What is larapilot-release?

A release-management workflow for planning and shipping software versions with a release ledger, Gitflow branches, version numbers, assigned specifications, and a final shipping process. Gitflow is a branching convention that separates release work from regular development.

Use it to plan release roadmaps, create release branches, assign specifications to versions, manage parallel releases, or complete a release ceremony.

It keeps release scope, branch state, and shipping decisions in one process instead of leaving them in scattered notes or manual Git commands. It also requires release mode to be enabled before use.

larapilot-release — Skill for Claude Code and Codex by andreapollastri

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 andreapollastri/larapilot --skill larapilot-release

Clone the repo

git clone --depth 1 https://github.com/andreapollastri/larapilot

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/andreapollastri/larapilot/larapilot-release/github.svg)](https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-release)

Your own site

<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-release"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-release/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/andreapollastri/larapilot/larapilot-release"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,041 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	$0.00062	$0.02041
Opus 5.5	$0.00025	$0.00816
Sonnet 5.5	$0.00012	$0.00408
Haiku 4.5	$0.00006	$0.00204

Measured 4d ago against content hash 466ef3e7cb4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

larapilot-release 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 4d 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.

resources/boost/skills/larapilot-release/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Larapilot — Release Management

Manage the versions of the product when data.settings.release_mode is YES: the release ledger, which story targets which version, how far each version is, its release notes, and the Gitflow release branches. Sarah owns Git mechanics; Jack owns policy; Mark owns scope; Albert writes the notes.

Context

php artisan larapilot:context release — with --session={token} when this conversation already holds one, --fresh after a compaction. Read every file under data.runtime.read, none under loaded. Settings, paths, and data.project come from that envelope: no config-show. The contracts are release.md (ledger, Gitflow) and versions.md (the version in every step, numbering, shipping). data.release already holds the version the work is on, each open version's progress, and the stories with none. When the release is shipped in this session, read ship-2.md (on demand) or hand over to /larapilot-ship.

Gate

If data.settings.release_mode is NO, stop and suggest /larapilot-settings → enable Release mode, or php artisan larapilot:settings-set --release-mode=YES.

The Team

Agent	Role
🤖 Zoey	Context estimate; frames release trade-offs
⌨️ Sarah	Git — release branches, tags, parallel branch switching, import from Git tags
🚀 Jack	Release policy, status transitions, ship ceremony with Lars/Oliver
💎 Mark	Scope — which specs belong to which release
📒 Lucille	Deadlines influence roadmap cuts when enabled; milestones per version
📝 Albert	Release notes — the draft rewritten in the PRD language and the words of the product

Config & CLI

php artisan larapilot:release-list {--status=} — every version with progress (stories and points by state, forecast_end, milestone, risk), current, unassigned
php artisan larapilot:release-show {--semver=} — one version: its stories by state, epics, open stories, forecast against its milestone; the version the work is on when omitted
php artisan larapilot:release-notes {--semver=} {--file=} {--write} — the release notes: the draft from the stories, or the team's text; --file= keeps a rewritten text, --write keeps the draft ({paths.release_notes})
php artisan larapilot:release-add {--semver=} {--title=} {--status=} {--specs=} {--branch=} — status in_progress also cuts release/x.y.z (no checkout)
php artisan larapilot:release-set {--semver=} {--status=} {--branch=} {--specs=} {--add-spec=} {--remove-spec=} {--shipped-at=} — moving to in_progress cuts the branch (no checkout); --add-spec= moves the story out of any other open version (moved_from)
php artisan larapilot:release-cut {--semver=} {--no-checkout} {--push} — create release/x.y.z from develop and check it out
php artisan larapilot:release-feature {--semver=} {--spec=} {--slug=} {--no-checkout} {--push} — feature/US-XXX-* from that release
php artisan larapilot:release-sync {--semver=} — merge develop into the release branch
php artisan larapilot:release-ship {--semver=} {--push} {--defer-to=} {--force} — merge to main, tag vX.Y.Z, back-merge develop, mark shipped. It refuses a version with open stories (details.open) unless --defer-to=x.y.z|backlog moves them once the version is out, or --force ships them as not delivered — the user's choice, never yours. When data.settings.hooks is YES it runs the hooks of release.shipped (hooks.md): a refusal with details.hooks means nothing was merged — fix it or report it; a skill it names runs first, then --skill-hooks-done=; the skills under data.hooks.after.skills run before the release is reported
php artisan larapilot:release-import {--dry-run} — rebuild shipped releases from Git semver tags
php artisan larapilot:spec-list {--release=x.y.z|none} — the stories of a version, or of none; every item carries its release

Read the full file on GitHub · 92 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.

4d ago Changed · +7 lines · +31 tokens per session 466ef3e7cb4e
15d ago Changed · -3 lines b797feb85ce8
23d ago Changed · +7 lines 70f7bcaf51f8
24d ago Changed · +2 lines · -70 tokens per session 4864d2950475
29d ago First seen · 79 lines · 101 tokens per session scan A 034f9e1f5d68

Subscribe to this mod's changes

larapilot-release is a skill published in the GitHub repository andreapollastri/larapilot (22 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 2,041 once invoked, about $0.0002 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 2026-09-18.

Git and workflow Project management Releases ai automation boost laravel mockup spec-driven-development

gsd-complete-milestone

Archive completed milestone and prepare for next version.

open-gsd/gsd-core · 16 tokens

codex-issue-coordinator

Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.

owainlewis/blueprint · 59 tokens

larapilot-release