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 commands/tk-logl/sentinel/mutategit clone --depth 1 https://github.com/tk-logl/sentinelWhat 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 | $0.00014 | $0.00622 |
| Opus 5 | $0.00007 | $0.00311 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
mutate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sentinel:mutate
Run mutation testing on specified source files to verify that tests actually catch bugs.
What to Do
-
Check if mutmut is installed:
python3 -m mutmut --version 2>/dev/null || pip install mutmut -
Determine target files:
- If the user specified files: use those
- If not: find files changed since last commit:
git diff --name-only HEAD~1 | grep '\.py$' | grep -v test_ | grep -v __pycache__
-
Find corresponding test files for each target:
apps/{service}/module.py→apps/{service}/tests/test_module.pyvoice/backend/module.py→voice/backend/tests/test_module.py
-
Run mutmut on each target file:
python3 -m mutmut run --paths-to-mutate=<target_file> --tests-dir=<test_dir> -
Report results:
- Show mutation score (killed / total)
- List surviving mutants (these indicate weak tests)
- For each survivor, show the mutation and which test should catch it
-
Provide actionable guidance:
- For each surviving mutant, suggest a specific test assertion that would kill it
- Example: "Mutant changed
>to>=in line 42 — add a boundary test:assert func(0) == expected"
Example Output
=== Mutation Testing Report ===
Target: apps/brain/services.py
Tests: apps/brain/tests/test_services.py
Score: 47/50 killed (94%)
Surviving mutants:
Line 42: changed > to >= in hybrid_search()
→ Add test: assert hybrid_search(query="x", top_k=0) raises ValueError
Line 78: removed return statement in _normalize_score()
→ Add test: assert _normalize_score(0.5) == 0.5
Line 95: changed True to False in is_valid_query()
→ Add test: assert is_valid_query("valid") == True
Configuration
In pyproject.toml:
[tool.mutmut]
paths_to_mutate = "apps/"
backup = false
runner = "python -m pytest --tb=no -q"
mutate_only_covered_lines = true
Notes
- Mutation testing is SLOW (minutes, not seconds) — this is a command, not a hook
- Only mutate changed files to keep run time practical (2-5 minutes)
- A mutation score below 70% means tests are not constraining behavior
- Target: 80%+ for core logic modules
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.
- 2d ago First seen · 78 lines · 14 tokens per session scan A d72ae0828608
mutate is a command published in the GitHub repository tk-logl/sentinel (4 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 622 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.