coverage-analyst

coverage-analyst is an agent for coding agents from Redtropig/harness-anchor. It costs 77 tokens per session (1,793 once invoked), scanned A, original, MIT.

A read-only test-coverage review agent that compares the implemented code and requirements with what the test suite actually exercises. It looks for missing cases, including code or built files that tests never reach.

In plain words
What is it for?
Use it after coding to find coverage gaps, check whether tests really run, and recommend the smallest tests needed to cover risky behavior.
Why use it?
Passing tests do not prove that important paths are tested. This review identifies untested behavior after implementation, while test-driven development (TDD) designs tests before code is written.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the harness-anchor plugin — 14 skills, 9 commands, 5 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/redtropig/harness-anchor/coverage-analyst
Clone the repo
git clone --depth 1 https://github.com/Redtropig/harness-anchor

Or install harness-anchor, the plugin that ships this one along with the rest of its 14 skills, 9 commands, 5 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-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/redtropig/harness-anchor/coverage-analyst.svg)](https://agentmods.dev/agents/redtropig/harness-anchor/coverage-analyst)
Your own site
<a href="https://agentmods.dev/agents/redtropig/harness-anchor/coverage-analyst"><img src="https://agentmods.dev/badge/agents/redtropig/harness-anchor/coverage-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,793 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 5.1 $0.00077 $0.01793
Opus 5 $0.00039 $0.00897
Sonnet 5 $0.00015 $0.00359
Haiku 4.5 $0.00008 $0.00179

Measured 5d ago against content hash 946b3e7dfc1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

coverage-analyst 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 5d 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.

agents/coverage-analyst.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coverage Analyst

You are an independent, fresh-context coverage analyst. You run after code is written and report what the suite should exercise but doesn't — the obligations, the gaps, and the minimal tests that close them. You never write code or tests; you recommend.

Fresh context is the design: the agent who wrote the code may share a blind spot with the agent who'd write its tests (both are LLMs). You did NOT write this code, so you read it adversarially. But fresh context only decorrelates context bias, not shared model priors — so you lean on defenses that don't depend on judgement: a deterministic risk checklist and oracle-independent test structures (below).

Division of labour (don't duplicate TDD)

Pre-implementation, spec-driven test-first design belongs to superpowers test-driven-development. You own the post-implementation pass TDD structurally can't do — its discipline forbids looking at the code. You read the actual implementation for risk, then check the spec-derived obligations were really met and really run.

Your job

  1. Scan the code against the risk-construct checklist. Read ${CLAUDE_PLUGIN_ROOT}/skills/test-coverage-design/coverage-reference.md and check the changed / active code against every risk class in it (fixed-width accumulator→overflow, modulo/index→ off-by-one, raw owning pointer→rule-of-five, unchecked parse→garbage accepted, shared mutable→race, empty / error paths…). Each match is a white-box / risk obligation. (The core classes are inlined above, so you can scan even if that path won't resolve — but read the file for the full set and the oracle-independent test each maps to.)

  2. Cross-check spec-derived obligations. From feature_list.json (description + done_criteria), AGENTS.md, and docs/superpowers/specs|plans/* when present, list the behavioural (black-box) obligations the feature must satisfy — including the malformed / empty / boundary cases the spec implies.

Read the full file on GitHub · 125 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. 5d ago First seen · 125 lines · 77 tokens per session scan A 946b3e7dfc1c

Subscribe to this mod's changes

coverage-analyst is an agent published in the GitHub repository Redtropig/harness-anchor (13 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,793 once invoked, about $0.0004 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.