doc-sync

doc-sync is a skill for Claude Code, Codex from hams-ollo/zen-agent-skills. It costs 193 tokens per session (4,443 once invoked), scanned A, original, MIT.

A skill for finding documentation that no longer matches the code or repository, known as documentation drift.

In plain words
What is it for?
Use it to audit documentation after code changes, compare written claims with repository facts, and classify findings for correction or human review.
Why use it?
It separates outdated descriptions from documents that define project rules and from historical records, reducing the risk of changing the wrong document.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

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/hams-ollo/zen-agent-skills/doc-sync
Any agent
npx skills add hams-ollo/zen-agent-skills --skill doc-sync
Clone the repo
git clone --depth 1 https://github.com/hams-ollo/zen-agent-skills

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 doc-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/doc-sync.svg)](https://agentmods.dev/skills/hams-ollo/zen-agent-skills/doc-sync)
Your own site
<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/doc-sync"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/doc-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,443 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 5.1 $0.00193 $0.04443
Opus 5 $0.00097 $0.02221
Sonnet 5 $0.00039 $0.00889
Haiku 4.5 $0.00019 $0.00444

Measured 2d ago against content hash c54cb73b6ccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

doc-sync 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.

.agents/skills/doc-sync/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

doc-sync

Find out which documents went wrong. The kit already has a skill for writing a document that does not exist (doc-author) and one for editing a document you have already decided is wrong (doc-revise). Neither answers the question that generates the work: after the code moved, which of these documents is now lying?

Finding out by hand does not scale and it fails silently, because a missed stale claim reads exactly like a correct one. This skill makes the sweep systematic and grounds every claim it reports in a specific repository fact.

The classification is the whole idea. A naive drift-fixer is worse than no drift-fixer, because documentation is not one kind of thing. A document derived from the code is wrong when it disagrees with the code. A document that governs the code (an approved spec, a rules module, the repository's agent instructions) means the opposite: when it disagrees with the code, the code is wrong, and an agent that "corrects" the document has quietly rewritten the contract to match a bug. A ledger does not drift at all, because an entry describing a past state was never a claim about the present. So this skill decides what a document is before it decides what may be done with it.

It composes doc-revise by reference for the editing half and does not restate its rules, the same way verifier-agent composes spec-conformance.

When to use

  • A change has landed and you want to know which documents it invalidated.
  • A documentation set has not been audited in a while and you suspect stale claims.
  • Before a release, a handoff, or a status update, when documents are about to be trusted by someone who cannot check them.
  • After a rename, a move, or a deletion, when cross-references may now point at nothing.

When not to use

  • The document does not exist yet: use doc-author.
  • You already know what is wrong and just want it changed: use doc-revise.
  • You want to know whether an implementation matches its spec: use spec-conformance. That audits code against a contract; this audits prose against a repository.
  • You want an opinion on how well a document is written, structured, or pitched. Quality is not drift, and neither is a house-style violation.

Read the full file on GitHub · 316 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 Changed · +5 lines c54cb73b6ccc
  2. 5d ago First seen · 311 lines · 193 tokens per session scan A c9f802a94e68

Subscribe to this mod's changes

doc-sync is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 193 tokens to every session and 4,443 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

review

Use when explicitly invoked to review a branch diff (or any diff or files pointed at) with a find-only subagent covering rubric and conventions, change conformance against the AC-N and their runtime-verification evidence, and documentation consistency — one plain-text verdict that reaches lgtm only when no dimension…

ribeirogab/specwright · 107 tokens

implement

Use when explicitly invoked to execute a change's tasks.md from the first unticked step: implement each task, run its validation, commit, then run the quality gate and verify every acceptance criterion by observed behavior. Needs no conversation context — the change folder is the whole input. Trigger on…

ribeirogab/specwright · 79 tokens

ship

Use when explicitly invoked to run the whole change ladder without stopping — ticket, plan, implementation, quality gate, runtime verification, review to lgtm — deciding every open question autonomously and recording each decision in proposal.md. Trigger on '/sw:ship', '$sw:ship', or a request to take something from…

ribeirogab/specwright · 76 tokens

archive

Use when explicitly invoked to close out a change whose branch has already merged: confirm the merge from git alone, then move the change folder under changes/archive/ with its ship date. Trigger on '/sw:archive', '$sw:archive', 'archive this change', or a request to close out a merged change.

ribeirogab/specwright · 65 tokens

gsd-audit-milestone

Audit milestone completion against original intent before archiving.

open-gsd/gsd-core · 17 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens