Borrowing it
Nothing to install: this file belongs to InteliGHQ/intelig-agent-playbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/InteliGHQ/intelig-agent-playbook/main/.claude/skills/fitness-test/SKILL.mdgit clone --depth 1 https://github.com/InteliGHQ/intelig-agent-playbookWrote 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/intelighq/intelig-agent-playbook/fitness-test)<a href="https://agentmods.dev/skills/intelighq/intelig-agent-playbook/fitness-test"><img src="https://agentmods.dev/badge/skills/intelighq/intelig-agent-playbook/fitness-test/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/intelighq/intelig-agent-playbook/fitness-test"><img src="https://agentmods.dev/badge/skills/intelighq/intelig-agent-playbook/fitness-test.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 | $0.00094 | $0.00678 |
| Opus 5 | $0.00047 | $0.00339 |
| Sonnet 5 | $0.00019 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
fitness-test 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 10d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author a fitness test (advisory → enforced)
The repo's core move: when a rule keeps getting broken, you don't write a sterner sentence — you write a test the build cannot pass while the rule is violated. This skill packages how to do that here, with the conventions and a scaffold script, so it's one operation instead of a from-scratch guess each time.
When to use
- A
manual-reviewrule was violated again (thecode-reviewerflagged a repeat offender). - You're promoting a rule UP the Enforcement Map in
standards/architecture.rules.md.
When NOT to use
- The invariant is already enforced by
tsc(types) or the linter — that's thecitier. Don't duplicate it as a fitness test. - You can't state the rule as a checkable property over the source. Sharpen the rule first; a vague rule makes a flaky test.
The contract (non-negotiable)
- The test lives in the bounded context's
test/architecture.fitness.test.ts(seearch-examples/). - The test name starts with the rule ID, e.g.
test("API-001: controllers import no domain types", …). - On failure it prints the rule ID and the offending files — so the next agent gets the ID in the red build and the lesson isn't taught twice.
- For dependency rules, prefer a real architecture-test tool (dependency-cruiser / ts-arch) over ad-hoc string matching; string scans miss re-exports, path aliases, and dynamic imports.
Steps
- Read the rule in
standards/architecture.rules.mdfor its principle (the why), not just the wording — the test should defend the principle. - State the invariant as a property over
src/**(e.g. "no file inapi/**importsdomain/**"). - Scaffold the test: run
scaffold.sh <RULE-ID> "<what it checks>"from this skill for a stub, then fill in the predicate. - Make it go red against a known violation, then green. A test you've only seen pass is not yet a wall.
- Promote the rule: change its tag in
STANDARDS_DIGEST.mdand its row in the Enforcement Map tofitness, citing the new test.
What ships with it
1 file 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.
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.
- 10d ago First seen · 46 lines · 94 tokens per session scan A 97657122842b
fitness-test is a skill published in the GitHub repository InteliGHQ/intelig-agent-playbook (2 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 678 once invoked, about $0.0005 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 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.