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/poteto/noodle/testingnpx skills add poteto/noodle --skill testinggit clone --depth 1 https://github.com/poteto/noodleWhat 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 | $0.00068 | $0.00660 |
| Opus 5 | $0.00034 | $0.00330 |
| Sonnet 5 | $0.00014 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
testing 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing
Test-driven by default. Prove the problem before solving it.
Core Workflow: Bug First
- Reproduce — Run the failing scenario and observe the actual behavior
- Write a failing test — Minimal reproduction as a test case
- Commit the failing test — Use
Skill(commit)with message liketest: reproduce #issue-description - Fix the code — Only now attempt the fix
- Verify — Run
pnpm testand confirm the test passes - Commit the fix — Separate commit from the test
This applies to all bug fixes. The failing test proves the bug exists and prevents regressions.
Fixture Tests
Noodle uses directory-based fixtures in testdata/. Read references/fixtures.md for full format, helper API, and code patterns.
Creating a New Fixture
./scripts/scaffold-fixture.sh <package-dir> <fixture-name> [state-count]
Fill in the generated input.json/input.ndjson and expected.md, then:
pnpm fixtures:hash:sync
Bug Fixtures
See references/fixtures.md for full bug fixture format (frontmatter fields, expected error sections, and the fix workflow).
Key Commands
| Command | Purpose |
|---|---|
pnpm test |
Run all tests |
pnpm test:short |
Skip integration tests |
pnpm check |
Full local CI (test + vet + lint + fixtures) |
pnpm bugs |
List fixtures marked as known bugs |
pnpm fixtures:loop |
Verify loop fixtures match expected |
pnpm fixtures:loop:record |
Regenerate loop fixture expected output |
pnpm fixtures:hash |
Verify fixture input hashes |
pnpm fixtures:hash:sync |
Update fixture input hashes |
pnpm vet |
Run go vet |
pnpm lint:arch |
Architecture lint (file sizes, legacy patterns) |
Running Specific Tests
# Single package
go test ./loop
# Single test
go test ./loop -run TestLoopDirectoryFixtures
# Bypass cache
go test -count=1 ./parse
# With race detector
go test -race ./...
# Verbose
go test -v ./tui
What ships with it
1 file 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.
- 2d ago First seen · 90 lines · 68 tokens per session scan A 38ed7bc2db7b
testing is a skill published in the GitHub repository poteto/noodle (263 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 660 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…