close

close is a skill for Claude Code, Codex from regen-coordination/org-os-template. It costs 15 tokens per session (986 once invoked), scanned A, original, MIT.

A session-closing procedure for an org-os workspace. It summarizes completed work, records a dated memory entry, updates task and plan files, and commits and pushes the changes.

In plain words
What is it for?
Use it at the end of an org-os session to document actions, update memory and heartbeat files, refresh plans, and prepare the repository for the next session.
Why use it?
It removes the risk of losing decisions, unfinished work, or the next steps when a work session ends. It keeps the workspace records and task queues aligned with what happened.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

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 skills/regen-coordination/org-os-template/close
Any agent
npx skills add regen-coordination/org-os-template --skill close
Clone the repo
git clone --depth 1 https://github.com/regen-coordination/org-os-template

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for close

README.md
[![agentmods](https://agentmods.dev/badge/skills/regen-coordination/org-os-template/close.svg)](https://agentmods.dev/skills/regen-coordination/org-os-template/close)
Your own site
<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/close"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/close.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 986 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 5.1 $0.00015 $0.00986
Opus 5 $0.00008 $0.00493
Sonnet 5 $0.00003 $0.00197
Haiku 4.5 $0.00002 $0.00099

Measured 5d ago against content hash 53985a81547f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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.

skills/commands/close/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are closing the current org-os session. Read skills/org-os-init/SKILL.md Phase 4 for the full close protocol, then execute these steps:

1. Summarize

List everything accomplished this session using visual indicators:

  • completed items
  • files updated
  • items still open

Render as a ─── Session Summary ─── panel.

2. Write Memory

Append a session entry to memory/YYYY-MM-DD.md (today's date). Create the file if it doesn't exist. Format:

## Session — [HH:MM]

**Focus:** [What was worked on]

### Key Decisions
- [Decision 1]

### Actions Taken
- [x] [What was done]

### Next
- [ ] [What remains]

3. Update HEARTBEAT.md

Move completed tasks to "Recently Completed" with today's date. Add any new tasks that emerged.

4. Update MEMORY.md

If key decisions were made, append to the Key Decisions section (most recent first).

5. Update Plan Queue

If any plan in docs/agent-plans/ changed status (started, completed, new tasks checked off), update the plan file and docs/agent-plans/QUEUE.md.

6. Symbient Close-Pulse (conditional)

If symbient/SEED.md exists in this workspace (habitats are operator-private and gitignored — most checkouts have none), offer the operator a close-pulse:

  • On accept: follow skills/symbient/SKILL.md — the framework copy is authoritative wherever the body has one; the habitat's symbient/SKILL.md is a snapshot and governs only in bodies with no framework skill dir — wake, weave ONE small quilt (2×2 or 3×3) + patchnote into symbient/weave/YYYY-MM-DD.md, and append the anonymous pointer line to today's session block in memory/YYYY-MM-DD.md: > #patchnote-title — <description> · woven: symbient/weave/YYYY-MM-DD.md (path pointer only — never a being's name in tracked files).
  • On decline or any error: continue closing normally. This step never blocks.

Read the full file on GitHub · 116 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. 5d ago First seen · 116 lines · 15 tokens per session scan A 53985a81547f

Subscribe to this mod's changes

close is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 986 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.