Borrowing it
Nothing to install: this file belongs to kamiazya/scopes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamiazya/scopes/main/.claude/commands/pm/sync.mdgit clone --depth 1 https://github.com/kamiazya/scopesWrote 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.
[](https://agentmods.dev/commands/kamiazya/scopes/sync)<a href="https://agentmods.dev/commands/kamiazya/scopes/sync"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/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.
<a href="https://agentmods.dev/commands/kamiazya/scopes/sync"><img src="https://agentmods.dev/badge/commands/kamiazya/scopes/sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00504 |
| Opus 5.5 | $0.00000 | $0.00202 |
| Sonnet 5.5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
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.
What it actually says
Sync
Full bidirectional sync between local and GitHub.
Usage
/pm:sync [epic_name]
If epic_name provided, sync only that epic. Otherwise sync all.
Instructions
1. Pull from GitHub
Get current state of all issues:
# Get all epic and task issues
gh issue list --label "epic" --limit 1000 --json number,title,state,body,labels,updatedAt
gh issue list --label "task" --limit 1000 --json number,title,state,body,labels,updatedAt
2. Update Local from GitHub
For each GitHub issue:
- Find corresponding local file by issue number
- Compare states:
- If GitHub state newer (updatedAt > local updated), update local
- If GitHub closed but local open, close local
- If GitHub reopened but local closed, reopen local
- Update frontmatter to match GitHub state
3. Push Local to GitHub
For each local task/epic:
- If has GitHub URL but GitHub issue not found, it was deleted - mark local as archived
- If no GitHub URL, create new issue (like epic-sync)
- If local updated > GitHub updatedAt, push changes:
gh issue edit {number} --body-file {local_file}
4. Handle Conflicts
If both changed (local and GitHub updated since last sync):
- Show both versions
- Ask user: "Local and GitHub both changed. Keep: (local/github/merge)?"
- Apply user's choice
5. Update Sync Timestamps
Update all synced files with last_sync timestamp.
6. Output
🔄 Sync Complete
Pulled from GitHub:
Updated: {count} files
Closed: {count} issues
Pushed to GitHub:
Updated: {count} issues
Created: {count} new issues
Conflicts resolved: {count}
Status:
✅ All files synced
{or list any sync failures}
Important Notes
Follow /rules/github-operations.md for GitHub commands.
Follow /rules/frontmatter-operations.md for local updates.
Always backup before sync in case of issues.
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 · 83 lines · 0 tokens per session scan A 2799ad79df2d
sync is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 11mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 504 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 2026-08-31.
sync compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| synckamiazya/scopes | Command | 2 | 11mo ago | Apache-2.0 | A | 0 | Claude Code |
| CHANGELOGbytedance/UI-TARS-desktop | Command | 40k | 29d ago | Apache-2.0 | A | 0 | Claude Code |
| diagnose-deeptracezscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 29 | Claude Code |
| create-access-rulezscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 20 | Claude Code |
| investigate-incidentzscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 27 | Claude Code |
| review-attack-surfacezscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 27 | Claude Code |
| create-timeout-rulezscaler/zscaler-mcp-server | Command | 55 | 10d ago | MIT | A | 21 | Claude Code |