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 damianvtran/local-operator --skill test-driven-developmentgit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/test-driven-development)<a href="https://agentmods.dev/skills/damianvtran/local-operator/test-driven-development"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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/damianvtran/local-operator/test-driven-development"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/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 | $0.00048 | $0.00598 |
| Opus 5.5 | $0.00019 | $0.00239 |
| Sonnet 5.5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
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 5d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-driven development
Iron law: no production code without a failing test that demands it.
The cycle
- RED: write the smallest test for the next bit of behaviour. Run it. Read the failure and confirm it fails for the reason you intended (your assertion), not an import error, a typo, or a missing fixture. A test that fails for the wrong reason proves nothing.
- GREEN: write the least production code that passes. Run the test again. Nothing more than the test asks for.
- REFACTOR: improve names and structure while all tests stay green. Run them again.
Then the next slice. Cycles are minutes, not hours; commit-sized.
Bugs: reproduce first
- Turn the bug into a failing test before touching the fix. Watch it fail, fix, watch it pass.
- If you cannot express the bug as a failing test, you do not understand it yet; switch to
skill://systematic-debugging. - Keep the repro test after the fix as the regression test. A bug fix without a test that dies when the bug returns is incomplete.
Already wrote the code? Delete it
Code written before its tests is untrusted: nothing was ever observed failing, and its behaviour was never pinned. Delete and re-derive from the tests. Adapting pre-test code to pass tests keeps the untested behaviour hidden inside.
Exception: throwaway exploration deleted before the work starts. Spikes inform; they do not ship.
Anti-patterns
| Anti-pattern | Why it fails | Instead |
|---|---|---|
| Mock-heavy tests that assert on the mock | Tests the mock; passes while the real component is broken | Prefer the real object; fake only at system boundaries; assert the outcome |
| Assertion-free tests ("it runs") | Passes always; proves nothing | Assert the observable outcome |
| Implementation-detail tests (private calls, call order) | Break on any refactor; resist change | Test behaviour through the public seam |
| Coverage chasing | Volume without discrimination | One test per behaviour and per edge |
| Tests written after, never seen red | Cannot distinguish a test from a tautology | Run new tests before the code; confirm red |
| Skipped or xfailed tests left behind | Silent coverage hole | Fix or delete; never skip quietly |
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.
- 5d ago First seen · 47 lines · 48 tokens per session scan A 516707d441ae
test-driven-development is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 598 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 2026-10-11.
Other skills, from other repositories
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
test-writing
Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
implement
Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…