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.
curl -O https://raw.githubusercontent.com/cesarnml/son-of-anton/main/.agents/skills/closeout-stack/SKILL.mdgit clone --depth 1 https://github.com/cesarnml/son-of-antonWrote 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/skills/cesarnml/son-of-anton/closeout-stack)<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>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 | $0.00034 | $0.01388 |
| Opus 5 | $0.00017 | $0.00694 |
| Sonnet 5 | $0.00007 | $0.00278 |
| Haiku 4.5 | $0.00003 | $0.00139 |
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.
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.
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.
- 8d ago First seen · 86 lines · 34 tokens per session scan A dc8fe7bc988b
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.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
updater_guide
Guidance for checking for and installing Row-Bot updates.