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 agentmods add skills/t1/tdder/tddnpx skills add t1/tdder --skill tddgit clone --depth 1 https://github.com/t1/tdderWhat 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 | $0.00102 | $0.01411 |
| Opus 5 | $0.00051 | $0.00705 |
| Sonnet 5 | $0.00020 | $0.00282 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
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 3d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development (TDD)
Strict Red-Green-Refactor discipline for adding features and fixing bugs. This skill is language-agnostic; language-specific conventions are provided by separate skills.
Core Process
1. Test List First
Create a list of test cases for base functionality only before writing any implementation.
Use the language's equivalent of pending/todo tests (e.g., it.todo(), @Disabled, @Ignore).
Focus on core functionality, not advanced features.
2. Test List Approval
After creating the test list, present it as markdown.
Then, if the human-in-the-loop is not off, use AskUserQuestion:
- Question: "Want to adjust the test list before we start?"
- Options:
- "Looks good, start" — proceed with the first test
- "Add more tests" — wait for the user to specify additional tests
3. One Test at a Time
Convert exactly one pending test to executable test code at a time. All other tests remain as pending descriptions. Never have more than one failing test in the red phase. Implement only what is needed to make that single test pass. Do not think ahead or implement features for future tests.
4. Red-Green-Refactor Cycle
Red Phase (Compilation Error)
- Write the test referencing a non-existent function/class.
- Predict: "This will fail with a compilation error on
<symbol>." - Run — confirm compilation error, compare with prediction.
Red Phase (Runtime Error)
- Create an empty function/class returning a wrong value.
- Predict: "This will fail with an assertion error — expected
<X>, got<Y>." - Run — confirm assertion error, compare with prediction.
Green Phase
- Predict: "This will pass after I implement
<X>." - Implement minimal code to make the test pass. Do not add features for future tests. Do not optimize or refactor yet.
- Run — confirm green, compare with prediction.
Refactor Phase
Must attempt at least one refactoring. If no improvement is possible, document why.
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.
- 3d ago First seen · 171 lines · 102 tokens per session scan A 7538bba89068
tdd is a skill published in the GitHub repository t1/tdder (14 stars, last pushed 3d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,411 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 2026-08-30.
Other skills, from other repositories
develop-tdd
Test-driven development with red-green-refactor loop using vertical slices. Use for features (epic tasks) or bugs (specs/bugs/BUG-.md).
tdd-arrange-act-assert
This skill should be used when the user asks to "structure tests", "organize test code", mentions "arrange act assert", "AAA pattern", "given when then", discusses test readability, or wants to improve test structure.
tdd-red-green-refactor
This skill should be used when the user asks to "do TDD", "write tests first", mentions "red-green-refactor", discusses test-driven development cycles, or wants to build features incrementally with tests.
tdd-test-first
This skill should be used when the user asks to "write tests first", "start with a test", mentions "test-first development", discusses writing tests before implementation, or wants to ensure code is testable by design.
delphi-tdd-and-quality
Desenvolvimento Orientado a Testes (TDD), escrita de testes unitários DUnitX e correções de bugs no Delphi.
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…