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 jimtin/production-ai --skill user-action-coverage-reviewgit clone --depth 1 https://github.com/jimtin/production-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/jimtin/production-ai/user-action-coverage-review)<a href="https://agentmods.dev/skills/jimtin/production-ai/user-action-coverage-review"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/user-action-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/jimtin/production-ai/user-action-coverage-review"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/user-action-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 | $0.00086 | $0.00903 |
| Opus 5 | $0.00043 | $0.00451 |
| Sonnet 5 | $0.00017 | $0.00181 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
user-action-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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Action Coverage Review
Purpose
Use this skill to prevent missing browser, integration, and unit coverage from being discovered only at the full gate. This is an impact-scoped coverage review, not a full app audit. Use $full-app-review for whole-app or production-readiness audits.
When To Use
Use after plan acceptance and before implementation for substantial user-facing or workflow work, including:
- new or changed routes, forms, navigation, mutations, saves, deletes, uploads, imports, exports, toggles, filters, role-gated actions, admin/user portal workflows, and deployed-flow behavior
- frontend changes covered by
$frontend-design-quality - release-readiness work where user workflows or critical paths are in scope
The $clarify-before-build exit hands off here: a confirmed Shared Understanding Contract for substantial user-facing work names this skill as the first post-confirmation step, and the action matrix becomes the contract's acceptance-criteria evidence.
Rerun before final validation if implementation scope changes, if a user action is added or removed, or if tests are rewritten.
Workflow
-
Load repo truth.
- Read applicable
AGENTS.md, route/workflow manifests, critical-path inventories, Playwright specs, integration tests, unit tests, and relevant package scripts. - Prefer existing repo inventory files over inventing a parallel source of truth —
$repo-testing-setupcommits these at foundation time.
- Read applicable
-
Build the action matrix before implementation.
- Include every affected click, form submit, save, autosave, upload/import/export, delete/archive, navigation, keyboard path, role-gated mutation, empty/error/retry state, and removed action.
- Include public, authenticated, admin, and superadmin roles when the surface supports them.
-
Map evidence.
- Browser/E2E evidence must prove the user can actually perform or cannot perform the action.
- Integration evidence must cover API routes, persistence boundaries, provider adapters, permissions, workflows, queues/jobs, and cross-module contracts.
- Unit evidence must cover changed hooks, services, helpers, validation, rendering utilities, state machines, and branch behavior.
What ships with it
1 file 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.
- 10d ago First seen · 78 lines · 86 tokens per session scan A 7cc8c9c2df12
user-action-coverage-review is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 903 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 2026-08-31.
Other skills, from other repositories
Browser Agent QA Testing
Teach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.
bugbug-automation
Automate Bugbug tasks via Rube MCP (Composio). Always search tools first for current schemas.
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping…
test-writer
Write thorough tests following TDD and BDD principles.
test-sweep
Run all test suites (unit, integration, API, E2E) and aggregate results into a summary report. Use after completing execution slices or before the Review Gate.
audit-loop
Run a recursive audit drain loop — discover findings from the running system, triage each into bug/spec/classifier lanes, repeat until convergence. USE FOR: end-to-end audit of a deployed or locally-running app, draining findings to zero. DO NOT USE FOR: single-shot tempering runs (use forgetemperingrun), one-off bug…