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 loiane/specs-driven-development-spring-angular --skill tdd-red-green-refactorgit clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angularWrote 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/loiane/specs-driven-development-spring-angular/tdd-red-green-refactor)<a href="https://agentmods.dev/skills/loiane/specs-driven-development-spring-angular/tdd-red-green-refactor"><img src="https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/tdd-red-green-refactor/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/loiane/specs-driven-development-spring-angular/tdd-red-green-refactor"><img src="https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/tdd-red-green-refactor.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 | $0.00056 | $0.01670 |
| Opus 5.5 | $0.00022 | $0.00668 |
| Sonnet 5.5 | $0.00011 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
tdd-red-green-refactor 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD: red / green / refactor / simplify
The four phases (per task)
1. RED — write a failing test
-
Read the task entry in
04-tasks.md. ConfirmTest-IDsandAC-IDs. -
Write the smallest possible test that asserts the behavior described by the AC.
- Annotation block on every
@Testmethod is non-negotiable:@Test→@Tag("AC-NNN")→@DisplayName("..."). Write the@DisplayNamebefore the test body — the act of articulating the display name forces clarity about what the test verifies. Format for AC-traced tests:"<T-ID>: given <precondition>, when <action>, then <outcome>". Short BDD-style sentence is acceptable for utility/regression tests not tied to a specific AC. (Project rule:feedback_displayname_on_every_test.md.)
- Annotation block on every
-
Run only that test (
mvn -Dtest=ClassName#method test). -
The test must fail, and the failure must be for the right reason (the asserted behavior is missing, not a typo or compilation error).
-
Append a
redblock to05-implementation-log.mdwith the failing command and the first 10 lines of the failure output. -
Update
.specs/<id>/.tdd-state.json:{ "active_task": "T-001", "tasks": { "T-001": { "phase": "red", "red_at": "2026-04-18T10:00:00Z", "red_test_signature": "...", "red_failure_excerpt": "..." } } }
The block-impl-without-failing-test hook reads this file. No src/main/** edit is allowed unless phase == red and red_failure_excerpt is non-empty.
2. GREEN — minimum production code
- Edit only files in the task's
Files in scope. The hook enforces this. - Write the minimum code to make the failing test pass. No speculative features. No "while I'm here" cleanups.
- Re-run the test (
mvn -Dtest=...). It must pass. - Run the module's full Surefire suite to ensure no regression (
mvn -q test -pl <module>). - Append a
greenblock to05-implementation-log.md. - Set
.tdd-state.jsonphasetogreen.
3. REFACTOR — improve internals, hold behavior
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 · 114 lines · 56 tokens per session scan A 7ba01eca068f
tdd-red-green-refactor is a skill published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 9d ago), licensed MIT. It adds 56 tokens to every session and 1,670 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 2026-08-30.
Other skills, from other repositories
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
kiro-impl
Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
112-java-maven-plugins
Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) …
tdd
Test-driven development with red-green-refactor loops around vertical slices (tracer bullets), not horizontal layers. Use when asked to "use TDD", "write test-first", "red-green-refactor", "build this with tests", or when a feature has a clear observable contract. The discipline complement to the test/add-tests skills…
JUnit 5 Testing
Production-grade Java unit and integration testing with JUnit 5 covering assertions, parameterized tests, lifecycle hooks, Mockito mocking, nested tests, and extensions.