TMDb: Skill for Claude Code

.claude/skills/canon-tdd/SKILL.md

canon-tdd is a skill for Claude Code from adamayoung/TMDb. It costs 68 tokens per session (1,247 once invoked), scanned A, original, Apache-2.0.

A test-driven development guide based on Kent Beck's approach. Test-driven development means writing a test that fails, making it pass with code, then improving the code while keeping the test passing.

In plain words
What is it for?
It is for adding features, endpoints, data models, or methods, fixing bugs, and carrying out development plans one tested behaviour at a time.
Why use it?
It prevents implementation from getting ahead of the intended behaviour and makes the required cases and edge cases explicit.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is adamayoung/TMDb's own configuration. It tells Claude Code how to work on TMDb itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TMDb configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/adamayoung/TMDb/main/.claude/skills/canon-tdd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/adamayoung/TMDb

Made for: Claude Code.

Wrote 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.

agentmods badge for canon-tdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamayoung/tmdb/canon-tdd/github.svg)](https://agentmods.dev/skills/adamayoung/tmdb/canon-tdd)
Your own site
<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.

agentmods 80×15 button for canon-tdd

Your own site · 80×15
<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>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 665053eab462, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

.claude/skills/canon-tdd/SKILL.md · 97 lines

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.

  1. 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".
  2. 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.
  3. 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.
  4. Refactor only on green, and keep refactoring out of the make-it-pass step.
  5. Repeat until the test list is empty, adding newly-discovered cases to the list as you go.

The five steps

  1. 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.
  2. 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.
  3. 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.
  4. Optionally refactor — improve names, structure, and duplication while every test stays green. Skip if there's nothing to improve.
  5. Repeat — next item, until the list is empty.

Read the full file on GitHub · 97 lines

Changes

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.

  1. 12d ago First seen · 97 lines · 68 tokens per session scan A 665053eab462

Subscribe to this mod's changes

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.