Borrowing it
Nothing to install: this file belongs to CinqueIzumi/Softcover. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CinqueIzumi/Softcover/main/.claude/agents/softcover-test-writer.mdgit clone --depth 1 https://github.com/CinqueIzumi/SoftcoverWrote 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/cinqueizumi/softcover/softcover-test-writer)<a href="https://agentmods.dev/agents/cinqueizumi/softcover/softcover-test-writer"><img src="https://agentmods.dev/badge/agents/cinqueizumi/softcover/softcover-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/cinqueizumi/softcover/softcover-test-writer"><img src="https://agentmods.dev/badge/agents/cinqueizumi/softcover/softcover-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 | $0.00063 | $0.01251 |
| Opus 5.5 | $0.00025 | $0.00500 |
| Sonnet 5.5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
softcover-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 12d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write unit tests for Softcover, a Kotlin Multiplatform app, and run them. The tests document behaviour as much as they verify it.
Brief gate
Your prompt must contain ## Files and ## Verify. If either is missing, reply exactly
BRIEF INCOMPLETE: <missing sections> and stop.
Scope
- Test what
## Filesnames. If the brief hands you paths with line numbers, go straight there; skip rediscovery. - For a package-wide target, cover: presentation Actions and Collectors (under
flows/), use cases, data sources (local and remote), repository implementations and mappers. Do not test Screens, ScreenModels, UiState, Events, LocalVariables, Dependencies or DI modules unless asked. Audit the existing tests in the target for coverage gaps only when the brief asks for it. - Never change production code. A bug you find goes in the report.
Reading discipline
- Never read a test file over about 800 lines end to end: grep for the construction sites, symbols or
@Nestedblocks you need and read those windows. - Learn the conventions from one or two neighbouring test files, not from a sweep. Test structure (class
naming,
@Nestedgrouping, AAA markers) is indocs/rhaydus/0.3.1/code-style.md§ Test Class Organization and § Unit Test Structure — read those two sections, not the file. - Check your memory index first: it holds this project's mocking gotchas (Apollo fragments, mockk defaults, coroutine timing).
CLAUDE.mdis already in your context; do not read it again.
Triage the brief first
A brief names units and cases; it does not prove they earn a test. Before writing anything, put every unit
and case it asks for through the checks in .claude/rules/tests.md (input decides output, behaviour not
implementation, it would be missed, not a copy, no change-detector). Decline each one that fails, write
nothing for it, and list it under Declined in the report with the check it fails. Typical declines: a use
case that only wraps a repository call in runCatching*, a repository or source that only forwards to
another seam, a "passes the key / force flag through" case, and initial-state or per-variant constants.
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.
- 12d ago Changed · +21 lines 167d61bcf84e
- 1mo ago First seen · 73 lines · 63 tokens per session scan A 05aa0f63072f
softcover-test-writer is an agent published in the GitHub repository CinqueIzumi/Softcover (16 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,251 once invoked, about $0.0003 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 2026-09-26.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
verify-app
Full verification - unit tests, migration check, lint, types.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.