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.
npx skills add Eliyce/paqad-ai --skill state-coverage-reviewgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/skills/eliyce/paqad-ai/state-coverage-review)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/state-coverage-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/state-coverage-review/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/skills/eliyce/paqad-ai/state-coverage-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/state-coverage-review.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 | $0.00037 | $0.00852 |
| Opus 5 | $0.00018 | $0.00426 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
state-coverage-review 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 8d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Cross-checks the declared state machine of each component against (1) what the source code implements and (2) what Playwright tests actually exercise. A declared state that's neither implemented nor tested is a finding; an implemented state that's never tested is a coverage finding.
Use This When
Use this for every design-test run after component-conformance-review. It depends on the AST inventory that skill produced.
Inputs
- Read
docs/instructions/design-system/components.mdfor declared states. - Read Playwright test files (
tests/**,e2e/**) for what's exercised. - Read
references/state-coverage-checklist.mdbefore grading.
Procedure
The set arithmetic across declared / implemented / tested is deterministic — drive it with the scripts. LLM picks severity per missing state (focus and error are elevated to high per the checklist).
- For each component, run
scripts/extract-source-states.sh <component-file>→ TSV of<state>\t<signal>(signals::hover, Tailwindhover:utility,disabledprop,aria-disabled, framer-motion hooks, etc.).defaultis always emitted. - Run
scripts/extract-tested-states.sh --component <Name> --tests <dir>→ TSV of<state>\t<test-file>. The tests directory should contain Playwright specs only (the script greps for component name + state driver pattern; mixing the component's source with the tests dir would self-pollute the result). - Take the declared states from
components.md(the CSV fromparse-components-md.shworks directly). - Run
scripts/cross-reference-states.sh --declared <csv> --implemented <impl.tsv> --tested <tested.tsv>. Each row is a deterministic gap:declared-not-implemented\t<state>→statefinding.implemented-not-tested\t<state>→statefinding (regression risk).tested-not-implemented\t<state>→documentation-driftfinding (test asserts something the component can't reach).
Output Contract
- Match
assets/output.template.md.contract_refiscomponents.md → <ComponentName> > <state>. - Default severity
medium. Usehighwhen the missing state isfocus(a11y blocker) orerror(silently fails for users). - Output must pass
scripts/lint-findings.sh(exit 0).
What ships with it
7 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.
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.
- 8d ago First seen · 75 lines · 37 tokens per session scan A 437a9f22582e
state-coverage-review is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 852 once invoked, about $0.0002 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.
Other skills, from other repositories
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
testing-strategy
A testing guide that explains how to combine unit, integration, contract, and end-to-end tests. End-to-end tests check complete user flows, while integration tests check components working together.
auto-test
An end-to-end testing helper that runs the test scenarios written in a `scenarios.md` file. End-to-end tests check a complete user flow across the relevant parts of an application.
auto-verify
A frontend user-experience verification workflow built around Playwright, a tool for controlling browsers in automated tests. It checks important user flows and visual states in a frontend.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.