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.
npx agentmods add skills/perhapsspy/project-legibility/tighten-docsnpx skills add perhapsspy/project-legibility --skill tighten-docsgit clone --depth 1 https://github.com/perhapsspy/project-legibilityWrote 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.
[](https://agentmods.dev/skills/perhapsspy/project-legibility/tighten-docs)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
- 3d ago First seen · 55 lines · 96 tokens per session scan A a71548a8d41a
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.
Other skills, from other repositories
author
Write a new doc in the right place with the right name. Use when asked to "write a doc", "where should this doc go", "add an ADR", "document this decision", "new spec", or "new feature plan".
router
Find the right doc before reading code. Use when asked "where is X documented", "is there a spec/ADR for X", "what's the roadmap", "open bugs", "read the docs about X", or "share the docs".
changelog
Record shipped work in the monthly changelog (append-only). Use when something ships or when asked "what changed", "add to changelog", "release notes", or "what shipped this month".
init
Set up docflow in a repo with no docs yet: scaffold the docs tree, write docflow.json, add agent guidance. Use when asked to "set up docflow", "initialize docs", "scaffold docs", or "make this repo use docflow".
check
Friendly docflow readiness check: one status, one reason, and the exact next command. Use when asked if docflow is set up, ready, or "what do I do next".
doctor
Read-only docflow diagnosis: scans docs, config, changelog, and links, then recommends init, adopt, or repair. Use when asked "check docs setup", "should I set up docflow", "why is docflow not working", or "doctor".