A documentation-sync tool for downloading official Anthropic reference material into a project and checking what changed. It also examines how those changes may affect project documentation and related components.

Use it when refreshing reference docs, checking documentation changes, or reviewing possible effects on validators, plugins, and project documentation. A dry run can preview changes without overwriting files.

It avoids relying on outdated copies of product documentation and helps distinguish confirmed updates from files that could not be downloaded.

How joaquimscosta/arkhe-claude-plugins configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to joaquimscosta/arkhe-claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/joaquimscosta/arkhe-claude-plugins/main/.claude/skills/sync-docs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

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/joaquimscosta/arkhe-claude-plugins/sync-docs.svg)](https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/sync-docs)

Your own site

<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/sync-docs"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/sync-docs.svg" alt="Measured on agentmods" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,142 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	$0.00068	$0.01142
Opus 5	$0.00034	$0.00571
Sonnet 5	$0.00014	$0.00228
Haiku 4.5	$0.00007	$0.00114

Measured 7d ago against content hash 075e690dfd43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sync-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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/sync_and_diff.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/sync-docs/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Docs

Sync official Anthropic documentation into docs/reference/ and produce an impact analysis report.

Quick Start

Run the sync and diff script:

scripts/sync_and_diff.py

Preview changes without overwriting:

scripts/sync_and_diff.py --dry-run

Execution

Phase 1: Sync & Diff

Execute scripts/sync_and_diff.py (or with --dry-run if $ARGUMENTS contains --dry-run)

Capture the whole JSON document. Never pipe it through tail/head — sync_health and sync_result are at the top of the output and are the first things to read.
Gate on sync_health before anything else:
- If sync_health.complete is true, proceed to step 3.
- If sync_health.complete is false, stop and do not report impacts for the files in sync_health.not_fetched. Their "changed": false only means "not downloaded", not "up to date". Print sync_health.warning, re-run the sync once to retry the failed files, and if they still fail, report them explicitly as UNVERIFIED in the summary table rather than as unchanged.
update-claude-docs.sh exits 0 when at least one file downloads, so a non-zero exit code is not the signal — a 1-of-8 sync also exits 0. Trust sync_health, not sync_result.exit_code.
Parse the rest of the JSON output
Display a summary table of changed/unchanged files, using download_status to mark any file that was not fetched

Phase 2: Impact Analysis

For each changed file, perform the following analysis. See WORKFLOW.md for detailed steps.

2a. Skill Validator Impact (CRITICAL priority)

Check discrepancies in the JSON output:

skill_frontmatter_keys.in_docs_not_validator (CRITICAL): New fields in SKILLS.md the validator will reject as unknown (FM009). Report exact fields and line in validate_skill.py to update (ALLOWED_FRONTMATTER_KEYS, ~line 151).
skill_frontmatter_keys.in_validator_not_docs (WARNING): Fields the validator allows but SKILLS.md no longer documents. May be from SUBAGENTS.md (valid for context: fork) or deprecated.
subagent_frontmatter_keys (INFO): New subagent fields from SUBAGENTS.md. Not all are valid in skill frontmatter — report for context. Only flag fields that overlap with skill usage (e.g., maxTurns, mcpServers, memory, skills).
hook_events.in_docs_not_validator (CRITICAL): New hook events the validator will reject (HK001). Report the line to update (VALID_HOOK_EVENTS, ~line 1021).
hook_events.in_validator_not_docs (WARNING): Hook events the validator knows but docs no longer list.
memory_scopes: Review manually if SUBAGENTS.md changed — check if memory scope options expanded.

Read the full file on GitHub · 110 lines

Files

What ships with it

4 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.

7d ago First seen · 110 lines · 68 tokens per session scan A 075e690dfd43

Subscribe to this mod's changes

sync-docs is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 1,142 once invoked, about $0.0003 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 2026-08-30.

Claude Code Research Writing and docs ai-agents ai-developer-tools anthropic claude-code-agents claude-code-plugins

skill-capture

Turn a recurring in-session workflow into a reusable Claude Code skill. Load this the moment you notice you have run the SAME multi-step sequence (same ordered steps or commands, small variation allowed) about three times in the current session, or when open candidates are waiting in .credo/skill-candidates.md at…

Marcel-Bich/marcel-bich-claude-marketplace · 170 tokens

test-writer

Generate comprehensive tests including unit, integration, and property-based tests.

kivo360/OmoiOS · 12 tokens

git-workflow

Git branching, commits, and PR workflow following GitFlow conventions.

kivo360/OmoiOS · 12 tokens

refactor-planner

Plan safe refactoring with dependency analysis, impact assessment, and rollback strategies.

kivo360/OmoiOS · 14 tokens

cross-cutting-checklist-generator

Detect when a concern is scattered across many places in a project (config keys, enums, translations, feature flags, API endpoints, doc references) and auto-generate a project-local checklist so that same concern is never partially updated again. Use whenever you add or change something that also exists in several…

Marcel-Bich/marcel-bich-claude-marketplace · 94 tokens

openspec-workflow

Write the spec before the code, then check the built thing against it — so agents build what was agreed, not what they invented.

ToruAI/toru-claude-agents · 32 tokens

arkhe-claude-plugins: Skill for Claude Code