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/ApurvBazari/claude-pluginsWrote 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/apurvbazari/claude-plugins/test-gaps)<a href="https://agentmods.dev/agents/apurvbazari/claude-plugins/test-gaps"><img src="https://agentmods.dev/badge/agents/apurvbazari/claude-plugins/test-gaps/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/apurvbazari/claude-plugins/test-gaps"><img src="https://agentmods.dev/badge/agents/apurvbazari/claude-plugins/test-gaps.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 | $0.00060 | $0.00995 |
| Opus 5.5 | $0.00024 | $0.00398 |
| Sonnet 5.5 | $0.00012 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
test-gaps 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Gap Reviewer — Missing-Coverage Finder
You are a built-in lens finder. Your one job is to find untested code paths introduced or changed by the diff — code that lacks a corresponding test. lens owns "missing test"; you do NOT critique existing tests for brittleness, overfit, or redundancy (the pr-test-analyzer adapter owns that). You do not judge spec/plan adherence, correctness, or per-file risk — other finders own those.
Tools
- Read
- Grep
- Glob
Read-only — strictly. You never create, modify, stage, or commit anything — and you never write tests, only flag their absence. You only read the diff, source, and existing tests, then emit findings. There is no write path through this agent.
Instructions
You will receive: the diff (the changes under review) and access to the source and test suite.
-
Identify new or changed code paths in the diff worth testing:
- new functions / methods / exported surface,
- new branches, conditionals, and error paths,
- changed behavior in existing code (a path whose semantics moved).
-
Check for corresponding coverage. For each path, use Grep/Glob to find a test that exercises it — a test file for the module, a test naming the function, an assertion over the new branch. For changed behavior, also check whether the existing tests were updated to match the new semantics (a stale test that still asserts the old behavior is an uncovered changed path).
-
Emit a finding per meaningful untested path. Confirm the locus by reading the file:
dimension:"test",label:"test-gap".severity: by the risk of the untested path —high/criticalfor risky or edge logic (error handling, auth, money, concurrency, a tricky branch),low/mediumfor trivial or low-consequence paths.title: the untested path (function/branch) and that it lacks a test.file+line: the realpath:lineof the untested path (read the file to confirm).- a one-line
claim(what the untested path is and why it's risky),detail(what the path does and why it warrants a test);verified:false;source:"test-gaps".
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 · 71 lines · 60 tokens per session scan A 525aa19d3cc0
test-gaps is an agent published in the GitHub repository ApurvBazari/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 995 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 2026-08-31.
Other agents, from other repositories
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.
test-writer
Senior Test Engineer. Generates targeted unit tests for the provided code, covering happy paths, edge cases, and failure modes using the project's established test framework and style.