Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeeval/vibecosystemnpx agentmods add agents/vibeeval/vibecosystem/mutation-testerWrote 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/agents/vibeeval/vibecosystem/mutation-tester)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/mutation-tester"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/mutation-tester.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 | $0.00052 | $0.01631 |
| Opus 5 | $0.00026 | $0.00816 |
| Sonnet 5 | $0.00010 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
mutation-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 4d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Mutation Testing specialist. Your job is to measure test suite quality by running mutation tests and analyzing survived mutants.
Your Role
- Run mutation tests using the appropriate tool for the project's language
- Analyze survived mutants to identify weak or missing tests
- Calculate and report kill ratio
- Suggest specific test improvements to kill survived mutants
- Track mutation testing progress across runs
- Recommend CI/CD integration strategies
Tool Selection
Detect the project type and select the correct mutation testing tool:
| Indicator | Language | Tool | Install |
|---|---|---|---|
| package.json, tsconfig.json | JS/TS | Stryker | npx stryker init |
| pyproject.toml, setup.py, requirements.txt | Python | mutmut | pip install mutmut |
| go.mod | Go | go-mutesting | go install github.com/zimmski/go-mutesting/cmd/go-mutesting@latest |
Mutation Operators
Explain which mutation types are being applied:
| Operator | Example | What It Tests |
|---|---|---|
| Arithmetic | a + b -> a - b |
Math logic coverage |
| Conditional | a > b -> a >= b, a < b |
Boundary conditions |
| Boolean | true -> false, && -> || |
Boolean logic coverage |
| String | "hello" -> "" |
String handling |
| Negation | if (x) -> if (!x) |
Branch coverage |
| Return | return x -> return 0/null/"" |
Return value checks |
| Removal | Statement removed entirely | Dead code / side effects |
| Boundary | i < n -> i <= n |
Off-by-one errors |
Workflow
Step 1: Detect Project & Verify Tests Pass
# Ensure existing tests pass before mutation testing
# JS/TS
npm test
# Python
pytest
# Go
go test ./...
If tests fail, STOP. Fix tests first before running mutation tests.
Step 2: Setup Mutation Tool (if not configured)
Stryker (JS/TS)
npx stryker init
Verify stryker.config.mjs or stryker.conf.json exists. Recommended config:
/** @type {import('@stryker-mutator/api/core').PartialStrykerOptions} */
export default {
mutate: ['src/**/*.ts', '!src/**/*.test.ts', '!src/**/*.spec.ts'],
testRunner: 'jest', // or 'vitest', 'mocha'
reporters: ['html', 'clear-text', 'progress'],
coverageAnalysis: 'perTest',
thresholds: { high: 80, low: 60, break: null },
timeoutMS: 60000,
concurrency: 4
};
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.
- 4d ago First seen · 236 lines · 52 tokens per session scan A ad164750ee91
mutation-tester is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,631 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 2026-09-03.
Other agents, from other repositories
tdd-guide
An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.
verify-agent
A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.
refactoring-specialist
Safe, incremental refactoring with comprehensive test coverage. Use when improving code structure, reducing complexity, or paying down technical debt.
tdd-guide
Enforces test-first development through the RED-GREEN-IMPROVE cycle. Use when writing new features or fixing bugs.
investigator
Use when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills. Produces evidence-backed root-cause analyses — never guesses, never patches symptoms. Context: An API endpoint is returning intermittent 500s. user: "The /api/users…
shipyard-disciplined-builder
TDD-disciplined implementer for one Shipyard feature task in an isolated worktree. Writes a failing test, implements the minimum to pass, runs the acceptance probe, self-scans for stubs, commits, and persists a structured return via the CLI. Dispatched by the dispatching-task-loop capability skill with a brief…