mutator

A testing subagent that changes code or tests in small ways to see whether the test suite catches those changes. This technique is called mutation testing.

In plain words
What is it for?
Test the strength of tests in Rust, TypeScript, or JavaScript workspaces and report surviving mutations or unavailable tools.
Why use it?
It reveals tests that pass but do not detect important implementation mistakes.

Agent

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 agents/orin-dx/agent-plugins/mutator
Clone the repo
git clone --depth 1 https://github.com/orin-dx/agent-plugins
Per session 183 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,044 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 $0.00183 $0.01044
Opus 5 $0.00092 $0.00522
Sonnet 5 $0.00037 $0.00209
Haiku 4.5 $0.00018 $0.00104

Measured yesterday against content hash 8968f87d787e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mutator 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 yesterday.

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.

plugins/smith/agents/mutator.md · 69 lines

What it actually says

<load_first> For Rust workspaces: shared/references/rust-tooling.md For TypeScript/JavaScript workspaces: shared/references/typescript-tooling.md </load_first>

{
  "tool_used": "cargo-mutants | stryker | tool_unavailable",
  "mutants_tested": 0,
  "survived_mutants": [
    {
      "id": "string",
      "file": "string",
      "line": 0,
      "mutation_description": "string",
      "why_it_survived": "string"
    }
  ],
  "precision_tests": [
    {
      "for_mutant_id": "string",
      "test_name": "string",
      "test_description": "string",
      "assertion": "string"
    }
  ],
  "verdict": "pass | fail | tool_unavailable",
  "reasoning": "string"
}

reasoning is a private scratchpad. It is not forwarded downstream.

WHEN verdict is fail, THE SYSTEM SHALL re-invoke implementer with precision_tests as additional failing tests to write and make green before proceeding. WHEN verdict is tool_unavailable, THE SYSTEM SHALL pass the report to exit-gate, which SHALL record a coverage_gap rather than blocking the changeset. WHEN the mutation tool is present but returns an error, THE SYSTEM SHALL report the error as a blocker rather than treating it as tool_unavailable.

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. yesterday First seen · 69 lines · 183 tokens per session scan A 8968f87d787e

Subscribe to this mod's changes

mutator is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 5d ago), licensed MIT. It adds 183 tokens to every session and 1,044 once invoked, about $0.0009 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

security-auditor

Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

addyosmani/agent-skills · 35 tokens

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens

lead

Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.

nguyenthienthanh/aura-frog · 28 tokens

replanner

Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.

nguyenthienthanh/aura-frog · 57 tokens

geo-schema-render

Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.

greglas75/zuvo · 23 tokens