revise

revise is a skill for Claude Code from bguthrie/prospero. It costs 32 tokens per session (1,612 once invoked), scanned A, original, MIT.

Editorial feedback for a blog draft that has already been edited by its author. It checks both the structure of the piece and the wording, using the project's writing rules and audience.

In plain words
What is it for?
Use it to polish an existing draft, improve its organization, and get specific suggestions for clearer line-level writing.
Why use it?
It helps authors find unclear arguments, weak structure, and awkward sentences before publishing without replacing their own editing decisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the prospero plugin — 6 skills, 5 commands shipped together

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.

agentmods
npx agentmods add skills/bguthrie/prospero/revise
Any agent
npx skills add bguthrie/prospero --skill revise
Clone the repo
git clone --depth 1 https://github.com/bguthrie/prospero

Made for: Claude Code.

Or install prospero, the plugin that ships this one along with the rest of its 6 skills, 5 commands.

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.

agentmods badge for revise

README.md
[![agentmods](https://agentmods.dev/badge/skills/bguthrie/prospero/revise.svg)](https://agentmods.dev/skills/bguthrie/prospero/revise)
Your own site
<a href="https://agentmods.dev/skills/bguthrie/prospero/revise"><img src="https://agentmods.dev/badge/skills/bguthrie/prospero/revise.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01612
Opus 5 $0.00016 $0.00806
Sonnet 5 $0.00006 $0.00322
Haiku 4.5 $0.00003 $0.00161

Measured 6d ago against content hash 111541a61cb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

revise 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 6d 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.

skills/revise/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revise

The author has made an editing pass on a draft and wants feedback before publishing. Revise reads the current draft and returns specific, actionable suggestions — structural where the argument needs it, line-level where the prose does. Revise is collaborative editorial feedback; it is not the adversarial review that /critique in draft mode provides.

When to use

  • The user has a draft at the resolved post_path_pattern (typically written by /author) and has made their own editing pass, and wants feedback on the current state.
  • The user wants a line-level polish pass before publishing.

Do NOT use for:

  • Producing a new outline from a topic → use /interrogate.
  • Oppositional review before drafting → use /critique in outline mode.
  • Independent adversarial evaluation of the draft against its outline → use /critique in draft mode (which revise can offer to invoke; see below).
  • Writing the first draft → use /author.

Preconditions

Run these as a silent preflight. Do not narrate them to the user unless a check fails; a passing preflight should be invisible.

1. .prospero/config.toml must exist

If .prospero/config.toml does NOT exist in the current working directory, invoke the prospero:init skill and follow it to completion. When init returns, resume at step 2 below. Do not proceed to revision with an unconfigured project.

2. .prospero/voice.md and .prospero/audience.md must be filled in

For each of .prospero/voice.md and .prospero/audience.md, compute byte-for-byte equality against the plugin's corresponding template at <plugin-root>/templates/voice.md and <plugin-root>/templates/audience.md. Use the plugin-root resolution procedure defined in the init skill's "Resolving the plugin's templates directory" section. Do not abbreviate its failure handling: zero matches → ask the user; multiple matches → ask the user; match found but voice.md or audience.md missing → halt with the resolved path.

  • If either user file is Missing → halt with: ".prospero/<file> is missing. Run /init to restore it, then fill it in before /revise."
  • If either user file is byte-for-byte equal to its template → halt with: ".prospero/<file> is the unmodified scaffold. Fill it in before running /revise; this is the one thing Prospero cannot write for you."
  • Otherwise → the file is user content. Proceed.

Read the full file on GitHub · 83 lines

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.

  1. 6d ago First seen · 83 lines · 32 tokens per session scan A 111541a61cb1

Subscribe to this mod's changes

revise is a skill published in the GitHub repository bguthrie/prospero (6 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,612 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

convex-billing

Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).

openclaw/clawhub · 29 tokens

dev-workflow

The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.

iflytek/skillhub · 35 tokens

convex-performance-audit

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

openclaw/clawhub · 38 tokens

happiness-skill

当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.

kangarooking/cangjie-skill · 136 tokens