ai-ready-product-workflow-v2: Command for Claude Code

.claude/commands/sync-check.md

sync-check is a command for Claude Code from karlng279/ai-ready-product-workflow-v2. It costs 0 tokens per session (663 once invoked), scanned A, original, MIT.

A command for checking whether project artifacts are out of sync after one has changed. An artifact is a project document or design file, and the command uses the artifact-sync process to create targeted patches.

In plain words
What is it for?
Use it with a feature name and changed artifact path to inspect dependencies and prepare synchronization changes for review.
Why use it?
It helps reveal which related files may now be stale and avoids updating them blindly or regenerating them wholesale.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is karlng279/ai-ready-product-workflow-v2's own configuration. It tells Claude Code how to work on ai-ready-product-workflow-v2 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-ready-product-workflow-v2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to karlng279/ai-ready-product-workflow-v2. 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/karlng279/ai-ready-product-workflow-v2/main/.claude/commands/sync-check.md
Clone the repo
git clone --depth 1 https://github.com/karlng279/ai-ready-product-workflow-v2

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.

agentmods badge for sync-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/karlng279/ai-ready-product-workflow-v2/sync-check/github.svg)](https://agentmods.dev/commands/karlng279/ai-ready-product-workflow-v2/sync-check)
Your own site
<a href="https://agentmods.dev/commands/karlng279/ai-ready-product-workflow-v2/sync-check"><img src="https://agentmods.dev/badge/commands/karlng279/ai-ready-product-workflow-v2/sync-check/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.

agentmods 80×15 button for sync-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/karlng279/ai-ready-product-workflow-v2/sync-check"><img src="https://agentmods.dev/badge/commands/karlng279/ai-ready-product-workflow-v2/sync-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 663 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00663
Opus 5 $0.00000 $0.00331
Sonnet 5 $0.00000 $0.00133
Haiku 4.5 $0.00000 $0.00066

Measured 5d ago against content hash f0f12f8254ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sync-check 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 5d 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.

.claude/commands/sync-check.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sync-check

Run artifact synchronization analysis for a feature after an artifact has changed. Detects stale upstream and downstream artifacts and generates surgical sync patches.

Usage

/sync-check [feature-name] [changed-artifact-path]

Examples:

/sync-check export-customs-clearances design/wireframes.md
/sync-check my-feature po/usd/ST-003.md
/sync-check my-feature po/prd.md
/sync-check my-feature                   # will ask which artifact changed

If feature-name is omitted, ask for it. If changed-artifact-path is omitted, ask which artifact was recently modified.


Execution Steps

Step 0 — Confirm Target

  1. Parse $ARGUMENTS for feature-name and changed-artifact-path
  2. Resolve the full path: features/{feature-name}/{changed-artifact-path}
  3. Read the changed artifact
  4. If change_summary is not present in its frontmatter, ask:

    "What changed in this artifact? Describe in one sentence."

  5. If change_type is not present, classify it using the artifact-sync skill methodology

Step 1 — Activate artifact-sync

Read skills/artifact-sync/SKILL.md (or .agent/skills/artifact-sync/SKILL.md if installed). Follow all steps defined in the skill:

  • Classify the change type
  • Build the impact set (forward and backward)
  • Produce the Stale Impact Report
  • Generate surgical patches

Step 2 — Present the Report

Output the full Stale Impact Report as defined in the skill. Wait for the user to review before proceeding.

Step 3 — Apply Patches (with confirmation)

After presenting the report, ask:

"Apply approved patches now, or review manually first?"

If "apply now":

  • For MEDIUM and LOW severity patches: apply automatically, list files updated
  • For HIGH severity patches: show each patch's before/after and ask "Apply this patch? (yes/no)" before writing

If "review manually":

  • Print the list of files that need updates
  • Stop — user can run /sync-check again when ready to apply

Step 4 — Post-Sync Summary

Read the full file on GitHub · 86 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. 5d ago First seen · 86 lines · 0 tokens per session scan A f0f12f8254ad

Subscribe to this mod's changes

sync-check is a command published in the GitHub repository karlng279/ai-ready-product-workflow-v2 (6 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 663 tokens. 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 2026-09-05.