mx-report

A reporting step for mutation testing, where source code is deliberately changed to see whether tests catch the changes. It calculates a mutation score and produces a report showing test gaps and surviving changes.

In plain words
What is it for?
Use it to generate a mutation-testing report, review surviving mutants, understand why they matter, and identify tests to add.
Why use it?
It turns mutation-test results into a summary that helps explain which code changes were not detected by the tests.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/claritune/mutantx/mx-report
Any agent
npx skills add Claritune/mutantx --skill mx-report
Clone the repo
git clone --depth 1 https://github.com/Claritune/mutantx

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00541
Opus 5 $0.00012 $0.00270
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured 2d ago against content hash 013614913ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mx-report 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.

.claude/skills/mx-report/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MutantX — Phase 4: Reporting

This phase has two layers:

  1. Deterministic (Python script) — calculates scores, generates summary tables, includes patch diffs for survived mutants
  2. AI analysis (this skill) — reads the report and adds "why this matters" explanations, suggested tests, and prioritized recommendations

Step 1: Run the Deterministic Report Script

Locate and execute mx-report.py:

python3 <path-to-mx-report.py> --mutants-dir .mutants

Find mx-report.py by checking these locations in order:

  1. ./src/scripts/mx-report.py (if inside the MutantX repo)
  2. ~/.claude/scripts/mx-report.py (global install)

This generates .mutants/report.md with summary statistics, survived mutant patches, killed mutant table, and updates the manifest summary. Display the script's output to the user.

Step 2: AI Analysis of Survived Mutants

After the script runs, read .mutants/report.md. For each survived mutant section (marked with <!-- AI analysis --> comments), replace the comment with:

For each survived mutant:

  1. Read the patch diff shown in the report.
  2. Read the relevant source file to understand the surrounding code context.
  3. Add these two sections after the diff block:

Why this matters: A brief explanation of what kind of bug this mutation represents and what could go wrong in production if this bug existed. Be specific to the actual code, not generic.

Suggested test: A concrete, copy-pasteable test case (in the project's language and test framework) that would catch this mutant. Use realistic test names and assertions.

After all survived mutants:

Add a ## Recommendations section at the end of the report with 2-5 bullet points summarizing the most important test gaps found. Be specific — reference file names and functionality, not generic advice.

Step 3: Present Results

Display a concise summary to the user:

Mutation Testing Complete!

Score: 84% (16 killed / 19 testable)
Survived: 3 mutants — see .mutants/report.md for details

Top gaps:
  - src/billing.ts: price rounding logic has no edge case tests
  - src/auth.ts: token expiry check can be bypassed

Read the full file on GitHub · 61 lines

Changes

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.

  1. 2d ago First seen · 61 lines · 23 tokens per session scan A 013614913ea1

Subscribe to this mod's changes

mx-report is a skill published in the GitHub repository Claritune/mutantx (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 541 once invoked, about $0.0001 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 2026-08-31.