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-errorgit 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-error)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-error"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-error/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-error"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-error.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 | $0.00092 | $0.02789 |
| Opus 5.5 | $0.00037 | $0.01116 |
| Sonnet 5.5 | $0.00018 | $0.00558 |
| Haiku 4.5 | $0.00009 | $0.00279 |
Grade A, and why
larapilot-error 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 14d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Production errors
You bring the errors of production into the workflow. One tracker, settings.errors_provider, records what the running application throws: when none is set, you ask the user which one. You download what is open, have the user confirm bug by bug, group what they chose into resolution groups, and hand each group to larapilot-triage. You write no spec and no code yourself.
Context
php artisan larapilot:context error — with --session={token} when this conversation already holds one, --fresh after a compaction. Read every file under data.runtime.read, none under loaded: the every-skill files only. The skill an error ends up in runs its own context call with this session.
Output Economy
High — one status line, one table of errors, then the handoffs. The detail of every error is in the report file, not in chat.
The Team (this phase)
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — output economy, session/credit risk (every skill) |
| 🎧 Sophia | Support Manager — confirms each bug, then the handoffs, one group at a time |
| 🧪 Anne | Test Architect — what reproduces the error, the test that pins the fix |
| 🔗 Matt | Integration Manager — the tracker, its credentials in .env, the project in it |
Config & CLI
data.settings.errors,errors_provider, andpaths.supportare in thecontextenvelopephp artisan larapilot:settings-set --errors=YES --errors-provider={id}— the tracker the user chosephp artisan larapilot:errors-status— setting, tracker, credentials, project,hintsphp artisan larapilot:errors-list --new --kind=error --report— the errors with no decision and the ones that came back; writes{paths.support}/errors.mdphp artisan larapilot:errors-plan --codes=BUG12,BUG21— groups confirmed codes by domain and placephp artisan larapilot:errors-link BUG12 --spec=US-012— the spec that fixes the bugphp artisan larapilot:errors-link BUG12 --ignore --reason="…"— left as it is, and whyphp artisan larapilot:errors-resolve BUG12— closes it in the tracker, once the fix is releasedphp artisan larapilot:logs --group --search="QueryException"— the same exception in the logs of this machine
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.
- 14d ago Changed · +1 lines 976a46b6ee29
- 15d ago First seen · 187 lines · 92 tokens per session scan A 22cd89665da0
larapilot-error is a skill published in the GitHub repository andreapollastri/larapilot (22 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 2,789 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 2026-10-02.
Other skills, from other repositories
gsd-debug
Systematic debugging with persistent state across context resets.
gsd-forensics
Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.
kiro-debug
Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
kiro-verify-completion
Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.
gsd-ns-review
quality gates | code review debug audit security eval ui.
gsd-audit-fix
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.