humanize-docs

A command for rewriting existing documentation so it is easier for people to scan and understand. It works on Markdown, reStructuredText, MDX, and text files in a specified path.

In plain words
What is it for?
Humanizing documentation, breaking up dense sections, improving progressive disclosure, and reorganizing existing technical content.
Why use it?
It reduces dense writing and unclear organization without inventing new information.

Command

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 commands/acaprino/daodan/humanize-docs
Clone the repo
git clone --depth 1 https://github.com/acaprino/daodan
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 864 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 $0.00073 $0.00864
Opus 5 $0.00036 $0.00432
Sonnet 5 $0.00015 $0.00173
Haiku 4.5 $0.00007 $0.00086

Measured 2d ago against content hash c6748f9fd501, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanize-docs 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.

exports/claude/plugins/codebase-mapper/commands/humanize-docs.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanize Documentation

CRITICAL RULES

  1. Path required. The user must provide a path to documentation files or directory.
  2. Never invent content. Only restructure and rephrase existing content.
  3. Confirm scope. Show what will be rewritten before starting.
  4. Never enter plan mode. Execute immediately.

Step 1: Validate Target

Parse $ARGUMENTS for the documentation path.

If no path provided, ask:

Which documentation should I humanize? Provide a path to a file or directory.

Verify the path exists and contains documentation files (.md, .rst, .mdx, .txt).

Step 2: Assess and Confirm Scope

Read the target documentation. Present a brief assessment:

Documentation to humanize: [path]

Files found: [count]
Total lines: ~[count]

Issues detected:
- [X] instances of passive voice / AI boilerplate
- [X] dense paragraphs (> 4 sentences)
- [X] monolithic diagrams
- [X] missing progressive disclosure
- [X] mixed reference / tutorial content

1. Proceed with humanization
2. Narrow scope -- I'll specify which files
3. Cancel

Use AskUserQuestion. Do NOT proceed until the user confirms.

Step 3: Rewrite

Spawn the doc-humanizer agent:

Task:
  subagent_type: "codebase-mapper:doc-humanizer"
  description: "Humanize documentation at [path]"
  prompt: |
    Rewrite the following documentation to be human-readable.

    ## Target
    [path and file list]

    ## Instructions
    Read all target files and rewrite them following the codebase-mapper
    writing guidelines. Humanize toward the target register (if the user
    specified one) or infer it via
    ${CLAUDE_PLUGIN_ROOT}/skills/codebase-mapper/references/audience-adaptation.md.
    Fix anti-patterns (passive voice, AI boilerplate,
    dense text, missing structure) while preserving all factual content.

    Rewrite files in-place using the Edit tool.
    Provide a change summary when done.

Step 4: AI Trace Removal Pass

After the doc-humanizer restructures the content, run a second pass with the text-humanizer agent to catch remaining AI writing patterns in the prose.

Read the full file on GitHub · 125 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 · 125 lines · 73 tokens per session scan A c6748f9fd501

Subscribe to this mod's changes

humanize-docs is a command published in the GitHub repository acaprino/daodan (8 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 864 once invoked, about $0.0004 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.