A documentation-maintenance workflow that checks whether project documents still match completed work. It reads a queue, a list of pending tasks, and reviews linked specifications and architecture notes.

Use it to process pending documentation checks, propose updates, apply them after approval, and clear completed queue entries.

It helps prevent project documentation from drifting away from the code and requirements after work is finished.

docs-sync — Skill for Claude Code by AgentureHQ/agenture-loop

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.

Any agent

npx skills add AgentureHQ/agenture-loop --skill docs-sync

Clone the repo

git clone --depth 1 https://github.com/AgentureHQ/agenture-loop

Made for: Claude Code.

Or install agn, the plugin that ships this one along with the rest of its 9 skills, 2 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/agenturehq/agenture-loop/docs-sync/github.svg)](https://agentmods.dev/skills/agenturehq/agenture-loop/docs-sync)

Your own site

<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/docs-sync"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/docs-sync/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/docs-sync"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/docs-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,287 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.01287
Opus 5.5	$0.00031	$0.00515
Sonnet 5.5	$0.00016	$0.00257
Haiku 4.5	$0.00008	$0.00129

Measured 2mo ago against content hash d551c391104d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-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 2mo 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/agn/skills/docs-sync/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs sync (`/agn:docs-sync`)

Purpose

Every time a work unit closes (task → done, feature close, epic close), taskman.sh appends an entry to tasks/docs-sync-queue.txt and prints a "Doc-sync pending" hint. This skill processes that queue: it reviews upstream docs/* files for drift against each closed unit, proposes diffs, and clears the entry once the user approves.

Follow plugins/agn/rules/doc-maintenance.md for what to check and when no update is needed.

Arguments

Position	Variable	Value
`$1`	filter	Optional. Without an argument, process all pending entries. With a number, process only that line of the queue (1-indexed). With a slug or path, process only entries matching that id.

Preconditions

tasks/docs-sync-queue.txt exists. If missing or empty, report "No pending doc-sync entries." and stop.
For each entry being processed, the named unit file must exist (closed task in tasks/done/, feature in tasks/features/, epic in tasks/epics/).

Workflow

Read the queue — Load tasks/docs-sync-queue.txt. Each line:
```
<ISO-8601 timestamp> <kind> <id-or-path>
```
kind is task, feature, or epic. For task, id-or-path is the full path under tasks/done/. For feature/epic, it is the slug.

Apply $1 filter if provided.
For each entry, in order:

a. Load context. Read the closed unit's file. If it carries feature: <slug> or epic: <slug>, also read the parent. If the closed unit links to a spec under docs/<area>/.../-spec.md, read that spec.

b. Check upstream docs in dependency order (per rules/doc-maintenance.md):
1. docs/vision.md
2. docs/spec.md
3. docs/requirements.md
4. docs/architecture.md
5. Linked spec under docs/<area>/.../-spec.md (if applicable)
For each doc, ask:
- Does the doc state a behavior or intent that the closed work changed or invalidated?
- Does the doc lack a behavior or intent that the closed work now exhibits?

Read the full file on GitHub · 89 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.

2mo ago First seen · 89 lines · 78 tokens per session scan A d551c391104d

Subscribe to this mod's changes

docs-sync is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,287 once invoked, about $0.0003 per session on Opus 5.5. 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.

Writing and docs ai-coding claude-code-plugin

connect

Install the scoped Antigravity permission hook.

greenpolo/cc-multi-cli-plugin · 11 tokens

hook-template

Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.

claude-world/director-mode-lite · 39 tokens

check-environment

Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.

claude-world/director-mode-lite · 44 tokens

agents

List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.

claude-world/director-mode-lite · 29 tokens

handoff-gemini

Delegate long-context analysis, research, and large-document summarization to Google Gemini CLI (1M-token context) via non-interactive gemini -p, preserving Claude context. Use when the user says 'use gemini'/'hand off to gemini' or a task needs 100K+ tokens of context.

claude-world/director-mode-lite · 71 tokens

test-runner

Test execution reference: framework detection (pytest/jest/vitest/go/cargo/junit) and correct run/coverage commands, plus failure-analysis steps. Use when running tests, analyzing test failures, or verifying coverage after code changes.

claude-world/director-mode-lite · 50 tokens