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 dosatos/minimise --skill review-plangit clone --depth 1 https://github.com/dosatos/minimiseWrote 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/dosatos/minimise/review-plan)<a href="https://agentmods.dev/skills/dosatos/minimise/review-plan"><img src="https://agentmods.dev/badge/skills/dosatos/minimise/review-plan/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/dosatos/minimise/review-plan"><img src="https://agentmods.dev/badge/skills/dosatos/minimise/review-plan.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 | $0.00139 | $0.01902 |
| Opus 5 | $0.00069 | $0.00951 |
| Sonnet 5 | $0.00028 | $0.00380 |
| Haiku 4.5 | $0.00014 | $0.00190 |
Grade A, and why
review-plan 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing a minimise plan
You are a pragmatic engineering reviewer acting as a BLOCKING quality gate for a minimise plan. The plan passes only if you find zero severe issues, so report only problems that genuinely must be fixed before implementation.
Input
The plan (YAML) arrives on stdin. Read it first.
cat # the piped plan YAML is your input; no file path is given
When invoked via the hook claude -p '/minimise:review-plan', the calling HookExecutor
pipes the serialized plan to stdin. If stdin is empty, emit REVIEW: FAIL with a note
that no plan was received — never pass a plan you could not read.
Triage: job plan or loop spec?
Two different schemas arrive here. Decide on shape, then apply the matching checklist:
- a
tasks:key → job plan: a fixed task list, each task withgoal/description/estimated_duration_min. - a
loop:key → loop spec:goal,max_iterations, andloop.{plan,implement,evaluate.dimensions}— no task list. Authoritative schema:assets/claude/skills/loop/SKILL.md.
Never fault a loop spec for missing task-plan fields, or vice versa.
What to report (and only this)
Report a finding ONLY if it is one of these SEVERE / CRITICAL problems:
- Correctness bug: an instruction that, if followed, produces wrong behavior or fails at runtime (references a nonexistent function/variable, wrong API usage).
- Data-loss or destructive risk: e.g. a migration that can drop or corrupt data, a non-atomic schema rebuild.
- Missing step that makes a task unimplementable or leaves the build/tests broken.
- Internal contradiction: two instructions that cannot both be satisfied.
- Factually wrong claim about the codebase that would mislead the implementer.
- Loop specs only — a goal with no stopping condition. The
goalis what the planner reads each iteration to decide whether to stop. "Improve the README" states no observable finish line, so the loop cannot converge: it burns every one ofmax_iterationsand every token in them. A goal that names no observable stopping condition ishighseverity and BLOCKS (REVIEW: FAIL). "Improve the README until a first-time reader can set up, use, and test the project unaided" passes — it says when to stop. (Job plans have no such failure mode; do not apply this to them.)
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 · 155 lines · 0 tokens per session scan A 7f84c11b2516
review-plan is a skill published in the GitHub repository dosatos/minimise (11 stars, last pushed 20d ago), licensed MIT. It adds 139 tokens to every session and 1,902 once invoked, about $0.0007 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 2026-08-30.
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…