→v4 migration, and testing schemas with Jest or Vitest. Baseline: zod ^4.3.0. Triggers…
jest
Jest best practices, patterns, and API guidance for JavaScript/TypeScript testing. Covers mock design, async testing, matchers, timer mocks, snapshots, module mocking, configuration, and CI optimization. Baseline: jest ^30.0.0. Triggers on: jest imports, describe, it, test, expect, jest.fn, jest.mock, jest.spyOn…
agent-adoption-triage
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
zod-testing
Testing patterns for Zod schemas using Jest and Vitest. Covers schema correctness testing, mock data generation, error assertion patterns, integration testing with API handlers and forms, snapshot testing with z.toJSONSchema(), and property-based testing. Baseline: zod ^4.0.0. Triggers on: test files for Zod schemas…
redux-saga
Redux-Saga best practices, patterns, and API guidance for building, testing, and debugging generator-based side-effect middleware in Redux applications. Covers effect creators, fork model, channels, testing with redux-saga-test-plan, concurrency, cancellation, and modern Redux Toolkit integration. Baseline: redux-saga…
redux-saga-testing
Write tests for Redux Sagas using redux-saga-test-plan, runSaga, and manual generator testing. Covers expectSaga (integration), testSaga (unit), providers, partial matchers, reducer integration, error simulation, and cancellation testing. Works with Jest and Vitest. Triggers on: test files for sagas…