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/charannyk06/conductor-oss/claude-mdgit clone --depth 1 https://github.com/charannyk06/conductor-ossWrote 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/instructions/charannyk06/conductor-oss/claude-md)<a href="https://agentmods.dev/instructions/charannyk06/conductor-oss/claude-md"><img src="https://agentmods.dev/badge/instructions/charannyk06/conductor-oss/claude-md.svg" alt="Measured on agentmods" 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 | $0.01705 | $0.01705 |
| Opus 5 | $0.00852 | $0.00852 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
conductor-oss CLAUDE.md 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 6d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Context file for AI coding agents working on Conductor OSS.
What is Conductor OSS
Conductor is a local-first AI agent orchestrator. It turns Markdown kanban boards into dispatched coding tasks, runs them via agent CLIs (Claude Code, Codex, Gemini, Qwen Code, Amp, Hermes, Cursor CLI, OpenCode, Droid, GitHub Copilot, CCR) in isolated worktrees, and streams results through a dashboard with a multi-agent Skills tab.
One command. Markdown-native. Local-first by default.
Architecture
Stack
- Backend: Rust (axum, tokio, sqlx/SQLite). Repo dev scripts use port 4749; the launcher defaults to 4748 and forwards
CONDUCTOR_BACKEND_URL/NEXT_PUBLIC_CONDUCTOR_BACKEND_URLinto the dashboard. - Dashboard: Next.js (packages/web). Repo dev scripts use port 3000; the launcher defaults to 4747.
- CLI: Node.js launcher + Rust native binary
- Runtime: native PTY-based session management; regular sessions stay terminal-first and only ACP dispatcher sessions use the dispatcher conversation pane
- Persistence: SQLite in
.conductor/conductor.db+ Markdown files - Bridge/Access: optional relay, paired-device bridge, and dashboard access-control flows in the same repo
Rust Crates
| Crate | Purpose |
|---|---|
conductor-core |
Types, board parsing, config, task/session models, dispatcher |
conductor-server |
Axum HTTP server, routes, state management, SSE streaming |
conductor-db |
SQLite persistence via sqlx, migrations |
conductor-executors |
Agent adapters, process management, prompt delivery |
conductor-git |
Git/worktree operations |
conductor-relay |
Relay server for bridge and remote terminal flows |
conductor-types |
Shared bridge and transport protocol types |
conductor-watcher |
File system watching (board changes) |
conductor-cli |
Rust CLI binary |
notify-rust |
Desktop notification support |
TypeScript Packages
| Package | Purpose |
|---|---|
packages/cli |
npm CLI entrypoint, native binary launcher |
packages/core |
Shared TS types and schemas |
packages/web |
Next.js 16 dashboard UI, bridge onboarding, and access controls |
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.
- 6d ago First seen · 179 lines · 1,705 tokens per session scan A 00b503828e59
conductor-oss CLAUDE.md is an instructions file published in the GitHub repository charannyk06/conductor-oss (49 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,705 tokens to every session, about $0.0085 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 2026-08-30.
Other instructions, from other repositories
coding-wrapped AGENTS.md
Instructions for senlindesign/coding-wrapped, a project described as: A local-first Coding Wrapped Skill for Claude Code and Codex.
Vibe-Research AGENTS.md
AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.