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/gitpcl/openorchestrator/wt-statusgit clone --depth 1 https://github.com/gitpcl/openorchestratorWhat 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 | $0.00010 | $0.00383 |
| Opus 5 | $0.00005 | $0.00192 |
| Sonnet 5 | $0.00002 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
wt-status 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 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.
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
Worktree Claude Status
View Claude activity across all worktrees - see what each Claude session is working on, recent commands sent, and overall progress.
Current Context
Git worktrees:
!git worktree list 2>/dev/null || echo "No worktrees found"
tmux sessions (owt-*):
!tmux list-sessions 2>/dev/null | grep owt || echo "No owt sessions active"
Instructions
- Run:
owt status - Present the status table showing:
- Worktree name
- Branch
- Activity status (working/idle/blocked/waiting/completed)
- Current task description
- Number of commands sent to this worktree
- Last update time
- Highlight any worktrees that are blocked or have errors
- Show summary stats (how many active, idle, blocked)
- Suggest actions like:
- View detailed status:
owt status <worktree-name> - Set task:
owt status <worktree-name> --set-task "description" - Send command:
owt send <worktree-name> "your instruction" - Mark completed:
owt status <worktree-name> --set-status completed
- View detailed status:
Usage Examples
# View all worktree statuses
owt status
# View specific worktree in detail
owt status feature/auth
# Update what a worktree is working on
owt status feature/auth --set-task "Implementing OAuth flow"
# Mark a worktree as blocked
owt status feature/api --set-status blocked --notes "Waiting for API spec"
# Output as JSON for programmatic use
owt status --json
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 · 54 lines · 10 tokens per session scan A 9b7830338c0c
wt-status is a command published in the GitHub repository gitpcl/openorchestrator (5 stars, last pushed 28d ago), licensed MIT. It adds 10 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 2026-08-31.
Other commands, from other repositories
orchestrate
複数Issueを並列オーケストレーション（準備→開発→PR→マージ→UAT→修正ループ→完了）.
release
Command "release" from sageox/ox, covering release workflow, step 1: pre-flight checks, verify on main branch, clean working directory, run quality gates (run lint and tests in parallel) and step 1c: smoke tests (requires sageoxcipassword).
issue-enhance
Issue内容を分析し、ユーザーに質問しながら不足情報を補完・更新.
multi-stage-design-review
設計書の4段階レビュー（通常→整合性→影響分析→セキュリティ）と指摘対応を自動実行.
multi-stage-issue-review
Issue記載内容の多段階レビュー（通常→影響範囲）×2回と指摘対応を自動実行.
issues-exec-plan
複数Issueの並列作業可否を分析し、実行計画をまとめるエピックIssueを作成.