A finalization procedure for a tracked development task, called an episode, using its manifest, linked files, and completion receipts. A receipt is a record showing that a stage or result was completed.

Use it at the end of a normal, short, or otherwise completed workflow to verify records and produce the final task summary.

It creates a bounded final summary without rereading full conversation transcripts. It also checks that the recorded receipts are valid before closing the task.

closeout — Skill for Claude Code and Codex by EZotoff/ez-omo-config

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.

Any agent

npx skills add EZotoff/ez-omo-config --skill closeout

Clone the repo

git clone --depth 1 https://github.com/EZotoff/ez-omo-config

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/closeout/github.svg)](https://agentmods.dev/skills/ezotoff/ez-omo-config/closeout)

Your own site

<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/closeout"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/closeout/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/closeout"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/closeout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,255 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.01255
Opus 5.5	$0.00041	$0.00502
Sonnet 5.5	$0.00020	$0.00251
Haiku 4.5	$0.00010	$0.00126

Measured 11d ago against content hash 195a811202dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

closeout 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 11d 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/closeout/SKILL.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.

Closeout — Episode Terminal Summary (Standalone, Idempotent)

Invocation Paths

Every terminal path MUST invoke this skill (it references and enforces closeout; start-work does not own it):

Atlas post-F-wave — after the last F-box verdict is recorded in the plan's ## Execution Record.
In-session completion — when a lane finishes outside Atlas (e.g. /episode checkpoint lanes).
Lite completion — --lite lanes at teardown-receipt time.

Inputs (bounded — read NOTHING else)

Episode manifest: .omo/episodes/<slug>/manifest.yaml (schema v0.2: phases[] with append-only sequence-numbered receipts, learnings[], follow_ups[]).
Linked artifacts referenced by receipts (plan doc, .reviews.md ledger, evidence files).
Receipts — including bounded session_evidence refs: message IDs + immutable excerpts.

NEVER read full session transcripts. If a receipt's session_evidence is missing or unresolvable, that is a degraded-path input, not an invitation to go look.

Procedure

Verify receipts first: run scripts/episode-receipt.sh verify (from the episode's project root) against the manifest. Closeout consumes validated receipts only. Record the exit code.
Read the manifest, receipts, and linked artifacts listed above.
Write the closeout to .omo/episodes/<slug>/closeout.md with the four output sections below.
Emit the terminal receipt as the final line block of closeout.md, then close the episode: scripts/episode-receipt.sh append <episode_dir> --closeout --status <complete|degraded|failed> (the command hashes closeout.md as evidence and sets the manifest to closed). This step is NOT optional — without it the episode stays open and lint flags it. If closeout.md cannot be produced, record why and close with --status failed.
Disposition learnings (from learnings[]): mark each selected entry promoted (evidence + owner/scope → hand to wisdom-write), duplicate, or discarded. Unselected entries stay ephemeral — no diary.

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.

11d ago Changed 195a811202dd
17d ago First seen · 75 lines · 102 tokens per session scan A 94b3ee61bd20

Subscribe to this mod's changes

closeout is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 1,255 once invoked, about $0.0004 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 2026-09-29.

Project management ai-coding coding-assistant developer-productivity oh-my-opencode opencode opencode-config

launch

Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort…

Yeachan-Heo/oh-my-claudecode · 113 tokens

omc-plan

Strategic planning with optional interview workflow.

Yeachan-Heo/oh-my-claudecode · 11 tokens

ask-navigator

Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it…

Yeachan-Heo/oh-my-claudecode · 78 tokens

harbor

Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence.…

Yeachan-Heo/oh-my-claudecode · 83 tokens

project-session-manager

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.

Yeachan-Heo/oh-my-claudecode · 23 tokens

ultragoal

Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.

Yeachan-Heo/oh-my-claudecode · 38 tokens