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.
npx agentmods add commands/atman-33/workhub/sync-claude-user-pluginsgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/sync-claude-user-plugins)<a href="https://agentmods.dev/commands/atman-33/workhub/sync-claude-user-plugins"><img src="https://agentmods.dev/badge/commands/atman-33/workhub/sync-claude-user-plugins.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 | $0.00025 | $0.00383 |
| Opus 5 | $0.00013 | $0.00192 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
sync-claude-user-plugins 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 yesterday.
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
Copy commands and skills from the installed user-scope Claude plugins into the global OpenCode directories.
Run:
node .opencode/scripts/sync-claude-user-plugins.mjs
To overwrite commands or skills that already exist in the OpenCode global directories, run:
node .opencode/scripts/sync-claude-user-plugins.mjs --force
Steps:
- Verify
claude plugin listsucceeds in the current environment. - If needed, override the default roots with environment variables before running the script.
- Run the script above.
- Report the copied, skipped, missing, and parse-warning items shown in the script output.
Notes:
- By default, source plugins are resolved under
~/.claude/plugins/marketplacesand OpenCode global files are resolved under~/.config/opencodefor the current runtime environment. - To target a different install location, set
CLAUDE_PLUGINS_ROOTand/orOPENCODE_GLOBAL_ROOTbefore running the script. - Commands are copied into
<OPENCODE_GLOBAL_ROOT>/command. - Skills are copied into
<OPENCODE_GLOBAL_ROOT>/skills. - Example for WSL targeting Windows-installed tools:
export CLAUDE_PLUGINS_ROOT=/mnt/c/Users/<your-user>/.claude/plugins/marketplaces
export OPENCODE_GLOBAL_ROOT=/mnt/c/Users/<your-user>/.config/opencode
node .opencode/scripts/sync-claude-user-plugins.mjs
- OpenCode does not support plugin subfolders for discovery, so name collisions are handled by skipping existing targets unless
--forceis provided.
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.
- yesterday First seen · 41 lines · 25 tokens per session scan A 4906d4041a5d
sync-claude-user-plugins is a command published in the GitHub repository atman-33/workhub (2 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 383 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 2026-09-03.
Other commands, from other repositories
open
Open the memex vault in Finder or Obsidian.
done
Queue an obsidian-chronicle session summary in the background.
budget-mode
Switch Octopus model routing to the configured budget tier.
squirrel-show
Show or hide a status line segment (git, cost, tokens, pr, …).
process
Stage 2 processing. Scan inbox/raw/ for unprocessed captures, add full frontmatter (domain, type, tags, description), and move to inbox/ready/. Also scans thinking/ and shows a promotion reminder.
brief
Cold-start session orientation — use when starting fresh or returning after a long absence (days or weeks). Scales depth to how long you've been away. Not for quick mid-session checks (use /tools:status) or planning (use /tools:overview).