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 rohitgehe05/mindpowers --skill reviewing-docsgit clone --depth 1 https://github.com/rohitgehe05/mindpowersWrote 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/rohitgehe05/mindpowers/reviewing-docs)<a href="https://agentmods.dev/skills/rohitgehe05/mindpowers/reviewing-docs"><img src="https://agentmods.dev/badge/skills/rohitgehe05/mindpowers/reviewing-docs.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.03791 |
| Opus 5 | $0.00046 | $0.01895 |
| Sonnet 5 | $0.00018 | $0.00758 |
| Haiku 4.5 | $0.00009 | $0.00379 |
Grade A, and why
reviewing-docs 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 7d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing Docs
Overview
A standalone red-team pass for a finished (or nearly finished) piece of writing. It works whether or not the doc was made with mindpowers: a pasted memo, a doc someone else wrote, a file on disk, all fine. It is the "review" step of the mindpowers loop (shape → draft → review → remember), but it doesn't require the other steps to have happened.
The job is not to improve the prose. It's to find the places where the doc will get punctured in the room it's headed for, before that room punctures it: the exec meeting, the regulator's inbox, the Slack thread. Track the steps below as todos if your harness has a task list.
When this fires: "review this doc," "poke holes in this," "is this ready to send," "what am I missing before I ship this," or being handed a file/pasted text and asked whether it holds up. It does not fire for source code, config, or anything a code-review tool should be looking at; decline that and point at a code-review skill or tool instead.
User-Facing Language
Think precisely; respond plainly. Use common words and short sentences. Explain an unavoidable technical term the first time it appears, and give one short example when a rule could be misunderstood. For a material review conclusion, give a compact explanation: the recommendation or conclusion, what you checked, the main reasons, uncertainty, and the next step. Do not dump internal machinery. If the user says the explanation is unclear, explain it again from scratch.
Step 1: Find the spec
Check the doc for a paper trail before reviewing it blind.
- Look at the doc's own frontmatter for a
spec:link. - If there's none, scan
docs/mindpowers/specs/(and legacydocs/brainstorm/if it exists) for a spec with a matching filename stem or topic.
If a spec exists: do a fidelity check before anything else.
- Is every section the spec called for actually present in the doc?
- Did anything make it into the doc that the spec didn't scope in?
- Has the claim or recommendation drifted between spec and doc: softened, hedged, or quietly changed?
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.
- 7d ago First seen · 250 lines · 91 tokens per session scan A 315c01c6ec2a
reviewing-docs is a skill published in the GitHub repository rohitgehe05/mindpowers (5 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 3,791 once invoked, about $0.0005 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
okf-frontmatter
Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schemasource, documents); schema details link…
markifact-overview
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
text-stats
Compute word count, character count, or reading time for a piece of text using the in-bundle text-stats engine. Invoke whenever the user asks how long a passage is, how many words or characters it has, or how long it takes to read.
safe-write-operations
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
pdf-explore
Use this skill when the user has attached or pointed to a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, pull tables out as…
document-writer
Use when writing or improving technical documentation, API references, runbooks, onboarding guides, READMEs, changelogs, ADRs, release notes, or any content that ships to engineers or end users. Also use for structuring documentation sites (MkDocs, Docusaurus) and diagrams-as-code.