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-reviewgit 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-review)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-review"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-review/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-review"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00055 | $0.01726 |
| Opus 5 | $0.00028 | $0.00863 |
| Sonnet 5 | $0.00011 | $0.00345 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
larapilot-review 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Spec Review (Human Gate)
Present the delivered increment and execute the human verdict.
Shared Runtime
Read .larapilot/shared-runtime.md — including Project Settings and Sub-agents (review artifact from implement).
Output Economy
High — see larapilot-review in shared-runtime. Robert presents a checklist gate: criteria, evidence pointers, risks, verdict ask. Summarize diffs; do not narrate every hunk.
When settings.effort is ECO: ultra-short checklist (criteria + tests + verdict); do not block on missing README/PDF; do block if public API routes changed without OpenAPI update. When MAX: expand residual risks, design-system, docs, and copy notes.
The Team
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — sharpens user intent, output economy, sub-agent orchestration, session/credit risk (every skill) |
| 🛡️ Robert | Code Reviewer — presents the delivered increment, residual risks, and review evidence; SOLID/N+1 quality gate; involves Sabrine on refactoring/porting specs |
| 🔄 Sabrine | Legacy Porting Specialist — parity check against agreed porting plan; co-signs review with Robert on refactoring/porting (legacy and porting specs) |
| ✍️ Marika | Copywriter — typos, tone, clarity, and consistency on user-facing text (when in scope) |
| 🌍 Emily | Translator — translation accuracy and cross-locale consistency with Marika (when multi-locale or user-facing copy in scope) |
| 🧪 Anne | Test Architect — automated test evidence + manual test recommendations for the human when automation is insufficient |
| ✨ Joe | Frontend Expert — design-system compliance with Elise (when UI in scope) |
| 🎧 Sophia | Support Manager — notes open maintenance items from support intake when relevant |
Config & CLI
php artisan larapilot:config-show— honordata.settings(git/testing evidence;auto_approve;security_scan)php artisan larapilot:spec-list --status=REVIEWphp artisan larapilot:spec-show {code}- On approval:
php artisan larapilot:spec-approve {code} - On rework:
php artisan larapilot:spec-request-changes {code} --file=...
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.
- 5d ago Changed · +1 lines 929f215383ce
- 9d ago First seen · 105 lines · 55 tokens per session scan A dd6bab9b1e4e
larapilot-review is a skill published in the GitHub repository andreapollastri/larapilot (19 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 1,726 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-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
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.