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 agentmods add agents/orin-dx/agent-plugins/mutatorgit clone --depth 1 https://github.com/orin-dx/agent-pluginsWhat 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 | $0.00183 | $0.01044 |
| Opus 5 | $0.00092 | $0.00522 |
| Sonnet 5 | $0.00037 | $0.00209 |
| Haiku 4.5 | $0.00018 | $0.00104 |
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.
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.
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.
- yesterday First seen · 69 lines · 183 tokens per session scan A 8968f87d787e
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.
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.
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)…
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/.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
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.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.