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/sync-claude-skillsWrote 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-skills)<a href="https://agentmods.dev/commands/atman-33/workhub/sync-claude-skills"><img src="https://agentmods.dev/badge/commands/atman-33/workhub/sync-claude-skills/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/atman-33/workhub/sync-claude-skills"><img src="https://agentmods.dev/badge/commands/atman-33/workhub/sync-claude-skills.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 | $0.00020 | $0.00331 |
| Opus 5.5 | $0.00008 | $0.00132 |
| Sonnet 5.5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
sync-claude-skills 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 1mo 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
Copy the vault's own .claude/skills/ and .claude/agents/ into
.opencode/skills/ and .opencode/agent/.
Agents are rewritten into OpenCode's frontmatter on the way (mode: subagent,
a tools map, no model: — Claude's short model aliases are not OpenCode model
ids). Both directories are generated: edit the vault-local source, then re-run
this. Plugin skills/agents are not handled here — they reach OpenCode through
/sync-claude-user-plugins (enabled user-scope plugins only).
Run:
node .opencode/scripts/sync-claude-skills.mjs
To overwrite copies that already exist, run:
node .opencode/scripts/sync-claude-skills.mjs --force
To also delete copies whose source is gone (e.g. a deleted vault-local skill, or a plugin copy stranded by the move to user-scope-only plugins), run:
node .opencode/scripts/sync-claude-skills.mjs --prune
--prune only deletes manifest-tracked orphans; hand-written targets the
manifest never recorded are left alone. The two flags combine (--force --prune).
Steps:
- Run the script above from the vault root.
- Report the copied, skipped, and missing items shown in the script output.
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.
- 1mo ago Changed · +11 lines · -2 tokens per session 0be6bb0a6af7
- 1mo ago First seen · 30 lines · 22 tokens per session scan A 5f8e1a02f3a3
sync-claude-skills is a command published in the GitHub repository atman-33/workhub (3 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 331 once invoked, about $0.0001 per session on Opus 5.5. 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.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
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).
tm
Tmux session management - create, list, cleanup isolated sessions, short for /ar:tmux.
busy
Inhibit sleep only while Claude is actively processing.
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.