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 OutlineDriven/odin-claude-plugin --skill tests-purge-unneededgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/tests-purge-unneeded)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/tests-purge-unneeded"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/tests-purge-unneeded/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/outlinedriven/odin-claude-plugin/tests-purge-unneeded"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/tests-purge-unneeded.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 33 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00071 | $0.01298 |
| Opus 5 | $0.00036 | $0.00649 |
| Sonnet 5 | $0.00014 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
tests-purge-unneeded 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 8d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purge unneeded tests
Contract
| Field | Bound contract |
|---|---|
| Trigger | A legacy, slow, or duplicate test suite is being cleaned up, a post-refactor sweep is due, or the type system already covers an asserted contract. |
| Authority | vcs-reversible-destructive: restrict deletions to VCS-tracked test files, show the exact set before deletion, and use version control as recovery. |
| Side effect | Deletes proved-useless tracked tests in batches, keeps anything whose mutation fails, and runs the full suite after each batch. |
| Done | Each deleted test has one recorded mutation that survived before deletion, the full suite passes, and no protected boundary test was removed. |
Inputs
- Test suite root (required): directory or glob identifying the test files to audit.
- Language or framework (optional): if omitted, detect from project config files (package.json, Cargo.toml, pyproject.toml, go.mod, pom.xml, build.gradle).
- Scope constraint (optional): limit audit to specific directories, file patterns, or changed-files-only mode.
Refusals
- Will not delete a test whose injected mutation was caught — it is load-bearing.
- Will not delete a boundary-contract test (protocol compliance, error semantics, security invariants, real-I/O integration).
- Will not delete a test in a dynamic language that verifies a boundary shape the type system cannot guarantee.
- Will not persist any production-code mutation beyond the proof step.
- Will not delete a test whose failure mode cannot be articulated — keep it pending human review.
Procedure
- Bound scope. Identify the set of test files under audit. List every file path. Do not expand scope beyond the declared root or constraint. Done when: every file path in the audit set is listed.
- Identify candidates. For each test, check: (a) it asserts structure the type system already guarantees, (b) it passes input through verbatim, (c) it asserts a mock return against the fixture that configured it, (d) it has survived mutation testing with no caught mutation, or (e) the real bug its failure would indicate cannot be articulated. Done when: every test is classified as candidate or not-candidate with a reason.
- Articulate the bug. For each candidate, write one sentence: "this test fails when ___ goes wrong." If the sentence cannot name a concrete failure mode that a real code change could plausibly introduce, the test is a deletion candidate. Done when: every candidate has its one-sentence failure mode or is marked unarticulable.
- Check static guarantee. For static-guarantee languages (Rust, TypeScript-strict, Kotlin, Java, C++, OCaml): structural assertions are redundant — a test that asserts a struct has the fields the compiler proved it has catches no bug; mark for deletion. For dynamic languages (Python, JavaScript, Ruby): no compile-time guarantee that a function returns the shape the docstring claims — a boundary shape test is a real-bug test; keep unless step 5 proves otherwise. Done when: each candidate is classified by language guarantee.
- Check boundary contract. Does the test verify protocol compliance (HTTP status codes, message formats, retry semantics), error semantics (malformed input, partial failure, timeout), security invariants (authn/authz enforcement, input validation, rate limits), or real-I/O integration (DB transactions, file I/O, network calls)? If yes, keep regardless of step 4. Done when: each candidate is classified as boundary or non-boundary.
- Inject the bug. For each remaining deletion candidate, modify the production code to introduce the specific bug the test claims to catch. Run the test. If the test still passes, it does not catch that bug — record the mutation and the test outcome. If the test fails, it is load-bearing: revert the mutation and keep the test. Done when: every remaining candidate has a recorded mutation proof (survived or caught).
- Delete in batches. Delete tests whose mutation-proof is recorded. Each batch is an atomic commit with a rationale naming the mutation that survived. Run the full suite after each batch. If the suite regresses, revert the batch and investigate. Done when: all proved-useless tests are deleted in atomic commits and the full suite passes after each batch.
- Report. Produce the output artifact. Done when: the deletion report is emitted.
What ships with it
5 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.
- 8d ago First seen · 59 lines · 71 tokens per session scan A 067f0709b40e
tests-purge-unneeded is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,298 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…