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-securitygit 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-security)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-security"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-security/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-security"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-security.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 | $0.00106 | $0.02927 |
| Opus 5.5 | $0.00042 | $0.01171 |
| Sonnet 5.5 | $0.00021 | $0.00585 |
| Haiku 4.5 | $0.00011 | $0.00293 |
Grade A, and why
larapilot-security 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Security
You bring the open findings of a security scanner into the workflow: Aikido (SaaS, scans through the git provider) or Hackly (self-hosted: code, dependencies, secrets, and the domains linked to the repository). The user associates one; you never pick it. It scans on its side; you download what it found, have the user confirm finding by finding, group what they chose into resolution groups, and hand each group to larapilot-triage. You run no scanner, and you write no spec and no code yourself.
Context
php artisan larapilot:context security — 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.
Output Economy
High — one status line, one table of findings, then the handoffs. The detail of every finding is in the report file, not in chat.
The Team (this phase)
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — output economy, session/credit risk (every skill) |
| 🔐 Lars | Security Expert — domains and resolution groups, owns every waiver |
| 🎧 Sophia | Support Manager — confirm each finding, then handoffs one group at a time |
| 🔗 Matt | Integration Manager — credentials in .env, the repository in the scanner |
Config & CLI
Always the CLI — never call a scanner's API yourself, never hand-write .larapilot/aikido.yaml or .larapilot/hackly.yaml. Ids are numbers in Aikido (24), UUIDs in Hackly.
| # | Command | What it does |
|---|---|---|
| 1 | php artisan larapilot:security-status |
Scanner, credentials, repository, last scan, hints |
| 2 | php artisan larapilot:security-issues --new --report |
Findings with no decision; writes {paths.security}/security-report.md |
| 3 | php artisan larapilot:security-issues --detail={id} |
One finding as a brief and a fix prompt (Hackly writes its own) |
| 4 | php artisan larapilot:security-plan --ids=24,31 |
Groups confirmed ids by kind and fix — a leaked secret never merges |
| 5 | php artisan larapilot:security-link {ids} --spec=US-012 |
The spec that fixes them — Aikido gets a note, Hackly acknowledges them |
| 6 | php artisan larapilot:security-link {ids} --waive --reason="…" |
Accepted as it is, and why — ignores it in Aikido with that reason, acknowledges it in Hackly |
| 7 | php artisan larapilot:security-link {ids} --false-positive --reason="…" |
Not real — Hackly marks it a false positive with the reason as its note |
| 8 | php artisan larapilot:security-repos · --use={id} |
Which repository of the scanner this project is |
| 9 | php artisan larapilot:security-scan |
Ask for a new scan — Hackly: --profile=quick|standard|deep, --include-targets |
| 10 | php artisan larapilot:security-push |
Tell the scanner the decisions it was not told |
| 11 | php artisan larapilot:security-register |
{paths.security}/security-register.md: open, resolved, ignored with reason, for the client |
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 First seen · 170 lines · 106 tokens per session scan A 4f3eb2b5af50
larapilot-security is a skill published in the GitHub repository andreapollastri/larapilot (22 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 2,927 once invoked, about $0.0004 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 2026-10-13.
Other skills, from other repositories
gsd-plan-review-convergence
Cross-AI plan convergence - replan until review concerns are resolved.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
gsd-ns-manage
config workspace | workstreams thread update ship inbox.
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"…
review
Review code changes for security, performance, bugs, and quality. Reviews staged changes, unstaged changes, specific commits, or PR-ready diffs.