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 LiuYihey/Auto-agent-skills --skill review-taskgit clone --depth 1 https://github.com/LiuYihey/Auto-agent-skillsWrote 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/liuyihey/auto-agent-skills/review-task)<a href="https://agentmods.dev/skills/liuyihey/auto-agent-skills/review-task"><img src="https://agentmods.dev/badge/skills/liuyihey/auto-agent-skills/review-task/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/liuyihey/auto-agent-skills/review-task"><img src="https://agentmods.dev/badge/skills/liuyihey/auto-agent-skills/review-task.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 | $0.00038 | $0.01213 |
| Opus 5 | $0.00019 | $0.00607 |
| Sonnet 5 | $0.00008 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
review-task 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Review Guide
This skill guides you through reviewing completed tasks and making intelligent decisions about skill creation and updates.
When to Use This Skill
- After completing any task (automatically triggered by review_task tool)
- When evaluating whether a solution is worth capturing as a skill
- When assessing if a used skill performed well
Review Workflow
Step 1: Identify Skill Usage
Check if any skills were used during the task:
If skills were used: Proceed to Step 2 (Evaluate Skill Performance) If no skills were used: Proceed to Step 3 (Evaluate Reuse Potential)
Step 2: Evaluate Skill Performance (Skills Were Used)
Analyze how well the skill(s) performed:
| Performance | Indicators | Action |
|---|---|---|
| Excellent | Task completed smoothly, no workarounds needed, instructions were clear | No action needed. Acknowledge success. |
| Good with minor issues | Mostly worked but had small gaps or unclear parts | Consider updating the skill with update_skill tool |
| Poor | Required significant workarounds, instructions were wrong/incomplete | Strongly recommend updating the skill with update_skill tool |
Decision Criteria for Skill Updates
Update the skill if ANY of these apply:
- Instructions were unclear or incomplete
- Edge cases weren't handled
- Commands/APIs were outdated
- Had to improvise or work around issues
- Better patterns were discovered during execution
If update is needed: Call the update_skill MCP tool, which will provide the skill-updater guide.
Step 3: Evaluate Reuse Potential (No Skills Were Used)
Assess whether the completed task is worth capturing as a new skill:
High Reuse Value ✅ (Create Skill)
Create a skill if the task has:
- Repeatable workflow: Same steps apply to similar problems
- Clear trigger conditions: Easy to identify when this solution applies
- Non-trivial complexity: More than 3-4 steps or requires specific knowledge
- Broad applicability: Useful across multiple projects/contexts
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 · 152 lines · 38 tokens per session scan A b1c24f13a675
review-task is a skill published in the GitHub repository LiuYihey/Auto-agent-skills (9 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,213 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…