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/crewrig/crewrig/testernpx skills add crewrig/crewrig --skill testergit clone --depth 1 https://github.com/crewrig/crewrigWhat 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 | $0.00055 | $0.01434 |
| Opus 5 | $0.00028 | $0.00717 |
| Sonnet 5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
tester 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tester
Tests exist to catch regressions and to document behavior, not to inflate a coverage number. Bias toward fewer, sharper tests.
When to activate
- A feature is being added and the project's convention requires tests.
- A bug fix lacks a regression test.
- The user asks for a test plan or edge-case enumeration.
- A diff is up for review and you suspect under-tested behavior.
If the project has no test infrastructure and the user has not asked for one, do not invent one — say so and move on.
Operating mode
1. Identify the unit of behavior
Pick the smallest observable behavior to test, not the smallest function. A function with no observable contract has nothing to test. A file-level helper called only from one place is best tested through the caller.
2. Golden path + edge cases (not exhaustively)
For each behavior, plan:
- One golden-path test that exercises the success case.
- One or two edge-case tests for the failure modes that matter.
- A regression test if the test was triggered by a bug fix — named so it is obvious which bug it guards.
Edge cases to consider, in this order of priority:
- Empty / null / zero-length input.
- Boundary values (off-by-one, overflow, encoding edges).
- Known-bad input (malformed, adversarial — see security skill).
- Concurrent / repeated invocations if the surface is stateful.
- Partial failure (network mid-call, disk full, signal interrupt).
Stop adding cases when the marginal case becomes contrived. Coverage of contrived cases costs maintenance forever.
3. Real dependencies where it matters
For integration tests:
- Hit a real database when the project's convention is integration testing (use Testcontainers, Docker Compose, or the project's scaffold). Mocked DB tests have a known failure mode where they pass while the real schema is broken.
- Mock an external API only when its calls are non-deterministic, slow, or rate-limited. Otherwise prefer a recorded fixture (VCR-style).
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 · 161 lines · 55 tokens per session scan A c82bf5ccc4e8
tester is a skill published in the GitHub repository crewrig/crewrig (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,434 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.