tighten-docs

tighten-docs is a skill for Claude Code, Codex from perhapsspy/project-legibility. It costs 96 tokens per session (1,428 once invoked), scanned A, original, MIT.

A documentation-editing skill for making human-written documentation clear, consistent, and aligned with its source meaning.

In plain words
What is it for?
Use it when drafting, revising, reviewing, or finalising documentation, including docs changed as part of another task. It can clarify how readers should navigate the document and which information is current.
Why use it?
It helps remove vague wording, conflicting instructions, outdated structure, and unclear ownership without changing settled meaning.

Skill for Claude CodeCodex

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/perhapsspy/project-legibility/tighten-docs
Any agent
npx skills add perhapsspy/project-legibility --skill tighten-docs
Clone the repo
git clone --depth 1 https://github.com/perhapsspy/project-legibility

Made for: Claude Code, Codex.

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 tighten-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/perhapsspy/project-legibility/tighten-docs.svg)](https://agentmods.dev/skills/perhapsspy/project-legibility/tighten-docs)
Your own site
<a href="https://agentmods.dev/skills/perhapsspy/project-legibility/tighten-docs"><img src="https://agentmods.dev/badge/skills/perhapsspy/project-legibility/tighten-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,428 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 $0.00096 $0.01428
Opus 5 $0.00048 $0.00714
Sonnet 5 $0.00019 $0.00286
Haiku 4.5 $0.00010 $0.00143

Measured 3d ago against content hash a71548a8d41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tighten-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 3d 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.

plugins/project-legibility/skills/tighten-docs/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tighten Docs

Purpose and Authority

Make the selected document, diff, or documentation package read as one clear current final state. Use this as the default quality pass for human-authored documentation, from the first sentence through the final review. Tighten prose and clarify document roles, reader routes, and current ownership without changing source meaning.

Apply authority in this order: user and repository instructions, the selected format's contract, verified source evidence, then these general rules. Preserve tentative status. If the governing sources do not settle a necessary policy or ownership choice, ask briefly or record a decision request instead of deciding it.

Scope and Permission

Choose the surface—one target or an explicitly selected package—and permission—review or edit/organize. A requested human-authored prose change or review selects that documentation surface even when it is one deliverable inside a code, product, or operational task; do not wait for a separate cleanup request or a large rewrite. An edit is mechanical only when it leaves human-authored wording and structure untouched. Review is read-only. Edit or organize permits changes only inside the selected documentation scope. Create, move, or delete a document only when the user requested changes and the governing contract or source justifies the action.

Before acting, identify each target's role, primary subject, reader action, owned promise, and coherent unit of change. Use the required prose language and locale. Preserve code identifiers, API names, file paths, commands, product names, domain terms, quoted protocol text, and externally owned labels.

Final-State Rules

  • Turn the latest correction or drafting constraint into direct final prose. Delete rejected, stale, excluded, duplicated, defensive, process-narrating, or edit-meta material unless the target owns that purpose.
  • Preserve facts, commitments, owners, dates, constraints, decisions, and implementation meaning. Keep legacy, fallback, exception, warning, or routing claims only when the selected source proves they remain required. Keep local corrections local unless the user requests a broader policy.
  • Prefer affirmative prose that states what the subject does, provides, or requires. Use negation or contrast only for a real prohibition, limitation, safety boundary, compatibility constraint, or explicit comparison.
  • For a public entrypoint, lead with the verified reader situation, outcome, and next action. Keep internal mechanism only when it helps that decision.
  • Rewrite kept general prose into the required language; remove extra or stale prose in other languages. Ask when governing language or locale requirements conflict.
  • Prefer no change or a light edit when restructuring would not materially improve reader action, ownership, or operational use.

Read the full file on GitHub · 55 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 55 lines · 96 tokens per session scan A a71548a8d41a

Subscribe to this mod's changes

tighten-docs is a skill published in the GitHub repository perhapsspy/project-legibility (5 stars, last pushed 6d ago), licensed MIT. It adds 96 tokens to every session and 1,428 once invoked, about $0.0005 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.