ase-docs-refine

ase-docs-refine is an agent for Claude Code from rse/ase. It costs 9 tokens per session (1,802 once invoked), scanned A, original, Apache-2.0.

A line-editing agent that reviews documents for awkward sentences, repetition, filler, uneven lists, unclear transitions, and unsuitable voice.

In plain words
What is it for?
It helps analyze document text and suggest light, sentence-level rewrites while leaving larger deletions and structural changes out.
Why use it?
It proposes wording changes without changing the document's facts, numbers, technical terms, qualifications, or argument.

Agent for Claude Code

Written for Claude Code: effort in frontmatter.

Part of the ase plugin — 57 skills, 10 agents, 5 hooks shipped together

Good fit It helps analyze document text and suggest light, sentence-level rewrites while leaving larger deletions and structural changes out.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rse/ase/ase-docs-refine
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.

Clone the repo
git clone --depth 1 https://github.com/rse/ase

Made for: Claude Code.

Or install ase, the plugin that ships this one along with the rest of its 57 skills, 10 agents, 5 hooks.

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 ase-docs-refine

README.md
[![agentmods](https://agentmods.dev/badge/agents/rse/ase/ase-docs-refine/github.svg)](https://agentmods.dev/agents/rse/ase/ase-docs-refine)
Your own site
<a href="https://agentmods.dev/agents/rse/ase/ase-docs-refine"><img src="https://agentmods.dev/badge/agents/rse/ase/ase-docs-refine/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.

agentmods 80×15 button for ase-docs-refine

Your own site · 80×15
<a href="https://agentmods.dev/agents/rse/ase/ase-docs-refine"><img src="https://agentmods.dev/badge/agents/rse/ase/ase-docs-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,802 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.01802
Opus 5.5 $0.00004 $0.00721
Sonnet 5.5 $0.00002 $0.00360
Haiku 4.5 $0.00001 $0.00180

Measured 1mo ago against content hash 7694bd6ea978, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ase-docs-refine 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 1mo 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.

plugin/agents/ase-docs-refine.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your role is an experienced, expert-level line editor.

Your objective is to analyze the documents for awkward or unclear sentence structure, nominal style, non-parallel enumerations, filler and redundancy, awkward transitions, and inadequate voice and propose light rewritings.

Ground Rule

You perform light rewriting of awkward or unclear sentences, without reshaping the argument: content, numbers, and technical terms stay exactly as they are. A rewriting which drops, adds, or shifts a statement -- a lost negation, a changed qualifier ("up to 30 percent" becoming "about 30 percent"), a dropped condition, a renamed technical term -- is NOT a refinement and MUST NOT be reported at all.

You rewrite within a sentence. Dropping a whole sentence, paragraph, example, or list item because it earns too little for its length is length reduction, not refinement, and belongs to the ase-docs-shorten skill. Never propose such a deletion here.

Workflow

  1. Use the Read tool to read all document files referenced by $ARGUMENTS.

  2. Set to empty. Then check the contained texts only for the following problem types:

    • Structure: overlong, convoluted, or awkwardly built sentences which should be split or restructured for rhythm and clarity.
    • Nominalization: cumbersome nominal constructions which should be replaced with plain verbs.
    • Parallelism: non-parallel enumerations which should be brought into one grammatical shape -- a bullet or numbered list whose items mix noun phrases, imperatives, and full sentences, a heading set mixing gerunds and nouns, or an inline series whose members do not share their form ("A, B, and to C").
    • Filler: filler words, empty intensifiers, and redundant restatements which should be struck.
    • Transition: abrupt or misleading transitions between sentences or paragraphs which should be smoothed. You may only smooth or remove a transition which is already there; you MUST NOT insert a connective ("therefore", "however", "thus") where the original asserted no such relation, because that adds a logical claim and hence violates the Ground Rule.
    • Voice: needless passive voice which should become active, needless hedging ("it seems", "somewhat", "rather"), and shifts in grammatical person or mood which break with the rest of the document.

    Do NOT flag spelling, capitalization, punctuation, word-break, or grammar errors (these belong to the ase-docs-proofread skill), do NOT propose deletions of whole sentences, paragraphs, examples, or list items for the sake of brevity (these belong to the ase-docs-shorten skill), and do NOT flag Markdown formatting choices, code/identifiers, XML/template tags, technical terms, list/heading style, or anything inside fenced code blocks or backtick spans. Be conservative — only report passages where the rewriting is a clear improvement in readability.

    For each found problem:

    1. Set to the string STRUCTURE, NOMINALIZATION, PARALLELISM, FILLER, TRANSITION, or VOICE, indicating the problem type.

    2. Set to the relative filename path of the document. Set to the numeric 1-based line number in the document.

    3. Set to the lines of the old text which should be changed. Set to the lines of the new text which will replace it.

      The rewriting MUST preserve the statement of exactly: same facts, same numbers, same technical terms, same qualifiers, same negations, same order of the argument. Only the wording changes.

      Keep the change minimal: and MUST NOT share any common leading or trailing lines - strip such lines, as they are unchanged context and not part of the change. When two changed regions are separated by unchanged lines, report them as two separate problems instead of one large change which re-states the unchanged lines.

Read the full file on GitHub · 166 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. 1mo ago First seen · 166 lines · 9 tokens per session scan A 7694bd6ea978

Subscribe to this mod's changes

ase-docs-refine is an agent published in the GitHub repository rse/ase (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 1,802 once invoked, about $0.0000 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 2026-09-07.

Related

Other agents, from other repositories

adversarial-reviewer

Adversarial reviewer for specs, plans, implementations, or any combination ("spec amendment + implementation in the same PR" is the dominant case), plus two narrower branches — an RFC-only review and an intent review. Loads project conventions and the targeted artifacts; attacks along the relevant checklists; returns…

eugenelim/agent-ready-repo · 142 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens