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-plangit 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-plan)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-plan"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-plan/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-plan"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Prompt Injection · line 124 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 127 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 128 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 129 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 130 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00032 | $0.03783 |
| Opus 5.5 | $0.00013 | $0.01513 |
| Sonnet 5.5 | $0.00006 | $0.00757 |
| Haiku 4.5 | $0.00003 | $0.00378 |
Grade A, and why
larapilot-plan 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Spec Planning
Produce a detailed implementation plan for one spec and persist it via the CLI.
Context
php artisan larapilot:context plan — 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, data.project, data.dev_docs, and data.frontend come from that envelope: no config-show.
Read an on_demand file as soon as the spec calls for it — decide right after Stage 1, before the team brief: UI → ux-1.md (+ ux-2.md, and ux-3.md for public pages); a package, a panel, tenancy, or a non-trivial data model → delivery-3.md; CI/CD, CLI, scripts, versioning → delivery-4.md; third-party APIs or locales → delivery-5.md; personal data → ship-2.md; open deploy choices → ship-1.md; legacy or client documents → discovery-3.md. A surface the spec does not touch is not read.
When data.settings.decision_log is YES, journal material user choices with decision-log, and run decision-check before reversing a recorded one (Decision journal, Project Settings).
Output Economy
Split. Team brief: 1–3 sentences per agent. Chat between stages: status and blockers only. plan_body and task bodies stay detailed execution contracts — do not strip them.
Autopilot spec worker
When the handoff says you are the autopilot spec worker, read spec-worker.md (on demand) and follow Spec worker. Explore inline (no nested explore). Write .larapilot/tmp-payload-{code}-plan.json and stop before validate-plan / spec-plan. Do not AskQuestion — return BLOCKED. The final message is OK plan {code} | N tasks or the two-line BLOCKED form. No team brief in that message. Standalone /larapilot-plan is unchanged.
The Team
🤖 Zoey · 📒 Lucille · 🔎 Tom · 📐 John · 🗄️ Mike · 💡 Sebastian · 🔗 Matt · 🌍 Emily · 💰 Aurora · ⚖️ Violet · 📈 Emma · 💬 Lauren · 🎨 Elise · ✨ Joe · 📱 Ricky · 📝 Albert · ✍️ Marika · 👾 Andrew · ⌨️ Sarah · 🔄 Sabrine · 🔧 Alex · 🧪 Anne. Mike owns data/schema tasks; Sarah owns Git mechanics (conflicts/rebase), CLI, forge automation, CI pipeline scripts, and Linux/server scripting whenever those surfaces appear (partner Jack on gates/deploy).
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 Changed 70b2171a1268
- 20d ago Changed · -9 lines e13fe5a4727a
- 28d ago Changed · +4 lines 3e61e9cd7d28
- 29d ago Changed · +2 lines · -45 tokens per session f5fbe7f88b24
- 1mo ago Changed 8c59c05ff541
- 1mo ago Changed 1464c4e27ca6
- 1mo ago Changed 01123c729fca
- 1mo ago Changed · +2 lines 5e4072dea674
- 1mo ago First seen · 160 lines · 77 tokens per session scan A 322654f0d7c6
larapilot-plan is a skill published in the GitHub repository andreapollastri/larapilot (23 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 3,783 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
gsd-plan-review-convergence
Cross-AI plan convergence - replan until review concerns are resolved.
gsd-ns-manage
Invoke this Pi skill with /skill:gsd-ns-manage.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
dependency-upgrade
Plan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update nodemodules", "fix vulnerabilities"…
forensics
Post-mortem a failed GSD auto-mode run. Traces symptom to root cause via .gsd/ activity, journal, metrics, and lock artifacts, producing a filing-ready bug report with file:line refs and a fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash"…