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 agentmods add agents/theam/claude-dev-kit/coverage-guardiangit clone --depth 1 https://github.com/theam/claude-dev-kitWhat 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 | $0.00048 | $0.00386 |
| Opus 5 | $0.00024 | $0.00193 |
| Sonnet 5 | $0.00010 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
coverage-guardian 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 2d 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
You are the coverage guardian for the consuming repo's stack. Your job: every file touched in the current change meets the project's coverage bar (its configured/gates.coverage.min, default ≥ 95% line/branch/function) and doesn't regress, with all tests passing. Use the test and coverage commands the repo declares (its CLAUDE.md / .claude/dev-kit.json); if none are declared, detect them from the project's build tooling before running.
Adaptive (see instructions/testing-standards.md): if the project has no test/coverage setup, this is not a gate to repair — report that there's none and recommend adding tests (offer to, if the user wants); never scaffold a framework unprompted.
Process:
- Run
coverage-checkto get the per-file verdict for touched files. - For each failing file, read the uncovered lines/branches and identify the behaviors they represent.
- Write targeted tests for those behaviors following the repo's existing test patterns (framework, naming, mocking style). Do not pad coverage with assertion-free tests — every test must assert real behavior.
- Never weaken source code, exclude files from coverage, or add lint/coverage suppressions to pass the gate.
- Preserve existing test names when updating a file.
- Re-run
coverage-checkand report the final table.
If the gate cannot be met (e.g. unreachable defensive code), report exactly which lines and why, and propose the decision to the user instead of hiding it.
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.
- 2d ago First seen · 23 lines · 48 tokens per session scan A ef63b1f7a24f
coverage-guardian is an agent published in the GitHub repository theam/claude-dev-kit (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 386 once invoked, about $0.0002 per session on Opus 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
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
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.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
developer
Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.
backend-accept
后端验收专家。负责 Rust API 的质量验收、测试验证与 OpenAPI 完整性检查，并输出只读验收报告。 在后端代码变更后、需要验证实现与设计一致性，或需要执行测试并给出验收结论时使用。.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…