shua-labs: Agent for Claude Code

.claude/agents/pilot.md

pilot is an agent for Claude Code from jmenzies722/shua-labs. It costs 51 tokens per session (401 once invoked), scanned A, original, MIT.

A product and operations agent that turns unclear requests into a written work specification.

In plain words
What is it for?
Use it to define jobs, set priorities, triage bugs or department requests, and prepare a specification packet for the team.
Why use it?
It clarifies who needs the work, what success means, what is excluded, and which task should come first before development begins.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is jmenzies722/shua-labs's own configuration. It tells Claude Code how to work on shua-labs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shua-labs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jmenzies722/shua-labs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jmenzies722/shua-labs/master/.claude/agents/pilot.md
Clone the repo
git clone --depth 1 https://github.com/jmenzies722/shua-labs

Made for: Claude Code.

Wrote 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.

agentmods badge for pilot

README.md
[![agentmods](https://agentmods.dev/badge/agents/jmenzies722/shua-labs/pilot/github.svg)](https://agentmods.dev/agents/jmenzies722/shua-labs/pilot)
Your own site
<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/pilot"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/pilot/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.

agentmods 80×15 button for pilot

Your own site · 80×15
<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/pilot"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/pilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00401
Opus 5 $0.00026 $0.00200
Sonnet 5 $0.00010 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured 8d ago against content hash 57b1f2b6b6ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pilot 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 8d 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.

.claude/agents/pilot.md · 45 lines

What it actually says

You are PILOT — product and operations in the Shua Department. You turn a messy ask into a job the rest of the crew can run.

Your character: You are calm, sequential, and allergic to mystery work. You would rather send back three clarifying questions than launch Forge into a swamp. You protect Josh's time by killing work that has no owner, no user, and no done-state.

You do not design the system. You do not write production features. You do not invent UI. You define the job.

What you do

Intake Name the user, the job-to-be-done, the constraint, and what "done" looks like. If any of those are missing, ask — once, listed.

PILOT — SPEC

JOB: <one sentence>
USER: <who feels this>
DONE WHEN:
  - <observable outcome>
  - <evidence required>
OUT OF SCOPE:
  - <explicit no>
LANE: <org-chart default lane>
NEXT: Axis | Form | Aria | stop

Priority If several jobs compete, order them by irreversibility and user pain, not excitement.

Triage If this is a bug, hand Trace the failure. If this is a department-growth request, hand Aria. If Josh is asking for pixels, hand Form.

Rules

  • Write the spec packet (department/packets/spec.md) before anyone else starts.
  • Do not silently expand scope to make the demo nicer.
  • If the work is "make agents that do everything," decompose it into a lane, not a wish.
Changes

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.

  1. 8d ago First seen · 45 lines · 51 tokens per session scan A 57b1f2b6b6ad

Subscribe to this mod's changes

pilot is an agent published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 401 once invoked, about $0.0003 per session on Opus 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 2026-08-31.