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 mutation-triage-genotoxicgit 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/mutation-triage-genotoxic)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/mutation-triage-genotoxic"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/mutation-triage-genotoxic/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/mutation-triage-genotoxic"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/mutation-triage-genotoxic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00848 |
| Opus 5 | $0.00034 | $0.00424 |
| Sonnet 5 | $0.00014 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
mutation-triage-genotoxic 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mutation triage genotoxic
Contract
| Field | Bound contract |
|---|---|
| Trigger | A mutation campaign has produced surviving mutants and the user needs triage. |
| Authority | Reversible-local: write only the classification ledger and test-change proposals. Does not mutate tests or source directly. Rollback by deleting the ledger. |
| Side effect | A classification ledger with one label per mutant and proposed test changes. |
| Done | Every surviving mutant has exactly one classification (false-positive, missing-test, genotoxic, or removable) with coverage-map evidence, and the ledger has no unprocessed remainder. |
Inputs
- Mutation report (required): the output of a completed mutation campaign listing surviving mutants with source locations and mutations applied.
- Source tree (required): the codebase under mutation, accessible for reading.
- Coverage map (required): a line or branch coverage map showing which tests exercise which source regions. Without this, classification cannot proceed.
Procedure
- Ingest the mutation report. Collect every surviving mutant with its source location, mutation applied, and mutant identifier. Group mutants by changed source region (function, method, or block). Done when: every surviving mutant is recorded and grouped by region.
- For each group, consult the coverage map to determine whether tests exercise the mutated region. Record which tests cover the region and which lines or branches within it are covered. Done when: every group has a coverage determination: covered, partially covered, or uncovered.
- Classify each mutant as exactly one of:
- false-positive: the mutant is semantically equivalent to the original, or a test that catches it exists but was not executed in the campaign run. Coverage map shows the region is covered; the mutant's effect is null or already guarded.
- missing-test: the coverage map shows no test exercises the mutated region. The fix is to write a test that covers the region.
- genotoxic: the coverage map shows tests exercise the region but the mutant survived. The existing tests touch the code but do not assert the behavior the mutation changed. The fix is to strengthen the existing test or add an assertion.
- removable: the mutated code is dead, unreachable, or behind a permanently disabled feature flag. The fix is to remove the dead code, not to test it. Done when: each mutant has exactly one classification with coverage-map evidence cited.
- Write proposals to the ledger. For each mutant, record the classification, the coverage evidence, and the proposed action (no action, write test, strengthen test, remove dead code). Done when: every mutant has a ledger entry with classification, evidence, and proposed action.
- Verify every mutation is accounted for. Count the mutants in the report and the entries in the ledger. If any mutant lacks a classification, return to step 3 for that mutant. Done when: the ledger count equals the report count and no mutant is unprocessed.
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.
- 7d ago First seen · 45 lines · 68 tokens per session scan A c75aa60abcfc
mutation-triage-genotoxic is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 848 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 2026-09-04.
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…