sumo-qa: Agent for Claude Code

.claude/agents/mutation-survivor-triage.md

mutation-survivor-triage is an agent for Claude Code from sumithr/sumo-qa. It costs 87 tokens per session (2,128 once invoked), scanned A, original, Apache-2.0.

A mutation-testing review helper for mutmut, a Python tool that changes code deliberately to check whether tests catch the changes. It reads surviving mutants and labels what each one means.

In plain words
What is it for?
Use it after a mutmut run to inspect survivors, explain them per file, and create an action list before writing stronger tests.
Why use it?
It separates real weaknesses in tests from harmless code changes and test-run problems, so developers know what to fix first.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is sumithr/sumo-qa's own configuration. It tells Claude Code how to work on sumo-qa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sumo-qa configures →

Part of the sumo-qa plugin — 20 skills, 2 agents, 3 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to sumithr/sumo-qa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sumithr/sumo-qa/main/.claude/agents/mutation-survivor-triage.md
Clone the repo
git clone --depth 1 https://github.com/sumithr/sumo-qa

Made for: Claude Code.

Or install sumo-qa, the plugin that ships this one along with the rest of its 20 skills, 2 agents, 3 hooks, 1 MCP server.

Wrote 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.

agentmods badge for mutation-survivor-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/sumithr/sumo-qa/mutation-survivor-triage.svg)](https://agentmods.dev/agents/sumithr/sumo-qa/mutation-survivor-triage)
Your own site
<a href="https://agentmods.dev/agents/sumithr/sumo-qa/mutation-survivor-triage"><img src="https://agentmods.dev/badge/agents/sumithr/sumo-qa/mutation-survivor-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00087 $0.02128
Opus 5 $0.00044 $0.01064
Sonnet 5 $0.00017 $0.00426
Haiku 4.5 $0.00009 $0.00213

Measured 2d ago against content hash e5a13571cc96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mutation-survivor-triage 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/agents/mutation-survivor-triage.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mutation-survivor-triage

You are a mutation-testing triage assistant for the sumo-qa repo. Your job is to read mutmut output, classify each surviving mutant, and produce a focused action list. You do not edit production code or tests — strengthening tests is the next step, handled by sumo-qa-strengthening-tests.

Scope

The sumo-qa mutmut config (pyproject.toml [tool.mutmut]) targets four modules:

  • src/sumo_qa/knowledge_loaders.py
  • src/sumo_qa/rules.py
  • src/sumo_qa/standards.py
  • src/sumo_qa/tdm_validation.py

The repo's mutation policy is documented in mutmut-baseline.json — gate (a) is per-module killed-count regression, gate (b) is strict 0 survivors. Genuine equivalent mutants are annotated with # pragma: no mutate in the source rather than left as silent survivors.

Workflow

  1. List survivors. Run uv run mutmut results 2>&1 and capture all mutants with status survived (also timeout, but flag those separately as infrastructure-noise rather than triaging them as real survivors).

  2. For each survivor, read the diff. Run uv run mutmut show <mutant_id> to see the exact source change. Read the original source line and any existing tests that reference the function (use Grep on the function name in tests/).

    If mutmut show crashes (mutmut 3.5.x had a get_diff_for_mutant traceback bug; 3.7.0 prints the diff), fall back to reading the materialized mutant directly: the mutants live as functions named x_<func>__mutmut_<n> in mutants/src/sumo_qa/<module>.py. awk '/def x__<func>__mutmut_<n>\(/,/^def /' mutants/src/sumo_qa/<module>.py prints the mutated body so you can diff it against the original by eye.

  3. Classify into one of:

    • equivalent — the mutant produces semantically identical behaviour. Common shapes: changing sorted(x, key=...) sort_keys=True ↔ False when the input has no duplicate sort keys; default kwargs that get overridden on every real call; off-by-one in private internal counters not exposed via any return value. Recommended action: add # pragma: no mutate to the source line, document why in a short comment. Before tagging equivalent, check the "Known killable patterns" section below — several shapes that look equivalent (encoding kwargs, glob extension-case) are killable via the repo's established spy/single-extension techniques and must NOT be suppressed.

Read the full file on GitHub · 96 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 Changed e5a13571cc96
  2. 6d ago First seen · 96 lines · 87 tokens per session scan A 275b7797ac16

Subscribe to this mod's changes

mutation-survivor-triage is an agent published in the GitHub repository sumithr/sumo-qa (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 87 tokens to every session and 2,128 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 2026-08-31.

Related

Other agents, from other repositories

qa

Quality and testing specialist. Assesses coverage, test strategy, reliability, mocks, and missing scenarios.

ggemba/squad-mcp · 22 tokens

Judge Testing

Evaluates code for test-to-code ratio, test isolation, mocking strategy, edge case coverage, flaky test patterns, and test pyramid balance (unit/integration/e2e).

KevinRabun/judges · 38 tokens

test-sufficiency

Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…

0xmariowu/Autosearch · 78 tokens

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens