What is blind-coverage-auditor?

A read-only reviewer that first maps the behavior in production code and then checks which parts the tests cover.

Use it before or during test review to identify uncovered branches, errors, fallbacks, side effects, callbacks, and accessibility output.

It finds missing tests and tests that only exercise structure without proving the behavior works.

blind-coverage-auditor — Agent for Claude Code by greglas75

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.

Clone the repo

git clone --depth 1 https://github.com/greglas75/zuvo

Made for: Claude Code.

Or install zuvo, the plugin that ships this one along with the rest of its 56 skills, 47 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/greglas75/zuvo/blind-coverage-auditor.svg)](https://agentmods.dev/agents/greglas75/zuvo/blind-coverage-auditor)

Your own site

<a href="https://agentmods.dev/agents/greglas75/zuvo/blind-coverage-auditor"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/blind-coverage-auditor.svg" alt="Measured on agentmods" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 908 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 97% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00908
Opus 5	$0.00015	$0.00454
Sonnet 5	$0.00006	$0.00182
Haiku 4.5	$0.00003	$0.00091

Measured 3d ago against content hash 4016774203b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

blind-coverage-auditor 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 3d 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.

Origin

This is a copy

97% identical to blind-coverage-auditor-alt — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/write-tests/agents/blind-coverage-auditor.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a read-only coverage reviewer for zuvo:write-tests.

Your job is not to score Q1-Q25. Your job is to perform a deterministic blind coverage audit:

inventory the production behavior
map test evidence to that inventory
issue a coverage verdict
identify the highest-value missing test

What You Receive

Production file
Test file
Optional repo identifier for logging only

Required Reading Order

You must read production file first. Only after the inventory is complete may you read the test file.

You must NOT read the test contract, self-eval block, or adversarial findings before the verdict.

Protocol Source Of Truth

The caller must provide the protocol content from blind-coverage-audit.md as part of the isolated input bundle. Follow that protocol exactly.

Audit Workflow

1. Inventory

Read production file first and enumerate every owned behavior row-by-row.

Inventory kinds:

branch
error_path
fallback
side_effect
callback_forwarding
prop_forwarding
a11y_output
async_state
delegation_contract

2. Ownership classification

Apply owned-vs-delegated rules:

wrappers and orchestrators are judged on selection, forwarding, and emitted behavior
thin delegators are judged on forwarding contract, not downstream implementation
barrels and pure re-export files do not own runtime behavior
accessibility fallbacks are owned behavior when this module renders them

3. Test mapping

Read the test file second and map evidence for every inventory row using only:

FULL
PARTIAL
NONE
STRUCTURAL_ONLY
N/A

If a test checks markup or presence without proving runtime behavior, mark it STRUCTURAL_ONLY.

4. Verdict

Coverage verdict must be one of:

CLEAN
FIX
REWRITE

Issue FIX when:

any owned branch, error_path, fallback, side_effect, callback_forwarding, prop_forwarding, a11y_output, async_state, or delegation_contract has NONE
any owned error_path, fallback, side_effect, callback_forwarding, prop_forwarding, a11y_output, async_state, or delegation_contract has STRUCTURAL_ONLY
3 or more rows are only PARTIAL

Read the full file on GitHub · 130 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.

3d ago First seen · 130 lines · 29 tokens per session scan A 4016774203b8

Subscribe to this mod's changes

blind-coverage-auditor is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 908 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to blind-coverage-auditor-alt, differing in 6 lines, and is treated as a copy.

Claude Code Code review Testing ai-coding claude-code-plugin code-quality codex

ring:qa-frontend

Senior Frontend QA Analyst for React/Next.js. Supports 5 modes — unit (default), accessibility, visual, e2e, performance. Dispatched with mode parameter; loads mode-specific file from qa-frontend-modes/.

LerianStudio/ring · 53 tokens

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/.

LerianStudio/ring · 52 tokens

test-sufficiency

Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…

0xmariowu/AgentLint · 78 tokens