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.
git clone --depth 1 https://github.com/aegntic/cldcdeWrote 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.
[](https://agentmods.dev/commands/aegntic/cldcde/mutate)<a href="https://agentmods.dev/commands/aegntic/cldcde/mutate"><img src="https://agentmods.dev/badge/commands/aegntic/cldcde/mutate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/aegntic/cldcde/mutate"><img src="https://agentmods.dev/badge/commands/aegntic/cldcde/mutate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00304 |
| Opus 5.5 | $0.00000 | $0.00122 |
| Sonnet 5.5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
mutate 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 1mo 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.
What it actually says
/mutate - Run Mutation Testing
Run mutation testing to evaluate test suite effectiveness.
Steps
- Detect the project language and testing framework from configuration files
- Check if a mutation testing tool is installed (Stryker for JS/TS, mutmut for Python, PITest for Java)
- If not installed, provide installation instructions for the appropriate tool
- Identify the source files and their corresponding test files
- Configure mutation operators: arithmetic, conditional, string, return value mutations
- Run the mutation testing tool on the target source files
- Monitor progress: total mutants generated, killed, survived, timed out
- Calculate the mutation score (killed / total * 100)
- List survived mutants with file location, line number, and mutation description
- For each survived mutant, identify which test should have caught it
- Suggest specific test cases to write for the top 10 survived mutants
- Save the mutation report to the reports directory
Rules
- Start with a single file or module to keep execution time reasonable
- Set a timeout per mutant of 10x the normal test execution time
- Exclude test files, configuration files, and generated code from mutation
- A mutation score below 80% indicates weak test coverage
- Focus on survived mutants in critical business logic first
- Do not count equivalent mutants (mutations that produce identical behavior)
- Report execution time and mutant count for performance tracking
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.
- 1mo ago First seen · 29 lines · 0 tokens per session scan A be572625480c
mutate is a command published in the GitHub repository aegntic/cldcde (12 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 304 tokens. 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 commands, from other repositories
maintainer-review-test-coverage
Review the PR for test coverage — does new behavior have tests, are critical paths exercised, do existing tests still cover what they should (Pi-tuned).
discover-checks
Find the project's own checks and declare them. You do not run the gate: a script runs exactly what you declare, for as long as it takes, and records every exit status. Your declaration is the whole of what gets validated, so it must be the project's gate and nothing else.
scriptwriter-open
Open a REAL RECOGNISE REAL cascade with a peer at depth 1. Signs the canonical bytes locally, pushes the signed turn to the peer's /rrr/turn endpoint, records the cascade in this node's state.
scriptwriter-pair
Discover a peer scriptwriter node's /.well-known/scriptwriter descriptor and send a signed first-contact knock. Confirms the peer is reachable, verifies they speak the protocol, and exchanges greetings.
scriptwriter-status
Print a one-shot snapshot of this scriptwriter node — DID + handle + vibe, every active cascade (with depth + your-turn flag), every local room (with contribution counts). Use when the user wants to "see where they are" in the substrate.
apex-quick
Quick Flow for bounded fixes - the full APEX route with Brainstorm skipped and Plan compressed to one task; Analyze trio, delegated execution, eLicit, Verify, challenger and full sniper always run.