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-implementgit 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-implement)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-implement"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-implement/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-implement"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.04373 |
| Opus 5.5 | $0.00020 | $0.01749 |
| Sonnet 5.5 | $0.00010 | $0.00875 |
| Haiku 4.5 | $0.00005 | $0.00437 |
Grade A, and why
larapilot-implement 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Spec Implementation
Execute a planned spec: code, tests, review, handoff to REVIEW.
Context
php artisan larapilot:context implement — with --session={token} when this conversation already holds one, --fresh after a compaction. Read every file under data.runtime.read, none under loaded, and an on_demand file only when its when comes true. Settings (effort, git_mode, testing), paths, data.project, data.dev_docs, and data.frontend come from that envelope: no config-show.
The task bodies are the execution contract: each carries its own Git Deliverables, Test Data, and Domain Docs sections, written by the plan. The files you read hold the rules behind them — do not re-derive them, and do not apply a rule for a setting value the files do not show.
Output Economy
High. After each task, one line and nothing else:
TASK-04 → Invoice policy → Pest 4 passed → TASK-05
Copy that shape; do not add a second sentence. No table. Do not repeat the diff, filenames already committed, or test output the command already returned. One extra line per blocker: BLOCKED TASK-04 — reason. The only question this skill asks on its own is a mockup deviation, before it is coded (Mockup fidelity). Robert/Lars findings: one bullet per finding, severity first. Spec handoff before spec-review: 6 lines maximum. A table is allowed only in that handoff.
When settings.effort is ECO: never spawn sub-agents; defer docs except OpenAPI when public/partner API routes change and the developer domain docs under {paths.dev_docs}, which are written every time (terse prose, same sections); short inline Robert/Lars checklist only; one-line status. When MAX: always run Robert + Lars as sub-agents when available (else inline deep), expand residual-risk notes.
Autopilot spec worker
When the handoff says you are the autopilot spec worker, read spec-worker.md (on demand) and follow Spec worker. Run Phases 0–1 only. spec-start already ran — do not call it again, and do not call task-done, spec-review, code-log, usage-log, or decision-log. Do not spawn Robert, Lars, or any other sub-agent. Do not AskQuestion — return BLOCKED plus a done: line; a mockup deviation is such a block (BLOCKED TASK-NN — mockup deviation: {screen}: {what} ({why})). The final message is OK implement {code} | N tasks | pr: {url or —} or the two-line BLOCKED form. Standalone /larapilot-implement still runs Phase 2 and Phase 3.
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 · +6 lines 50262e1c5a9b
- 20d ago Changed · -24 lines e8ace12a1f7d
- 28d ago Changed · -8 lines 5bbe76551ce8
- 29d ago Changed · +6 lines · -7 tokens per session f4324d70da54
- 1mo ago Changed · +5 lines d3b1bf0a8791
- 1mo ago Changed · +3 lines 435d2f2c7c35
- 1mo ago First seen · 135 lines · 56 tokens per session scan A 85dda6783d4e
larapilot-implement is a skill published in the GitHub repository andreapollastri/larapilot (23 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 4,373 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 2026-08-30.
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"…