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 smartfrog/opencode-froggy --skill tddgit clone --depth 1 https://github.com/smartfrog/opencode-froggyWrote 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/smartfrog/opencode-froggy/tdd)<a href="https://agentmods.dev/skills/smartfrog/opencode-froggy/tdd"><img src="https://agentmods.dev/badge/skills/smartfrog/opencode-froggy/tdd/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/smartfrog/opencode-froggy/tdd"><img src="https://agentmods.dev/badge/skills/smartfrog/opencode-froggy/tdd.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 | $0.00017 | $0.00385 |
| Opus 5.5 | $0.00007 | $0.00154 |
| Sonnet 5.5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
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 14d 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.
What it actually says
Test-Driven Development
Use short test/code/refactor loops. Test-first is the default for features and bugfixes. When another form of verification is more appropriate, explain why and report the alternative check and its result; choose meaningful verification over formal compliance.
Workflow
- Pick an observable behavior from the acceptance criteria. For a bug, reproduce the failure with a focused test or another reliable check.
- Before implementation, write or update a behavioral test, run it, and confirm the failure comes from the missing or incorrect behavior, not a broken fixture or environment.
- Implement the simplest correct change, run the relevant checks, and refactor only where useful. Keep the loop with the implementer rather than splitting test, code, and refactor across workers.
- Repeat as needed, then run the project's required checks. Report actual commands, results, and meaningful verification gaps. Never claim a red/green cycle or a passing check that did not happen.
Adapt verification to the change
- Test observable behavior and regressions, not implementation details. Prefer deterministic, readable tests; reuse existing coverage when it already proves the behavior.
- Use unit tests for isolated logic, integration or contract checks for boundaries, and end-to-end checks for critical journeys where useful.
- For refactoring, rely on existing behavior tests and add characterization coverage when needed. For documentation or small reversible low-impact changes, use direct checks rather than artificial tests.
- For UI work, visual or interaction checks may be more useful than unit tests. For exploratory work, report findings and limitations before treating it as production-ready.
- If an environment or test setup is unavailable, investigate or use an appropriate alternative check and state the remaining uncertainty. Keep independently verifiable work moving; track material verification debt when it remains.
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.
- 14d ago Changed · -25 lines 9e23d0a23498
- 26d ago Changed · +4 lines df8fc49a08f3
- 1mo ago First seen · 45 lines · 17 tokens per session scan A 773800a6e3ee
tdd is a skill published in the GitHub repository smartfrog/opencode-froggy (109 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 385 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.