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.
git clone --depth 1 https://github.com/paulonasc/orchestraWrote 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/paulonasc/orchestra/close)<a href="https://agentmods.dev/commands/paulonasc/orchestra/close"><img src="https://agentmods.dev/badge/commands/paulonasc/orchestra/close/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/paulonasc/orchestra/close"><img src="https://agentmods.dev/badge/commands/paulonasc/orchestra/close.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 | $0.00790 |
| Opus 5.5 | $0.00000 | $0.00316 |
| Sonnet 5.5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
close 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/o close — Mark thread as completed
Marks the active thread (or a specified thread) as shipped. This removes it from dashboard aggregation and session-start injection.
Usage:
/o close— close the active thread ascompleted/o close --abandoned— close the active thread asabandoned(work was killed, not shipped)/o close 003-slug— close a specific thread by name
What it does:
- Read the thread's
progress.yaml - Set
status: completed(orstatus: abandonedwith--abandoned) - Set
completed_at: YYYY-MM-DD - If closing the active thread, clear
state/active-thread.md - Confirm:
Thread 001-instagram-integration closed as completed (2026-03-23).
24/24 items done, all verification PASS.
Cleared active thread — run /o list to pick the next one.
Safety checks:
- If closing as
completedbut the thread has items not markeddone, warn: "3 items are still in_progress. Close anyway?" - If closing as
completedbutverification.mdhas FAIL or PENDING items, warn: "2 verification items haven't passed. Close anyway?" - These are warnings, not blocks — the user might have good reasons (scope cut, moved to another thread, etc.)
Proactive close detection
You don't wait for the user to remember /o close. Watch for these signals during normal conversation and prompt the user:
Signals that a thread is done:
- User says "merged", "PR merged", "landed", "shipped", "deployed", "this is done", "we're good", "all set"
- You check a PR status (via
gh pr view,gh pr status, etc.) and it showsMERGED - All items in the active thread's
progress.yamlaredoneAND allverification.mditems arePASS - User asks to start a new thread or switches context to different work
When you detect a signal, use AskUserQuestion once — don't nag:
{thread-name} looks complete. Closing removes it from the dashboard — you can always reopen with
/o reopen.RECOMMENDATION: Choose A if all work is merged and verified.
A) Close it — mark as completed B) Not yet — still verifying
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 First seen · 75 lines · 0 tokens per session scan A 52ede0292acf
close is a command published in the GitHub repository paulonasc/orchestra (15 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 790 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 2026-08-30.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.