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 siarhei-belavus/agent-public --skill plan-reviewer-agentgit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/plan-reviewer-agent)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/plan-reviewer-agent"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/plan-reviewer-agent/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/siarhei-belavus/agent-public/plan-reviewer-agent"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/plan-reviewer-agent.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 | $0.00060 | $0.01830 |
| Opus 5 | $0.00030 | $0.00915 |
| Sonnet 5 | $0.00012 | $0.00366 |
| Haiku 4.5 | $0.00006 | $0.00183 |
Grade A, and why
plan-reviewer-agent 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer Agent
Review plans as execution contracts, not brainstorming notes. The goal is to determine whether a plan is ready to hand to another agent with no prior chat context and no opportunity to ask clarifying questions.
Treat the plan as not ready unless it is explicit, self-sufficient, unambiguous, and operationally safe to execute as written.
This skill is generic and project-agnostic. It should work for software, operations, documentation, migration, research, and other structured execution plans.
Review Standard
A plan is ready only when all of the following are true:
- every important term, artifact, and target outcome is explicit
- no step requires guessing intent from prior conversation
- the implementer can execute each step without hidden assumptions
- the plan does not contain choice-language where a decision should already be made
- the plan is clear enough that a competent agent can follow it in a clean context window without asking follow-up questions
If any of those conditions fail, the plan is not ready.
Core Workflow
-
Establish the real execution context.
- Review the provided plan text only.
- Assume the future executor will not see the surrounding conversation unless the plan includes that information directly.
- Judge the document on its own contents, not on what the human probably meant.
-
Run an ambiguity pass.
- Find wording that permits more than one reasonable interpretation.
- Flag vague nouns, unclear ownership, undefined success conditions, and steps that hide the actual action.
- Treat terms like "handle", "support", "improve", "clean up", and "update as needed" as ambiguous unless the plan defines the concrete work.
-
Run a self-sufficiency pass.
- Check whether the plan names the specific targets the executor must touch, create, remove, validate, or preserve.
- Check whether the plan embeds the semantic decisions that the executor would otherwise need to reconstruct.
- Flag every place where the implementer would need missing context, private conventions, or remembered backstory.
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 · 188 lines · 60 tokens per session scan A 7e47e9b4c029
plan-reviewer-agent is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,830 once invoked, about $0.0003 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…