son-of-anton: Skill for Claude Code

.agents/skills/closeout-stack/SKILL.md

soa-closeout-stack is a skill for Claude Code, Codex from cesarnml/son-of-anton. It costs 34 tokens per session (1,388 once invoked), scanned A, original, MIT.

A release step for a stacked pull request, where several related changes are delivered in order. It merges an approved completed phase into the repository’s configured main branch.

In plain words
What is it for?
Use it after a multi-ticket delivery has been reviewed and approved for final merge.
Why use it?
It handles the repetitive work of applying reviewed changes in sequence and closing the related pull requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is cesarnml/son-of-anton's own configuration. It tells Claude Code and Codex how to work on son-of-anton itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything son-of-anton configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cesarnml/son-of-anton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cesarnml/son-of-anton/main/.agents/skills/closeout-stack/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cesarnml/son-of-anton

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 soa-closeout-stack

README.md
[![agentmods](https://agentmods.dev/badge/skills/cesarnml/son-of-anton/closeout-stack.svg)](https://agentmods.dev/skills/cesarnml/son-of-anton/closeout-stack)
Your own site
<a href="https://agentmods.dev/skills/cesarnml/son-of-anton/closeout-stack"><img src="https://agentmods.dev/badge/skills/cesarnml/son-of-anton/closeout-stack.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,388 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01388
Opus 5 $0.00017 $0.00694
Sonnet 5 $0.00007 $0.00278
Haiku 4.5 $0.00003 $0.00139

Measured 8d ago against content hash dc8fe7bc988b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

soa-closeout-stack 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 8d 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.

.agents/skills/closeout-stack/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Closeout Stack

Merge a completed stacked delivery phase onto the configured closeoutBranch after the developer approves all PRs. Before running any command below, read closeoutBranch from orchestrator.config.json in the repo root (or .son-of-anton/orchestrator.config.json's default if the consumer repo has no override — both default to main when the key is absent) and set it as $CLOSEOUT_BRANCH for the rest of this session. Every command below uses that variable — substitute the actual configured value, which is main unless the repo's config says otherwise.

Primary Path

git checkout "$CLOSEOUT_BRANCH"
bun run closeout-stack --plan <plan-path>

Processes each ticket in stack order via git merge --squash (3-way, robust against parent patches). For each ticket: fetch + reset local $CLOSEOUT_BRANCH to origin/$CLOSEOUT_BRANCH, squash-merge the ticket branch, commit with PR title, push to origin/$CLOSEOUT_BRANCH, close PR, delete remote branch. Produces one squash commit per ticket on $CLOSEOUT_BRANCH when squash succeeds.

If merge --squash hits conflicts (common after earlier tickets were squash-merged so SHAs diverge from the stacked branches), closeout-stack resets to origin/$CLOSEOUT_BRANCH, reads the PR's commits via gh pr view --json commits, and lands them in order with git cherry-pick (merge commits use -m 1). When a picked commit is already fully present on $CLOSEOUT_BRANCH (empty patch), it runs git cherry-pick --skip and continues. That may yield multiple commits on $CLOSEOUT_BRANCH for one ticket. If cherry-pick fails for any other reason, recover manually using the checklist below.

Delivery artifact mirror (state.json, reviews/, handoffs/)

Closeout reads .agents/delivery/<plan-key>/state.json from the repo you run the command in. The orchestrator only writes delivery artifacts in the current working directory where you ran deliver — so across a stacked phase, reviews/ and handoffs/ files often land in different ticket worktrees, not only the last one.

Read the full file on GitHub · 86 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. 8d ago First seen · 86 lines · 34 tokens per session scan A dc8fe7bc988b

Subscribe to this mod's changes

soa-closeout-stack is a skill published in the GitHub repository cesarnml/son-of-anton (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,388 once invoked, about $0.0002 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.