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 commands/vrennat/developersdevelopers/tddgit clone --depth 1 https://github.com/vrennat/developersDevelopersWhat 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 | $0.00031 | $0.00362 |
| Opus 5 | $0.00015 | $0.00181 |
| Sonnet 5 | $0.00006 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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 yesterday.
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.
What it actually says
/tdd
Test-driven development loop. RED -> GREEN -> REFACTOR.
Opt-in only. The plugin does NOT auto-enforce TDD on every implementation. Use this when you want the discipline.
Procedure
- SCAFFOLD: define the interface. Types, function signature, throw
Not implemented. Commit. - RED: write the failing test(s). Cover happy path, edge cases (empty/null/max), error conditions. Run tests; verify they FAIL for the right reason.
- GREEN: write the minimum code to pass. No gold-plating. Run tests; verify PASS.
- REFACTOR: improve naming, extract helpers, reduce complexity. Run tests after each change; must stay green.
- REPEAT: next behavior or scenario, back to RED.
Commit after each phase that produces working state (after GREEN, after REFACTOR). Don't commit RED — the test is failing.
Rules
- Test FIRST. No exceptions in this command.
- Verify the test fails before implementing. A test that "passes" before you implement is testing the wrong thing.
- Refactor only when green. Tests are your safety net.
- Test behavior, not implementation. Don't mock everything; prefer integration tests where reasonable.
When NOT to use
- Quick spike or throwaway script: just write it.
- Exploring a library: write a scratch file, no tests needed.
- Bug fix where reproduction is the test: regression test then fix is fine, but you don't need the full RED-GREEN-REFACTOR ceremony.
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.
- yesterday First seen · 34 lines · 31 tokens per session scan A 755391d1dfe6
tdd is a command published in the GitHub repository vrennat/developersDevelopers (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 362 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.