What is sync-quickref?

A command that compares an existing Claude Code quick-reference guide with the current setup and updates only the differences.

It checks installed skills, agents, MCP servers, and plugins, rebuilds the guide’s JavaScript, and can optionally create a local commit.

It prevents the guide from becoming outdated while preserving manual changes and showing what was added, removed, or changed.

sync-quickref — Command by aplaceforallmystuff

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 commands/aplaceforallmystuff/cheaters-generator/sync-quickref

Clone the repo

git clone --depth 1 https://github.com/aplaceforallmystuff/cheaters-generator

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 495 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.00495
Opus 5	$0.00008	$0.00247
Sonnet 5	$0.00003	$0.00099
Haiku 4.5	$0.00002	$0.00049

Measured 2d ago against content hash 309aabf6bfbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-quickref 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.

commands/sync-quickref.md · 84 lines

What it actually says

Synchronize your existing Claude Code quick-reference with your current configuration.

Process

Scan current configuration:
- Skills from ~/.claude/skills/*/SKILL.md (parse frontmatter)
- Agents from ~/.claude/agents/ (parse model from frontmatter)
- MCP servers from ~/.claude.json
- Plugins from ~/.claude/plugins/
Compare against existing sheets in the quickref location

Report diff:

## Sync Report

### Added (3)
- [skill] vault-recall - Quick memory search
- [agent] oracle - Book knowledge assimilation
- [agent] workflow-coordinator - Multi-agent orchestrator

### Removed (1)
- [skill] old-skill - No longer exists

### Changed (2)
- [agent] librarian - Model changed: Sonnet → Opus
- [skill] morning-brief - Description updated

Update only affected sheets (preserves manual customizations)
Rebuild javascripts/main.js
Commit locally (optional)

Important: Frontmatter Parsing

Skills (SKILL.md)

---
description: What this skill does
user-invocable: true
---

Agents (.md files)

---
model: opus
tools:
  - Read
  - Write
---

The model field is extracted and displayed as "Model: Opus/Sonnet/Haiku". If no model field exists, display "Model: [not set]".

Output

After sync:

Sync Complete

Files modified:
- sheets/custom-skills.html (3 added, 1 removed)
- sheets/custom-agents.html (2 added, 1 changed)

Build output:
- javascripts/main.js (175 KB, 27 sheets)

Committed: "chore: sync 5 skills, 3 agents (Jan 14, 2026)"

$ARGUMENTS

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.

2d ago First seen · 84 lines · 0 tokens per session scan A 309aabf6bfbf

Subscribe to this mod's changes

sync-quickref is a command published in the GitHub repository aplaceforallmystuff/cheaters-generator (14 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 495 once invoked, about $0.0001 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.

Git and workflow Languages Writing and docs cheatsheet claude claude-code cli developer-tools

sync-quickref

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Process

Important: Frontmatter Parsing

Skills (SKILL.md)

Agents (.md files)

Output

What this file has done since we first saw it

Other commands, from other repositories

add-article

add-video

check-knowledge

quiz-commands

quiz-interactive-ui

quiz