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 fmind/dotfiles --skill test-driven-developmentgit clone --depth 1 https://github.com/fmind/dotfilesWrote 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/fmind/dotfiles/test-driven-development)<a href="https://agentmods.dev/skills/fmind/dotfiles/test-driven-development"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/test-driven-development/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/fmind/dotfiles/test-driven-development"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/test-driven-development.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 | $0.00046 | $0.00978 |
| Opus 5.5 | $0.00018 | $0.00391 |
| Sonnet 5.5 | $0.00009 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
test-driven-development 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development
Use a failing test to prove the test can detect the missing or broken behavior, then write the smallest trustworthy change.
Pragmatic Contract
- Test observable behavior and contracts, not private implementation or mock choreography.
- Scale the test level to risk. Prefer fast unit or contract tests; add integration, property, concurrency, or browser tests where the boundary demands them.
- For legacy code, first write a characterization or regression test around the behavior being changed.
- For a throwaway spike, generated code, or configuration-only change, state why test-first is inappropriate and define another failing validation signal. Do not silently call tests written afterward TDD.
- Never delete or overwrite user work merely because implementation preceded the test. Preserve it, establish a red-capable test, and disclose the sequence honestly.
- Never weaken an existing test, loosen a type, add a skip, or mock away the defect to manufacture green.
Cycle
- Discover the harness: Read repository instructions, existing tests, task definitions, and nearby patterns. Identify the smallest command that exercises the target behavior.
- State the contract: Name the production change that would make the test pass and a plausible regression that would make it fail.
- RED: Write one minimal test for one behavior. Run it and confirm it fails for the expected missing behavior, not a syntax, fixture, environment, or setup error.
- GREEN: Implement only enough production code to satisfy that test. Run the focused test and read the full output.
- Protect the neighborhood: Run the relevant package or subsystem tests. Fix production code when the new behavior breaks an existing valid contract; revisit the spec if contracts conflict.
- REFACTOR: Improve names, structure, duplication, and types only while all tests remain green. Do not add new behavior during refactoring.
- Repeat: Add the next smallest behavior, edge case, or failure path through a new red cycle.
- Prove the regression test: For a bug fix, temporarily reverse or bypass the fix when safe and confirm the regression test fails, then restore the fix and confirm green.
- Protect unrelated work: Before any full gate, inspect the full gate's task definition and working-tree state. If it runs whole-tree write-formatters and unrelated or user changes are present, validate the exact candidate in an isolated temporary worktree or run equivalent non-mutating checks; never reformat unrelated work.
- Run the full gate: Execute the repository-owned format, check, test, and build contract, normally
mise run all, warning-free.
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.
- 1mo ago First seen · 56 lines · 46 tokens per session scan A 25ea6b49e346
test-driven-development is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 978 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
python-testing
Write Python tests with pytest, fixtures, property tests, and TDD.
airflow
Develop and test Airflow DAGs with the Astronomer astro CLI.
smoke
Smoke-test every repo task and CLI command; warnings count as failures.
quality-assurance
Plan and run QA test campaigns over user journeys, failure modes, and release risks.
playwright
Automate browsers and E2E tests with Python Playwright: screenshots, traces.
cli-development
Design and build Python CLIs with Typer: commands, output contracts, and tests.