Borrowing it
Nothing to install: this file belongs to adamayoung/TMDb. 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/adamayoung/TMDb/main/.claude/skills/canon-tdd/SKILL.mdgit clone --depth 1 https://github.com/adamayoung/TMDbWrote 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/adamayoung/tmdb/canon-tdd)<a href="https://agentmods.dev/skills/adamayoung/tmdb/canon-tdd"><img src="https://agentmods.dev/badge/skills/adamayoung/tmdb/canon-tdd/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/adamayoung/tmdb/canon-tdd"><img src="https://agentmods.dev/badge/skills/adamayoung/tmdb/canon-tdd.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 | $0.00068 | $0.01247 |
| Opus 5 | $0.00034 | $0.00624 |
| Sonnet 5 | $0.00014 | $0.00249 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
canon-tdd 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 12d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canon TDD
Test-driven development the way Kent Beck describes as "Canon TDD", per https://adam-young.co.uk/blog/canon-tdd/. CLAUDE.md mandates a TDD approach for this package; this skill is the detailed how.
Red-Green-Refactor is the engine. The Test List is the steering wheel.
Agent behaviour contract
The point of this skill: do these by default, without being reminded.
- Start with a test list, and show it. Before touching production code, enumerate the behaviours and edge cases as a checklist and confirm it with the user (or state it explicitly). This is the steering wheel — it defines "done".
- No production code before a failing test. Write exactly one test, run it, and watch it fail for the right reason. Never write the implementation first and back-fill tests.
- One test at a time. Do not convert the whole test list into code up front — the first passing test often forces a design change that affects the rest.
- Refactor only on green, and keep refactoring out of the make-it-pass step.
- Repeat until the test list is empty, adding newly-discovered cases to the list as you go.
The five steps
- Write a test list — every behavioural variant and edge case you can think of, as a plain checklist. Not code yet. It's a living list: add to it whenever implementation reveals a new case.
- Write a test — pick the next item and write one real, automated test: setup, invocation, and assertions. Define what the system does and how it's invoked — not how it works inside. Run it; confirm it fails — and state the failure: quote the failing assertion/message and check it is the expected reason. (For brand-new API the first red is normally a compile error — the symbol doesn't exist yet; that is expected. Stub the minimal declaration and re-run so the red becomes the failing assertion.) A compile error in existing code, a missing import, or an unrelated crash is a red for the wrong reason — it proves nothing about the behaviour, so fix the test and re-run until it is red for the right reason.
- Make it pass — change the system to satisfy that test with the simplest thing that works. Nothing more; resist solving items still on the list.
- Optionally refactor — improve names, structure, and duplication while every test stays green. Skip if there's nothing to improve.
- Repeat — next item, until the list is empty.
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.
- 12d ago First seen · 97 lines · 68 tokens per session scan A 665053eab462
canon-tdd is a skill published in the GitHub repository adamayoung/TMDb (176 stars, last pushed 12d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,247 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
ax-testing
Skill "ax-testing" from Kasempiternal/axiom-v2, covering testing, quick patterns, swift testing basics, suites and traits and parameterized tests.
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.