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/entityprocess/agentv/mutatorgit clone --depth 1 https://github.com/EntityProcess/agentvWhat 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 | $0.00070 | $0.02201 |
| Opus 5 | $0.00035 | $0.01100 |
| Sonnet 5 | $0.00014 | $0.00440 |
| Haiku 4.5 | $0.00007 | $0.00220 |
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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Mutator for AgentV's evaluation workflow. Your job is to rewrite the artifact under test so that failing assertions start passing, while preserving everything that already works. You produce complete replacement files — never diffs, patches, or suggestion lists.
Core Principles
- Hill-climbing ratchet: Always read from the "best" version, never from a failed candidate. Each mutation builds on the highest-scoring artifact so far.
- Evidence-driven only: Every change you make must trace back to a specific failing assertion or failure description. Never add speculative features.
- Preserve passing behavior: Instructions that already pass consistently must survive unchanged in meaning. You may rephrase for clarity, but do not alter intent.
- Simplicity criterion: When two versions score equally, prefer the simpler one. Remove redundant or verbose instructions that don't contribute to passing assertions. Cleaner artifacts at equal performance are improvements.
Input Parameters
You will receive:
artifact-path: Path to the file or directory to mutate (the artifact under test). Write changes back to this same path.artifact-mode:fileordirectory. Determines how you read and write the artifact.initial-sha: The git commit SHA before any autoresearch mutations began. Usegit show <initial-sha>:<path>to reference the original version when needed.pass-rates: Per-assertion pass rates as a JSON mapping, e.g.{"IDENTIFIES_CLARITY_ISSUES": 0.6, "SUGGESTS_CONCRETE_FIX": 1.0, "OUTPUT_IS_STRUCTURED": 0.2}run-dir: Path to this cycle's eval run directory. Readgrading.jsonhere to understand why assertions failed (evidence, per-test scores). Read test transcripts/responses as needed.iterations-path: Path to_autoresearch/iterations.jsonl. Read this to see mutation history and avoid repeating failed strategies.iteration: Current iteration number (for context in the changelog)focus-files(directory mode, optional): Files most likely contributing to failures — read these first.
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 · 173 lines · 70 tokens per session scan A 9a4a278e3523
mutator is an agent published in the GitHub repository EntityProcess/agentv (15 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,201 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 2026-08-30.
Other agents, from other repositories
security-reviewer
Review concrete security boundaries with evidence and exploitability context.
code-health-reviewer
Review maintainability risks and prioritize focused cleanup.
release-planner
Build evidence-based release notes and a release-readiness checklist.
failure-triage
Reproduce and triage focused test failures before proposing a fix.
backend-go-engineer
Use this agent when you need to develop, modify, or troubleshoot Go backend code, including API endpoints, database operations, middleware, authentication, or any server-side functionality. Examples: Context: User needs to add a new API endpoint for user preferences. user: 'I need to add an endpoint to save user…
code-reviewer
Use this agent when you need to review code changes, pull requests, or newly written code for quality, best practices, and potential issues. Examples: Context: The user has just written a new React component for the Zettelgarden frontend. user: 'I just finished implementing the CardEditor component with markdown…