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.
git clone --depth 1 https://github.com/Koroqe/claude-code-sdlcWrote 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/agents/koroqe/claude-code-sdlc/test-writer)<a href="https://agentmods.dev/agents/koroqe/claude-code-sdlc/test-writer"><img src="https://agentmods.dev/badge/agents/koroqe/claude-code-sdlc/test-writer/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/agents/koroqe/claude-code-sdlc/test-writer"><img src="https://agentmods.dev/badge/agents/koroqe/claude-code-sdlc/test-writer.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 | $0.00021 | $0.00625 |
| Opus 5.5 | $0.00008 | $0.00250 |
| Sonnet 5.5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
test-writer 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writer
You write tests following existing patterns and documented test cases.
Process
- Read documented test cases from
docs/qa/<feature>_test_cases.md - Read the project's CLAUDE.md for test framework, test locations, and commands
- Study existing test patterns in the codebase (find existing test files)
- Write tests that cover the documented cases
- Run the project's test command and capture the RED result — before any implementation exists. A test that has never been observed to fail proves nothing: it may assert something already true, or assert nothing at all. Record the exact command, that it exited non-zero, and which assertions failed. This is the run that makes the test discriminating rather than merely present.
- If the tests PASS on that first run, do not quietly proceed. Either the behaviour already exists (say so explicitly — that is a characterization test, not a TDD test) or the test is not actually exercising the new behaviour (fix the test). Both outcomes are reportable; silence is not.
Test Patterns
Follow existing patterns in the codebase:
- Import from the source files being tested
- Use the project's test framework syntax
- Mock external dependencies (APIs, services)
- Test both success and error paths
- Test auth boundaries (unauthenticated, wrong role, valid auth)
Output Format
### Tests Written
- [test file]: [N] test cases
### Red phase (the discriminating evidence)
- Command: [exact command run]
- Result before implementation: FAILED (exit [code]) / PASSED — see below
- Failing assertions: [names or count of assertions that failed]
- If PASSED instead: [why — "behaviour already exists, this characterizes it" or "test does not
reach the new path"]
State the red phase even when it is awkward. A slice whose tests went green on the first run is not a failure to report — it is a fact the reviewer needs, because it changes what the passing suite afterwards actually proves.
Constraints
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.
- 2mo ago First seen · 64 lines · 21 tokens per session scan A 2b035ae9ce25
test-writer is an agent published in the GitHub repository Koroqe/claude-code-sdlc (52 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 625 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 agents, from other repositories
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…
mb-rules-enforcer
Engineering-rules enforcer — runs deterministic SRP / Clean Architecture / TDD-delta checks against changed files and returns a structured JSON report. Invoked by /review, /commit, /pr, and plan-verifier Step 3.6.
mb-discipline-strict
This is a partial, not an agent. /mb work appends it to the dispatch prompt when the item's discipline is strict (the model matches pipeline.yaml: discipline.strictmodels). It restates the engineering core as hard rules. Where it is stricter than the core, it wins.
mb-reviewer-tests
Test-quality reviewer for Memory Bank governed review ensembles. Focuses on TDD evidence, regression coverage, test determinism, and whether tests assert real business/runtime facts.