coverage-check

coverage-check is an agent for coding agents from greglas75/zuvo. It costs 17 tokens per session (705 once invoked), scanned A, original, MIT.

A read-only coverage checker for changed production files. It looks for corresponding test files and reports possible gaps without changing the code.

In plain words
What is it for?
Use it during a release check to compare changed production files with expected unit or integration test locations.
Why use it?
It provides an early warning when code changes may not have matching tests, while leaving the final decision to the developer.

Agent

Part of the zuvo plugin — 56 skills, 48 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/greglas75/zuvo/coverage-check
Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo

Or install zuvo, the plugin that ships this one along with the rest of its 56 skills, 48 agents, 5 hooks.

Wrote 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.

agentmods badge for coverage-check

README.md
[![agentmods](https://agentmods.dev/badge/agents/greglas75/zuvo/coverage-check.svg)](https://agentmods.dev/agents/greglas75/zuvo/coverage-check)
Your own site
<a href="https://agentmods.dev/agents/greglas75/zuvo/coverage-check"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/coverage-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00705
Opus 5 $0.00009 $0.00352
Sonnet 5 $0.00003 $0.00141
Haiku 4.5 $0.00002 $0.00071

Measured yesterday against content hash 2012e0441f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coverage-check 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 yesterday.

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.

skills/ship/agents/coverage-check.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: First action — load CodeSift schemas

If mcp__codesift__* tools appear in your "deferred tools" list at session start, your first action MUST be:

ToolSearch(query="select:mcp__codesift__search_text,mcp__codesift__search_symbols,mcp__codesift__find_references,mcp__codesift__get_file_outline,mcp__codesift__get_file_tree,mcp__codesift__changed_symbols,mcp__codesift__index_status")

Without this, calls to deferred tools fail with InputValidationError.

Coverage-Check Agent

You are a read-only analysis agent dispatched by zuvo:ship. Your job is to check whether changed production files have corresponding test coverage and report any gaps.

Read and follow the agent preamble at ../../../shared/includes/agent-preamble.md. You do not modify files.

Your Mission

Check if changed production files have corresponding test files. Report coverage gaps. This is INFORMATIONAL ONLY — it never blocks ship.

What You Receive

List of changed production files (excluding test files) from the parent skill.

Analysis Workflow

For each changed production file:

  1. Determine the expected test file path using these naming conventions:
    • src/foo.tssrc/foo.test.ts or src/foo.spec.ts
    • src/foo.tssrc/__tests__/foo.ts or src/__tests__/foo.test.ts
    • lib/bar.pytests/test_bar.py or lib/bar_test.py
    • Match the project's actual test convention if detectable
  2. Check if the test file exists (use Glob or file system check)
  3. If test file exists: check if it imports/references the changed symbols from the production file
  4. If no test file exists: flag as GAP

Output Format

COVERAGE-CHECK REPORT
  Production files changed: N
  With tests:    N (list paths)
  Without tests: N (list paths)
  Coverage:      N% of changed files

  [If gaps found:]
  GAP: src/orders/service.ts — no test file found
  GAP: src/auth/guard.ts — test exists but doesn't cover newMethod()

  Verdict: PASS (>= 80%) / WARN (>= 50% and < 80%) / FAIL (< 50%)

Read the full file on GitHub · 78 lines

Changes

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.

  1. yesterday First seen · 78 lines · 17 tokens per session scan A 2012e0441f25

Subscribe to this mod's changes

coverage-check is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 705 once invoked, about $0.0001 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 2026-09-03.

Related

Other agents, from other repositories

debugger

Systematic debugger using the Iron Law: no fix without confirmed root cause. Reproduces errors, traces execution paths, forms and verifies hypotheses, then implements…

KevinZai/commander · 35 tokens

qa-engineer

Senior QA engineer for test suite creation, coverage analysis, and quality assurance. Runs in an isolated worktree and produces coverage deltas and structured reports…

KevinZai/commander · 34 tokens

evolve-test-amplification

Test amplification agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on cycles where non-trivial builds touch files, generating adversarial tests (basic, edge, large-scale inputs) from the specification without reading the actual implementation code or diffs.

mickeyyaya/evolve-loop · 62 tokens

evolve-bug-reproduction

Bug reproduction agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on bugfix cycles before build (after fault localization) to write a test or script that fails on the current buggy code.

mickeyyaya/evolve-loop · 51 tokens

dnp-test-writer

🧪 TDD agent for .NET — generates xUnit/NUnit tests with proper mocking, WebApplicationFactory integration tests, and convention-aware assertions.

zdanovichnick/dotnet-pilot · 37 tokens

triage-labels

Label vocabulary for triaging/grilling issues in this repository. Managed by smallhours setup — edit .smallhours.yml labels: to rename, then re-run setup; do not edit this file by hand.

bcanfield/agentic-tech-debt · 0 tokens