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 agentmods add skills/angadhn/botference/review-docnpx skills add angadhn/botference --skill review-docgit clone --depth 1 https://github.com/angadhn/botferenceWrote 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/angadhn/botference/review-doc)<a href="https://agentmods.dev/skills/angadhn/botference/review-doc"><img src="https://agentmods.dev/badge/skills/angadhn/botference/review-doc.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 | $0.00102 | $0.00559 |
| Opus 5 | $0.00051 | $0.00280 |
| Sonnet 5 | $0.00020 | $0.00112 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
review-doc 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 4d 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.
What it actually says
review-doc — reviewable HTML documents with margin comments
What this produces
A single self-contained .review.html file (no network, no deps) that
renders a markdown document with:
- Google-Docs-style commenting: select text → 💬 → type a note; comments live as cards in a right margin rail, anchored to highlights.
- Persistence in
localStorage(survives reload, keyed per document). - Export feedback button → downloads
<doc>.feedback.md(quoted passages + the user's notes) and a copy-to-clipboard alternative. - General (unanchored) comments, dark/light theme support.
Workflow
- The markdown source stays canonical. Never hand-edit the generated HTML; regenerate it.
- Generate:
node <dir-containing-this-SKILL.md>/build-review.mjs <source.md> [out.html](the script sits next to this SKILL.md — use the path you read it from) (default output:<source>.review.htmlnext to the source). - Deliver:
open <out.html>on macOS so it lands in the user's real browser (commenting + export need a full browser, not a preview pane), and/or send the file. Tell the user the loop in one line: highlight → comment → Export feedback → give me the file. - When the user returns a
*.feedback.md(or pastes its contents): read every quoted passage + note, respond to or apply each one, then regenerate the review HTML from the updated markdown. Existing comments re-anchor by quote; notes on text that changed appear in the rail as "unanchored" rather than being lost.
Notes
- Works for any markdown: headings, tables, lists, code fences, blockquotes, links, images.
- The document id (localStorage key + feedback filename) is derived from the output filename — keep it stable across regenerations so the user's in-progress comments survive.
- If the user asks for review docs in some other format, that wins.
What ships with it
2 files 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.
- 4d ago First seen · 46 lines · 102 tokens per session scan A 3c42483b6c80
review-doc is a skill published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 559 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…