What is test-coverage?

A test-planning and test-running workflow for a feature, specification, code module, pull request, or ticket. It creates Markdown records describing what was tested and what happened.

It is for choosing suitable tests, getting tests written, running them, and recording the results in test-spec.md and test-report.md.

It helps turn broad testing work into a clear list of behaviors to check, while keeping a factual record of tests that passed, failed, or could not run.

test-coverage — Skill for Claude Code and Codex by ShiplightAI

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.

Any agent

npx skills add ShiplightAI/agent-skills --skill test-coverage

Clone the repo

git clone --depth 1 https://github.com/ShiplightAI/agent-skills

Made for: Claude Code, Codex.

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/skills/shiplightai/agent-skills/test-coverage/github.svg)](https://agentmods.dev/skills/shiplightai/agent-skills/test-coverage)

Your own site

<a href="https://agentmods.dev/skills/shiplightai/agent-skills/test-coverage"><img src="https://agentmods.dev/badge/skills/shiplightai/agent-skills/test-coverage/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shiplightai/agent-skills/test-coverage"><img src="https://agentmods.dev/badge/skills/shiplightai/agent-skills/test-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,350 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.02350
Opus 5.5	$0.00036	$0.00940
Sonnet 5.5	$0.00018	$0.00470
Haiku 4.5	$0.00009	$0.00235

Measured 2mo ago against content hash 6fa9fa6d3f34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-coverage 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 2mo 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.

skills/test-coverage/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Coverage

Test-creation workflow for one feature, spec, module, PR, or ticket at a time. Use after a feature is implemented (or alongside it, or after a PR) to decide what needs testing, choose the right testing strategy, drive the producers to write comprehensive tests, run them, and record the result.

It produces human-readable Markdown (test-spec.md, test-report.md) and test code via the producers. The report records facts — what was tested, by what test type, and what passed — not a graded confidence verdict.

What This Skill Owns

specs/<feature>/test-spec.md — the durable "testing what" contract: the behaviors, invariants, risks, and the declared priority of each.
specs/<feature>/test-report.md — the session record: what was tested, by what test type, what ran, and what passed, failed, or was blocked.
Repo-root TESTING.md (optional) — project testing-strategy notes (preferred modalities, gate/posture by priority, context labels). Standalone-safe: a baked-in default applies when absent.

Two Layers

Testing what — the behaviors, properties, requirements, and invariants that must be verified to trust the feature, each carrying a declared priority (P0–P3).
Testing how — the evidence used to verify them: unit, contract, integration, e2e, agent, manual, telemetry, static, smoke, script.

Comprehensive testing is not test count. Optimize for justified confidence per unit of cost (author + run + maintain), stability, latency, and diagnostic value. Buy sufficient confidence at the lowest cost, spending the scarce expensive-test budget (e2e, agent) where priority is highest.

Priority Is A Declared Fact

Each testing-what item carries a priority (P0–P3) read from an upstream dev artifact — the PRD, the feature breakdown, or the spec — never invented here. Priority is the effort lever: P0 gets the strongest posture, P3 the lightest. Per-behavior priority defaults to the feature's declared P-level; record a finer level in test-spec.md only when the spec or owner declares one. If nothing upstream declares a priority, mark it UNKNOWN and surface it for the owner rather than guessing — a guessed priority is not a fact.

Read the full file on GitHub · 209 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 209 lines · 90 tokens per session scan A 6fa9fa6d3f34

Subscribe to this mod's changes

test-coverage is a skill published in the GitHub repository ShiplightAI/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 2,350 once invoked, about $0.0004 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

test-coverage