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 agentmods add instructions/conductor-oss/conductor-cli/claude-mdgit clone --depth 1 https://github.com/conductor-oss/conductor-cliWhat 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 | $0.11709 | $0.11709 |
| Opus 5 | $0.05854 | $0.05854 |
| Sonnet 5 | $0.02342 | $0.02342 |
| Haiku 4.5 | $0.01171 | $0.01171 |
Grade B, and why
conductor-cli CLAUDE.md scanned grade B 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 2d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
# Execute any command per task over stdin/stdout How it starts
The opening of the file, as written. The whole thing — 997 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conductor CLI - AI Assistant Reference
Optimized reference for LLMs and AI assistants using the Conductor CLI.
Quick Overview
Conductor CLI (conductor) is a command-line tool for managing Netflix Conductor workflows, executions, tasks, webhooks, and schedules. It connects to Conductor server instances for workflow orchestration.
It also runs a local Conductor server for development (conductor server start), runs task workers
(conductor worker), and manages AI agents (conductor agent, conductor deploy).
Installation
# Homebrew (macOS/Linux)
brew install conductor-oss/conductor/conductor
# Manual download from: https://github.com/conductor-oss/conductor-cli/releases
Never suggest a bare brew install conductor. An unrelated conductor cask exists in
homebrew/cask (Conductor.app from conductor.build), and Homebrew resolves unqualified names
against core/cask before third-party taps — so the bare form installs the wrong package and
leaves no conductor binary on PATH. Tapping first does not help. Always use the
fully-qualified conductor-oss/conductor/conductor.
If the cask is already installed, installing the formula is not enough: Homebrew prints
conductor cask is installed, skipping link and creates no symlink, so conductor --version still
fails. Fix with brew link conductor (keeps both) or brew uninstall --cask conductor before
installing (CLI only). Diagnose with which conductor and brew info --cask conductor.
Authentication
Three methods. Command-line flags override individual settings. Below them, credentials come from a single source — the environment or a config file, never both at once (see Profile Management):
| Method | Command-line Flags | Environment Variables |
|---|---|---|
| Auth Token (recommended) | --auth-token <token> |
CONDUCTOR_AUTH_TOKEN |
| API Key + Secret | --auth-key <key> --auth-secret <secret> |
CONDUCTOR_AUTH_KEY, CONDUCTOR_AUTH_SECRET |
| Config File | --config <path> |
N/A |
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.
- 2d ago First seen · 997 lines · 11,709 tokens per session scan B 7d63b49194c3
conductor-cli CLAUDE.md is an instructions file published in the GitHub repository conductor-oss/conductor-cli (11 stars, last pushed 14d ago), licensed Apache-2.0. It adds 11,709 tokens to every session, about $0.0585 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.