What is Pilot CLAUDE.md?

Repository instructions for Pilot, an AI-powered command-line platform. They document workspace and per-package commands, the project’s pnpm monorepo structure, and pre-commit checks.

Use them to install dependencies, build, test, lint, run the development CLI, type-check packages, and prepare commits in Pilot.

They help coding agents choose the faster package-level checks, understand the repository layout, and avoid bypassing required lint and test checks.

How Medal-Social/Pilot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Medal-Social/Pilot. 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/Medal-Social/Pilot/prod/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Medal-Social/Pilot

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/medal-social/pilot/claude-md/github.svg)](https://agentmods.dev/instructions/medal-social/pilot/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/medal-social/pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/medal-social/pilot/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/medal-social/pilot/claude-md"><img src="https://agentmods.dev/badge/instructions/medal-social/pilot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,867 This file is loaded in full into every session.

When invoked 1,867 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01867	$0.01867
Opus 5.5	$0.00747	$0.00747
Sonnet 5.5	$0.00373	$0.00373
Haiku 4.5	$0.00187	$0.00187

Measured 28d ago against content hash 10efd53db696, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Pilot CLAUDE.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`Exec` interface (in `shell/exec.ts`) is the only place that touches `child_process`. Pass `interactive: true` for commands that need a real TTY (editors, prompts) — otherwise stdin/stdout/stderr are piped and captured.

CLAUDE.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pilot CLI

Medal Social's AI-powered CLI platform. Your AI crew, ready to fly.

Commands

# Workspace-wide
pnpm install                              # bootstrap deps
pnpm build                                # turbo: build all packages
pnpm test                                 # turbo: run all tests
pnpm lint                                 # biome check (warnings OK, errors block)
pnpm lint:fix                             # biome check --write (auto-fix)
pnpm dev                                  # filter to cli dev mode

# Per-package (preferred — much faster than full workspace)
pnpm --filter @medalsocial/pilot test <pattern> -- --run
pnpm --filter @medalsocial/kit test -- --run
pnpm --filter @medalsocial/kit exec tsc --noEmit

# Run the locally-built pilot binary
node packages/cli/dist/bin/pilot.js <command>
# Or globally link after `pnpm build`:
cd packages/cli && npm link

Pre-commit (husky): runs pnpm lint + pnpm test. Biome warnings (e.g. unused admin imports on pre-existing files) are tolerated; errors block. Don't use --no-verify — fix the underlying issue.

Project Overview

Monorepo: pnpm workspaces + Turborepo
CLI: React Ink + Commander.js
AI: Vercel AI SDK + @ai-sdk/anthropic (Claude)
Plugins: @medalsocial/kit (sanity, pencil are planned)
Build: tsc (ESM) + bun build --compile (binary)
Test: Vitest + ink-testing-library + E2E
Lint: Biome (strict, matching medal-monorepo)
Release: Changesets + GitHub Actions with npm trusted publishing/OIDC

Release workflows must use GitHub OIDC trusted publishing and provenance for npm. Do not add NPM_TOKEN or separate RELEASE_APP_* credentials; use the shared GitHub App secrets (APP_ID and APP_PRIVATE_KEY) when a workflow needs a bot token.

Code Conventions

TypeScript strict mode, no any (use unknown + type narrowing)
Use import type for type-only imports (enforced by Biome)
Single quotes, 2-space indent, 100-char line width, trailing commas ES5
No console.log for user output — use process.stdout.write (CLI output) or console.error (errors). There is no shared logger.
Error codes via PilotError(errorCodes.CODE, 'message'), never raw throws to users
All colors via design token system (colors.ts), never hardcoded hex in components

Read the full file on GitHub · 153 lines

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.

28d ago Changed · +4 lines · +41 tokens per session 10efd53db696
2mo ago First seen · 149 lines · 1,826 tokens per session scan A 248605718261

Subscribe to this mod's changes

Pilot CLAUDE.md is an instructions file published in the GitHub repository Medal-Social/Pilot (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 1,867 tokens to every session, about $0.0075 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Git and workflow agent claude codex medalsocial pilot pilot-cli

Pilot CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Pilot CLAUDE.mdMedal-Social/Pilot	Instructions file	2	12d ago	Apache-2.0	A	1,867	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Pilot: Instructions file for Claude Code