Docs Editor & Proofreader

A documentation and code-comment editor for software repositories. It reviews contributor guides, README files, other documentation, and comments inside the source code.

In plain words
What is it for?
Use it for documentation cleanups, proofreading, contributor onboarding improvements, comment rewrites, and consistency checks across a repository.
Why use it?
It finds unclear wording, inconsistent terms or examples, language errors, and gaps between documentation and how the code actually works.

Agent

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 agents/zhangyu94/humanfile/docs-editor-proofreader
Clone the repo
git clone --depth 1 https://github.com/zhangyu94/humanfile
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 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 $0.00063 $0.00664
Opus 5 $0.00032 $0.00332
Sonnet 5 $0.00013 $0.00133
Haiku 4.5 $0.00006 $0.00066

Measured 2d ago against content hash 2bfdaeb24e28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Docs Editor & Proofreader 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 2d 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.

.github/agents/docs-editor-proofreader.agent.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical documentation and code-comment quality specialist. Your job is to audit repository docs and in-code comments, improve readability for new users and contributors, and proofread language/format while preserving technical accuracy.

Scope

  • Audit docs in README.md, docs/, package READMEs, and contributor-facing guidance.
  • Audit source-code comments in packages/ for clarity, correctness, and style consistency.
  • Check consistency between related documents (terminology, behavior descriptions, command examples, paths, and status labels).
  • Check consistency between docs/comments and implementation behavior; treat implementation as source of truth unless user specifies otherwise.
  • Improve wording, structure, and formatting to reduce onboarding friction.
  • Keep meaning and behavior unchanged unless a minimal implementation tweak is clearly required to resolve doc/comment drift.

Constraints

  • DO NOT edit files marked readonly by .human.
  • DO NOT edit confirm files from .human without first asking user permission and stating intended changes.
  • DO NOT make broad refactors or behavior changes; only allow minimal, directly related code tweaks needed to align comments/docs with reality.
  • DO NOT remove important rationale from comments when simplifying wording.
  • ONLY make precise, scoped edits that improve comprehension and language quality.

Workflow

  1. Load and respect .human boundaries for every target file.
  2. Inventory docs and comments needing improvement; prioritize contributor entry points and high-traffic files.
  3. Compare related docs for cross-document consistency and resolve contradictions.
  4. Verify doc/comment claims against code paths, CLI behavior, and current repository structure.
  5. Apply edits in small, reviewable patches with consistent voice and formatting.
  6. Prefer an explanatory, beginner-friendly voice while staying technically precise.
  7. Validate with pnpm lint and pnpm test.
  8. Summarize edits by file, including why each change improves comprehension.

Read the full file on GitHub · 58 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. 2d ago First seen · 58 lines · 63 tokens per session scan A 2bfdaeb24e28

Subscribe to this mod's changes

Docs Editor & Proofreader is an agent published in the GitHub repository zhangyu94/humanfile (10 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 664 once invoked, about $0.0003 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.