A workflow for reviewing Markdown documents with MRSF, a sidecar format that stores comments separately from the document. It adds comments tied to specific lines and tracks whether issues have been resolved.

Use it to inspect Markdown files, add suggestions or issues with severity levels, validate the review data, and check or resolve existing comments.

It keeps review feedback structured and anchored to the text instead of mixing comments into the document or losing their location after edits.

mrsf-review — Skill for Claude Code by wictorwilen/MRSF

Install

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.

Any agent

npx skills add wictorwilen/MRSF --skill mrsf-review

Clone the repo

git clone --depth 1 https://github.com/wictorwilen/MRSF

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wictorwilen/mrsf/mrsf-review/github.svg)](https://agentmods.dev/skills/wictorwilen/mrsf/mrsf-review)

Your own site

<a href="https://agentmods.dev/skills/wictorwilen/mrsf/mrsf-review"><img src="https://agentmods.dev/badge/skills/wictorwilen/mrsf/mrsf-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wictorwilen/mrsf/mrsf-review"><img src="https://agentmods.dev/badge/skills/wictorwilen/mrsf/mrsf-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 524 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00051	$0.00524
Opus 5.5	$0.00020	$0.00210
Sonnet 5.5	$0.00010	$0.00105
Haiku 4.5	$0.00005	$0.00052

Measured 2mo ago against content hash c7239bd132cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mrsf-review 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 2mo 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.

examples/mrsf-review/SKILL.md · 40 lines

What it actually says

MRSF Document Review

You review Markdown documents by adding structured, anchored comments using the MRSF MCP server tools.

Setup

The MRSF MCP server must be available. It provides these tools: mrsf_discover, mrsf_validate, mrsf_add, mrsf_list, mrsf_resolve, mrsf_reanchor, mrsf_status, mrsf_rename, mrsf_delete, mrsf_repair, mrsf_help.

Workflow

Discover the sidecar for the target document using mrsf_discover.
Check existing comments with mrsf_list (use summary: true for an overview).
Read the document, then add comments with mrsf_add for each issue found. Always provide:
- document: path to the Markdown file
- text: your review comment
- author: your identity (e.g. "AI Reviewer (copilot)")
- line: the line number where the issue occurs
- type: one of suggestion, issue, question, accuracy, style, clarity
- severity: low, medium, or high
Validate the sidecar with mrsf_validate after adding comments.
Summarize what you found using mrsf_list with summary: true.

Comment Guidelines

Anchor every comment to a specific line (use line and optionally end_line).
Use type to categorize: accuracy for factual issues, clarity for confusing prose, suggestion for improvements, style for formatting.
Set severity: high for factual errors or broken instructions, medium for clarity issues, low for style nits.
For follow-ups on existing comments, use reply_to with the parent comment ID.
After the document is edited, run mrsf_reanchor to update comment positions.

Changes

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.

2mo ago First seen · 40 lines · 51 tokens per session scan A c7239bd132cb

Subscribe to this mod's changes

mrsf-review is a skill published in the GitHub repository wictorwilen/MRSF (31 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 524 once invoked, about $0.0002 per session on Opus 5.5. 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.

Writing and docs cli comments draft format markdown review

tether-edit

Respond to a human's anchored Tether comments on a markdown draft by PROPOSING rewrites (suggestion mode) — the human then Accepts or Rejects each in the editor. Use when the user says "apply my Tether comments", "address my comments", "suggest fixes for my comments", or points you at a .md they've commented on with…

tether-md/tether-md · 80 tokens

llmwiki

Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.

atomicstrata/llm-wiki-compiler · 66 tokens

crit-story

Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.

tomasz-tomczyk/crit · 47 tokens

processing-markdown

Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.

harehare/mq · 36 tokens

web-scraping

Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…

harehare/mq · 89 tokens

review

Use when a green diff needs adversarial judgment in the rsc SDD chain, between verify and ship — give a review keyed to the spec/plan/constitution in 02-DOCS/wiki/sdd/, or receive one and verify each comment before agreeing. NOT running lint/type/tests (that is verify), NOT the spec-less standalone pass (that is…

ericrisco/rsc-harness · 89 tokens