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/genai-io/san/tddnpx skills add genai-io/san --skill tddgit clone --depth 1 https://github.com/genai-io/sanWrote 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/genai-io/san/tdd)<a href="https://agentmods.dev/skills/genai-io/san/tdd"><img src="https://agentmods.dev/badge/skills/genai-io/san/tdd.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.00634 |
| Opus 5 | $0.00036 | $0.00317 |
| Sonnet 5 | $0.00015 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00063 |
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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD: red, green, refactor
Write the test before the code. A test written first specifies the behavior, fails for a known reason, and gives you a definition of done you can run. A test written after tends to describe whatever the code happens to do — bugs included.
Step 1: Find the test runner
Don't assume the command. Detect how this project runs and writes tests: look at
existing test files for the framework and conventions, and at the build/config
for the invocation (go test ./..., npm test, pytest, cargo test, …).
Match what's already there — same framework, same layout, same style.
Step 2: Name the behavior as tests (RED)
State the change as concrete cases before writing any implementation:
- The main success path — the behavior actually requested.
- The edges — empty, zero, boundary, maximum, unexpected input.
- The failures — what should error, and how it should error.
Write these as tests. For a bug fix, the first test reproduces the bug. Keep each test focused on one behavior with a clear name.
Step 3: Watch them fail
Run the tests and confirm they fail — and fail for the right reason (the behavior is missing), not a typo or an import error. A test you never saw fail proves nothing. This is the gate: do not write implementation until you've seen red.
Step 4: Implement to green
Write the minimum code that makes the tests pass. No features the tests don't demand, no speculative abstraction. Run the tests until they're green.
Step 5: Refactor on green
Now improve the shape — naming, duplication, structure — with the tests staying green the whole way. The tests let you clean up without fear; if one goes red, the last change altered behavior, so undo it.
Test what callers see, not how it's built
- Assert on observable behavior and return values, not private internals — tests bound to implementation break on every refactor and defeat Step 5.
- Keep tests isolated: no shared mutable state, no ordering dependency, each runs alone. Prefer real behavior; mock only what you can't run (network, clock, external services).
- Cover the edges and error paths, not just the happy case — that's where the bugs the persona is trying to prevent actually live.
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.
- 6d ago First seen · 69 lines · 73 tokens per session scan A 949f986e0619
tdd is a skill published in the GitHub repository genai-io/san (76 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 634 once invoked, about $0.0004 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
tdd
Test-driven development — write the failing test first, then the code. Triggers on TDD, test first, write tests, test-driven.
sesion
Ejecuta la sesión de implementación que marca el puntero ▶ de docs/plan/estado.md con el ciclo BDD→TDD→juicio→DoD, y cierra moviendo puntero y worklog en el mismo commit. Úsala cuando la tarea sea construir (no diseñar) y exista una sesión abierta en el plan; si la feature no está en el plan, antes va…
agent-builder
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
code-review
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
mcp-builder
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.