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/swingerman/engineer/mutategit clone --depth 1 https://github.com/swingerman/engineerWhat 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 | $0.00034 | $0.00525 |
| Opus 5 | $0.00017 | $0.00262 |
| Sonnet 5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
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 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
Run mutation testing on this project.
Instructions
-
Check that both test streams are green before proceeding:
- Run the unit tests
- Run acceptance tests if a pipeline exists (
./run-acceptance-tests.sh) - If either fails, report the failure and stop — do not mutate against a red baseline
-
Detect the project language and check if a mutation tool exists in the project.
- Preferred: Build a custom mutation tool using TDD — a project-specific
module that walks the AST, applies mutations one at a time, runs targeted
tests, and reports survivors. See the
atdd-mutateskill for the 4-module architecture (mutations, runner, core, hashing/selection) and mutation categories. - Alternative: If the user requests a faster setup, install an existing
framework (Stryker, mutmut, PIT, etc. — see the
atdd-mutateskill).
- Preferred: Build a custom mutation tool using TDD — a project-specific
module that walks the AST, applies mutations one at a time, runs targeted
tests, and reports survivors. See the
-
Configure the tool to:
- Target source code only (not tests, specs, generated files, or pipeline code)
- Exclude
generated-acceptance-tests/,acceptance-pipeline/, andspecs/ - If
$ARGUMENTSis provided, scope mutations to that path
-
Run the mutation tool. On the custom-tool path, run
dae_mutmap.py selectfirst and mutate only the changed functions it returns (differential mutation testing — see theatdd-mutateskill); on the framework path, enable the framework's incremental flag. -
Report results:
- Mutation score (percentage)
- Total mutants, killed, survived
- List each surviving mutant with: file, line, mutation description
- Assessment: strong (90%+), moderate (70-89%), or weak (<70%)
- On the custom-tool path, run
dae_mutmap.py updateto refreshmutation-manifest.json; combine fresh results with cached entries for unchanged functions
-
Ask whether to proceed with killing surviving mutants (invoke
/atdd:kill-mutants)
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 · 48 lines · 34 tokens per session scan A b51de204f583
mutate is a command published in the GitHub repository swingerman/engineer (144 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 525 once invoked, about $0.0002 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 commands, from other repositories
paul:help
Show available PAUL commands and usage guide.
paul:progress
Smart status with routing - suggests ONE next action.
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
test
Smart test runner with filtering, coverage, and health monitoring.
paul:verify
Guide manual user acceptance testing of recently built features.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…