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 transparent-pegasus/herdrpowers --skill test-driven-developmentgit clone --depth 1 https://github.com/transparent-pegasus/herdrpowersWrote 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/transparent-pegasus/herdrpowers/test-driven-development)<a href="https://agentmods.dev/skills/transparent-pegasus/herdrpowers/test-driven-development"><img src="https://agentmods.dev/badge/skills/transparent-pegasus/herdrpowers/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/transparent-pegasus/herdrpowers/test-driven-development"><img src="https://agentmods.dev/badge/skills/transparent-pegasus/herdrpowers/test-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.03016 |
| Opus 5.5 | $0.00007 | $0.01206 |
| Sonnet 5.5 | $0.00003 | $0.00603 |
| Haiku 4.5 | $0.00002 | $0.00302 |
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 11d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development (TDD)
Who Writes the Test (READ FIRST)
The resolved test-authoring assignment says — read it (see orchestration), do not assume. Two shapes ship, and they bind different rules.
A separate pane writes them (mode: delegate). That pane works from the task brief alone, in a worktree at the commit before the implementation, and is never shown the implementation — so its assertions cannot be shaped by code it read. If you are that pane, pane-driven-development's test author brief binds you: tests only, never production code, and a test that passes in that worktree is a defect to investigate and report. If you are the implementing pane, you implement the brief's stated interface exactly — someone else's assertions are already written against it — and you do not write the tests.
The implementing pane writes them (mode: implementer). The delegation brief that hands you a task also hands you its tests. That removes the structural guard against grading your own homework, so two compensating rules bind instead:
- Assertions come from the requirements, never from the code. Write the test against the task brief's stated behavior and exact values, before the implementation exists. A test written after the code, shaped to match it, catches nothing.
- The RED run is evidence you must produce. Your report carries the failing command and its output before implementation, with the reason the failure was expected, plus the passing run after. The reviewing panes treat missing or reconstructed RED evidence as a finding, and review your test code as the only independent check on it.
Either shape: whoever writes a test produces its RED run, assertions trace to the requirements, and the report names which pane wrote the tests. fix-round-test-authoring answers the same question for a fix round's covering tests. The Iron Law below binds whichever pane owns them: no production code without a failing test first.
Where Tests Go and How to Run Them
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.
- 11d ago Changed · +9 lines bba0776edfce
- 1mo ago First seen · 348 lines · 17 tokens per session scan A fcd496bfe507
test-driven-development is a skill published in the GitHub repository transparent-pegasus/herdrpowers (12 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 3,016 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
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…
test-driven-development
Writing code with tests first: RED-GREEN-REFACTOR, reproduce bugs as failing tests before fixing, and avoid testing anti-patterns. Use when implementing behaviour, fixing a defect, or asked to add tests.
rudder
Use locally captured coding-session intent to resolve a device-local behavioral spec, generate focused tests from that spec, implement the smallest production changes through red-green TDD, and verify coverage with the repository's native tooling. Use when the user asks to run Rudder, create or regenerate tests for…
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
tdd
Add new behavior test-first (write failing test → make it pass → refactor). Use when asked to "add a test for", "implement X with tests", or extending a codebase that already has a test suite.