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 koolamusic/claudefiles --skill principle-test-behavior-not-implementationgit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/koolamusic/claudefiles/principle-test-behavior-not-implementation)<a href="https://agentmods.dev/skills/koolamusic/claudefiles/principle-test-behavior-not-implementation"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/principle-test-behavior-not-implementation/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/koolamusic/claudefiles/principle-test-behavior-not-implementation"><img src="https://agentmods.dev/badge/skills/koolamusic/claudefiles/principle-test-behavior-not-implementation.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 | $0.00052 | $0.00320 |
| Opus 5.5 | $0.00021 | $0.00128 |
| Sonnet 5.5 | $0.00010 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
principle-test-behavior-not-implementation 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.
This is a copy
83% identical to principle-test-behavior-not-implementation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Test Behavior, Not Implementation
A test calls the code as its users do and asserts the exact result they see. Rewrite or delete any test that would still pass if every imported function returned undefined or a wrong value.
These shapes fail that check:
- Loose or no assertion:
toBeDefined,toBeTruthy,not.toThrow,toBeGreaterThan(0). - Call or absence only:
toHaveBeenCalled,not.toHaveBeenCalled,toBeUndefined,toEqual([]). - Expected value computed by the code under test:
expect(f(a)).toBe(f(a)). - Restated constant, config default, table row, or prompt string.
- Assertions on data the test built, with no call to the subject.
Fix: call the subject in the test body with one concrete input and assert the literal output or effect. For a mock, assert the payload it received. For an absence, also assert the presence on another input. For a constant, test the mechanism that reads it with one input instead of restating the value.
Keep relation checks across table rows (a key in two tables, a parent that exists) and *.test-d.ts type checks.
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 · 22 lines · 52 tokens per session scan A b2b73ba42920
principle-test-behavior-not-implementation is a skill published in the GitHub repository koolamusic/claudefiles (130 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 320 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to principle-test-behavior-not-implementation, differing in 0 lines, and is treated as a copy.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.