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 skills add buildfastwithai/gen-ai-experiments --skill test-strength-codex-test-strengthgit clone --depth 1 https://github.com/buildfastwithai/gen-ai-experimentsWrote 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/skills/buildfastwithai/gen-ai-experiments/test-strength-codex-test-strength)<a href="https://agentmods.dev/skills/buildfastwithai/gen-ai-experiments/test-strength-codex-test-strength"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/test-strength-codex-test-strength/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/skills/buildfastwithai/gen-ai-experiments/test-strength-codex-test-strength"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/test-strength-codex-test-strength.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00543 |
| Opus 5 | $0.00026 | $0.00271 |
| Sonnet 5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
test-strength 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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Strength
Run the bundled runner from the repository being assessed. Keep the repository working tree unchanged: the runner copies it to a temporary directory before each mutant run.
Run the audit
-
Confirm that Python and
pytestare available. Run from the target repository root. -
Run the bundled script, using its absolute skill path:
python <skill-path>\scripts\strength.py [--base <ref>] [path]Omit both arguments to compare the current worktree with the merge-base of the default branch. Use
--base main(or a commit) to choose the diff base. Pass an optional file or directory path to limit which changed Python production files are mutated. -
Read
strength_report.jsonin the target repository root. Treat a killed mutant as behavior caught by the suite and a survived mutant as behavior that the suite did not catch. The runner executes the full test suite for every mutant so indirect, fixture-based, and integration coverage are included.
Analyze survivors
For each item in survived_mutants:
-
Inspect its
diffand decide whether it changes observable behavior for valid inputs. -
Discard only genuinely equivalent mutants; state why they are equivalent.
-
For every real survivor, add one focused test that passes on the original code and fails for the mutant.
-
Verify that test before suggesting it:
pytest <temporary-test-file> python <skill-path>\scripts\strength.py verify "<mutant-id>" <temporary-test-file>The first command must pass. The verification command must print
VERIFICATION SUCCESSand exit with code 0. Remove the temporary verification file afterward unless the user asks to keep it.
Report results
Use this structure and include only real survivors:
<Total Tests> tests | <Total Mutants> mutants across <Changed Functions Count> changed functions
<Killed Count> killed | <Survived Count> survived | <Equivalent Count> equivalent (discarded)
### SURVIVED
#### <File Path>:<Line Number> <Function Name>
`<Original Expression>` -> `<Mutated Expression>`
Reason for survival: <why the current tests miss this behavior>
Suggested test:
```diff
+ <verified test change>
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 228 B
- fixtures/strong/auth.py 114 B runs code
- fixtures/strong/billing.py 236 B runs code
- fixtures/strong/calc.py 125 B runs code
- fixtures/strong/logger.py 142 B runs code
- fixtures/strong/test_strong.py 1.3 KB runs code
- fixtures/strong/utils.py 136 B runs code
- fixtures/weak/auth.py 114 B runs code
- fixtures/weak/billing.py 236 B runs code
- fixtures/weak/calc.py 125 B runs code
- fixtures/weak/logger.py 142 B runs code
- fixtures/weak/test_weak.py 737 B runs code
- fixtures/weak/utils.py 136 B runs code
- README.md 3.5 KB
- scripts/strength.py 27 KB runs code
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.
- 9d ago First seen · 59 lines · 52 tokens per session scan A e3255f522233
test-strength is a skill published in the GitHub repository buildfastwithai/gen-ai-experiments (763 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 543 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.