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.
npx skills add andreapollastri/larapilot --skill larapilot-autopilotgit clone --depth 1 https://github.com/andreapollastri/larapilotWrote 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/andreapollastri/larapilot/larapilot-autopilot)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-autopilot"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-autopilot/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.
<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-autopilot"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-autopilot.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.00884 |
| Opus 5 | $0.00028 | $0.00442 |
| Sonnet 5 | $0.00011 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
larapilot-autopilot 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Autopilot
Batch-run larapilot-plan and larapilot-implement across eligible specs. Optionally auto-approve when settings.auto_approve is YES.
Shared Runtime
Read .larapilot/shared-runtime.md — especially Project Settings (auto_approve).
Output Economy
Minimal — see larapilot-autopilot in shared-runtime. Per spec: US-XXX: {from}→{to} | N tasks | OK or blocker. Batch summary at end. Delegate plan/implement chat style when those flows run.
The Team
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — batch credit risk, recommends --max and checkpoints before long autopilot runs |
| 🛡️ Robert | Code Reviewer — short checklist before auto-approve when enabled |
Config & CLI
php artisan larapilot:config-show— readdata.settings.auto_approvephp artisan larapilot:spec-listphp artisan larapilot:metrics- When auto-approving:
php artisan larapilot:spec-approve {code}
Selection Rules
Read the PRD delivery target (see Delivery Target in shared-runtime). For Full Product or Enterprise, confirm with the user before processing large batches.
Default pipeline per spec:
- If status is
TODO→ runlarapilot-planfor that spec - If status is
PLANNED→ runlarapilot-implementfor that spec - If status is
REVIEWandsettings.auto_approveisYES→ short Robert checklist →spec-approve→DONE - If status is
REVIEWandauto_approveisNO→ leave inREVIEW(human/larapilot-reviewlater) - Skip specs in
IN PROGRESSorDONEunless explicitly requested
Respect user filters:
--epic EP-001(if provided in user message)--max 3(maximum specs to process)--stop-on-failure(halt batch on first blocker)
Execution
Process specs one at a time in priority order (same ordering as spec-next).
After each spec:
- Report progress in one line (Output Economy): code, status transition, task count, blocker if any
- On blocker: log, skip or stop per policy
- When implement finishes at
REVIEWandauto_approveisYES: one-line checklist (criteria met / tests / residual risk) thenspec-approvein the same turn — never invent approval if Critical blockers remain; leave inREVIEWand report
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.
- 9d ago First seen · 71 lines · 56 tokens per session scan A b040dd3b92eb
larapilot-autopilot is a skill published in the GitHub repository andreapollastri/larapilot (19 stars, last pushed 7d ago), licensed MIT. It adds 56 tokens to every session and 884 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cat:decompose-task
Split oversized task into smaller tasks with proper dependency management.
cat:run-retrospective
Run scheduled retrospective analysis, derive action items, and track effectiveness.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
recipe-plan-weekly-schedule
Review your Google Calendar week, identify gaps, and add events to fill them.