sync-ref-wip

sync-ref-wip is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 53 tokens per session (1,429 once invoked), scanned A, original, MIT.

A document-syncing skill for keeping stable reference files and work-in-progress files aligned in both directions.

In plain words
What is it for?
Use it to compare and synchronize files in ref/reference and wip/work-in-progress folders, either as selected pairs or across the folders.
Why use it?
It helps prevent the reference version and the actively edited version from drifting apart, using file dates and content maturity to choose a direction.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the cowork plugin — 5 skills shipped together

Good fit Use it to compare and synchronize files in ref/reference and wip/work-in-progress folders, either as selected pairs or across the folders.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/digital-stoic-org/agent-skills/sync-ref-wip
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 digital-stoic-org/agent-skills --skill sync-ref-wip
Clone the repo
git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install cowork, the plugin that ships this one along with the rest of its 5 skills.

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 sync-ref-wip

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/sync-ref-wip.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/sync-ref-wip)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/sync-ref-wip"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/sync-ref-wip.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,429 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 5
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00053 $0.01429
Opus 5 $0.00026 $0.00714
Sonnet 5 $0.00011 $0.00286
Haiku 4.5 $0.00005 $0.00143

Measured 8d ago against content hash 7483f43d31e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sync-ref-wip 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 8d 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.

cowork/skills/sync-ref-wip/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync ref ↔ wip

Bidirectional alignment between ref (stable reference) and wip (working documents).

Folder aliases: ref folder may be named ref/ or reference/. Wip folder may be named wip/ or work-in-progress/. Detect from the paths provided — both are equivalent.

⚠️ AskUserQuestion Guard

After EVERY AskUserQuestion call, check if answers are empty/blank. If empty: output "⚠️ Questions didn't display (known bug).", present options as numbered text list, WAIT for user reply.

Phase 0: Resolve Files

If called by user ($ARGUMENTS is empty or auto):

  1. Glob for ref folder (ref/ or reference/) and wip folder (wip/ or work-in-progress/) in current directory
  2. If neither found → abort: "⚠️ No ref/ or wip/ folder found. Use /switch to navigate to a project first."
  3. List files in both folders with last-modified dates
  4. Present menu:
    🔄 Sync ref ↔ wip
    
    🔒 ref/ files:
      1. persona-claire-v2.md (Mar 16)
      2. positioning-frameworks-v2.md (Mar 16)
    
    ✏️ wip/ files:
      3. brand-instance.md (Mar 16)
      4. content-marketing.md (Feb 27)
    
    Pick ref + wip file to sync (e.g. "1 3"), or "all" to scan everything:
    
  5. If user picks specific pair → set ref_file and wip_file
  6. If user picks "all" → scan all wip files for ref references, report drift for each pair found, ask which to fix

If called with arguments (two paths or by /save-work):

  • Parse ref_file and wip_file from arguments
  • drift_description from context or "auto-detect"

Phase 1: Detect Direction

Read both files in parallel. Also check timestamps:

stat -c '%Y %y' {ref_file} {wip_file}

Direction heuristics (check in order, first match wins):

Signal Direction Reasoning
ref is newer than wip + wip references old ref terms ref → wip ref was updated, wip hasn't caught up
wip is significantly newer + wip contains structured content absent from ref (versioned headers, decision tables, validated sections marked with dates) wip → ref wip has matured, ref is outdated
drift_description says "stale link" or "dead link" or "old terminology" ref → wip classic drift — wip points to outdated ref
drift_description says "promote" or "mature" or "validated" wip → ref explicit promotion request
wip has [Proposition] markers removed + content reviewed (dates, signatures, version bumps in wip) wip → ref wip graduated past draft stage
Cannot determine ref → wip safe default — ref is source of truth

Read the full file on GitHub · 134 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. 8d ago First seen · 134 lines · 53 tokens per session scan A 7483f43d31e2

Subscribe to this mod's changes

sync-ref-wip is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,429 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens