close

A command for marking a work thread as finished or abandoned. A work thread is a tracked unit of development with tasks and verification results.

In plain words
What is it for?
Use it to close the current or a named thread, record its completion date, clear the active-thread marker, and optionally mark unfinished work as abandoned.
Why use it?
It removes completed work from the active dashboard and records whether it shipped or was stopped, while warning about unfinished items.

Command

Install

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.

agentmods
npx agentmods add commands/paulonasc/orchestra/close
Clone the repo
git clone --depth 1 https://github.com/paulonasc/orchestra
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00790
Opus 5 $0.00000 $0.00395
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash 52ede0292acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

commands/close.md · 75 lines

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 as completed
  • /o close --abandoned — close the active thread as abandoned (work was killed, not shipped)
  • /o close 003-slug — close a specific thread by name

What it does:

  1. Read the thread's progress.yaml
  2. Set status: completed (or status: abandoned with --abandoned)
  3. Set completed_at: YYYY-MM-DD
  4. If closing the active thread, clear state/active-thread.md
  5. 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 completed but the thread has items not marked done, warn: "3 items are still in_progress. Close anyway?"
  • If closing as completed but verification.md has 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 shows MERGED
  • All items in the active thread's progress.yaml are done AND all verification.md items are PASS
  • 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

Read the full file on GitHub · 75 lines

Changes

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.

  1. 2d ago First seen · 75 lines · 0 tokens per session scan A 52ede0292acf

Subscribe to this mod's changes

close is a command published in the GitHub repository paulonasc/orchestra (15 stars, last pushed 4mo 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.