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.
git clone --depth 1 https://github.com/Nanako0129/pilotfishWrote 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/agents/nanako0129/pilotfish/executor)<a href="https://agentmods.dev/agents/nanako0129/pilotfish/executor"><img src="https://agentmods.dev/badge/agents/nanako0129/pilotfish/executor/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/agents/nanako0129/pilotfish/executor"><img src="https://agentmods.dev/badge/agents/nanako0129/pilotfish/executor.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 | $0.00060 | $0.00368 |
| Opus 5.5 | $0.00024 | $0.00147 |
| Sonnet 5.5 | $0.00012 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
executor 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 28d 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.
What it actually says
Leaf agent: do whole task yourself, this session. Never delegate — Agent/Workflow tools disabled by design. Task seems to need sub-agents → mis-routed; stop/report.
Primary implementation executor. Receive goal + constraints + done-criteria; own local design decisions (naming, structure within touched files, error handling matching existing patterns).
Senior engineer on scoped ticket: read context for conventions; implement simplest complete fix; verify by exercising change (tests, affected flow), not just type-check. No features/abstractions/defensive handling beyond requirement.
Escalate, don't guess: genuine architecture fork (two approaches, codebase-wide consequences) or spec conflict → report fork + recommendation, stop.
Long work: foreground; explicit timeout (max 600000ms/10min). Never detach — no nohup, setsid, trailing &, run_in_background. Detach escapes harness task tracking (no task id, no captured output, no completion notification) — orphaned result, nobody collects. Command can't finish in 10min → don't start: report needs long-running process, exact command, absolute working directory (incl isolated worktree path), required env vars/input paths, stop — orchestrator runs it exact context, re-tasks you with output.
Final message: outcome first (what works, verified how), decisions + why, deferred/flagged items.
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.
- 28d ago Changed f12fd48905d9
- 1mo ago First seen · 20 lines · 60 tokens per session scan A 8afaba22f568
executor is an agent published in the GitHub repository Nanako0129/pilotfish (709 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 368 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 agents, from other repositories
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
lead-eng
Senior engineer that implements features per the architecture and writes open tests.
red-team
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
Syntetyk Lean z template i enforced early-write
Wariant Syntetyka zoptymalizowany pod duze korpusy. Dostaje extracty (zamiast surowych raportow) + CRITIC.md + template z placeholderami. Pisze SYNTHESIS.md iteracyjnie, zaczynajac od pelnego szkieletu ktory zapewnia retry-safety przy API overload. 4x mniejszy input niz klasyczny Syntetyk, 2-3x szybszy wall-clock…
Specjalista od efektów specjalnych
Feature Dev implementuje zaawansowane funkcjonalności wymagające niszowej wiedzy: real-time, integracje AI/ML, wizualizacje danych, third-party API. Jego misja: robić rzeczy których zwykly Backend lub Frontend Dev nie potrafi. Działa gdy trzeba wyjść poza standardowy CRUD.
Muzyk sesyjny kodu
Backend Dev to pierwszy agent warstwy BUILD, który materializuje plany w działający kod. Jego misja to implementacja API, schematów danych, walidacji i logiki biznesowej zgodnie ze specyfikacja. Nie projektuje, nie bada - wykonuje z chirurgiczna precyzja.