Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/atman-33/workhubnpx agentmods add commands/atman-33/workhub/check-claude-plugin-syncWrote 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/atman-33/workhub/check-claude-plugin-sync)<a href="https://agentmods.dev/commands/atman-33/workhub/check-claude-plugin-sync"><img src="https://agentmods.dev/badge/commands/atman-33/workhub/check-claude-plugin-sync.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00420 |
| Opus 5 | $0.00013 | $0.00210 |
| Sonnet 5 | $0.00005 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade C, and why
check-claude-plugin-sync scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `orphan` — Target still exists, but the source plugin no longer provides it. Suggest `rm -rf <targetPath>` only after the user confirms it isn't hand-written. What it actually says
Diagnose whether Claude Code plugin skills and commands are in sync with their OpenCode copies, both project-scope and user-scope.
Run:
node .opencode/scripts/check-claude-plugin-sync.mjs
Steps:
- Run the diagnostic script above.
- Report every drift item with its status verbosely. Map statuses to plain-language advice:
missing— Source has it, target doesn't. Run the appropriate sync command below.stale-source— Source content changed since the last recorded copy. Re-run the sync with--force.diverged— Both source and target changed;--forcewill overwrite the local hand-edits. Point this out to the user before running.orphan— Target still exists, but the source plugin no longer provides it. Suggestrm -rf <targetPath>only after the user confirms it isn't hand-written.silent-user-edit/seeded— Informational only; no action needed.
- If any actionable drift is present, suggest the corresponding remediation commands:
- Project scope:
node .opencode/scripts/sync-claude-skills.mjs [--force] - User scope:
node .opencode/scripts/sync-claude-user-plugins.mjs [--force]
- Project scope:
Notes:
- The exit code is
0when there is no actionable drift, and2when there is. - User-scope discovery runs
claude plugin list; ifclaudeis unavailable, that scope is skipped with a warning. Install the Claude CLI to enable user-scope checks. - The reminder is also injected automatically at the start of every main-session chat message via the
inject-claude-plugin-sync-reminder-plugin. Use this command for a detailed, on-demand full report.
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 · 31 lines · 26 tokens per session scan C 5d41586b969e
check-claude-plugin-sync is a command published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 420 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
debug
Structured debugging with parallel investigation agents.
recover
Diagnose and recover from interrupted or corrupted state.
fix
자주 막히는 문제를 증상→원인→해결 순서로 안내 (초보자용).
lsp-setup
Set up LSP hooks and CLAUDE.md sections for the current project.
trace
Export a Grok session trace locally, or upload it to xAI.