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/claude-mdgit clone --depth 1 https://github.com/conductor-oss/conductorWrote 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/conductor-oss/conductor/claude-md)<a href="https://agentmods.dev/instructions/conductor-oss/conductor/claude-md"><img src="https://agentmods.dev/badge/instructions/conductor-oss/conductor/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 | $0.00662 | $0.00662 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
conductor 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Concrete reason this matters: a curl equivalent for `conductor workflow start --sync` was once written as `POST /api/workflow/{name}/run` — an endpoint that does not exist. Opening `WorkflowResource.java` first would hav How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — conductor (server repo)
Instructions for Claude Code working in this repository.
Writing Documentation
Documentation in this project is derived from source, not composed from memory or intuition. The workflow is: open the source → read what's there → write the doc from what you find. The source is the spec; the doc is a rendering of it.
Concrete reason this matters: a curl equivalent for conductor workflow start --sync was once written as POST /api/workflow/{name}/run — an endpoint that does not exist. Opening WorkflowResource.java first would have given the correct path (POST /api/workflow/execute/{name}/{version}) immediately.
For each content type, start here
REST endpoint or curl example
- Open the controller:
rest/src/main/java/com/netflix/conductor/rest/controllers/ - Find the method by its
@PostMapping/@GetMappingannotation — copy the path literally. - Read the method signature for query params, path variables, and request body.
- Write the curl from what you just read.
CLI command or flag
- Open
conductor-cli/cmd/*.go(separate repo under this workspace). - Find the
cobra.Commandfor the subcommand and read itsFlags()declarations. - Write the example from what you just read — flag names, types, and defaults.
SDK code example (Python, JS, Java, Go)
- Open the SDK source file for the method you're documenting.
- Read the method signature and required parameters.
- If a working test exists for that method, use it as the starting point.
- Write from the signature — do not infer from the method name alone.
Expected output block
- Get real output: run the command, or find it in test fixtures or CI logs.
- Paste verbatim. Do not construct output that "looks right."
- For variable fields (IDs, timestamps), use annotated placeholders like
<workflow-id>.
Editing an existing section
- Before changing anything, read every code block and command in the section.
- Verify each one using the steps above, not just the block you plan to change.
- Fix anything you find while you're there.
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.
- 4d ago First seen · 59 lines · 662 tokens per session scan A 80dd3b9dd863
conductor CLAUDE.md is an instructions file published in the GitHub repository conductor-oss/conductor (32,172 stars, last pushed today), licensed Apache-2.0. It adds 662 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mcp-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/mcp-for-beginners, covering agents.md, project overview, key technologies, architecture and setup commands.
tools AGENTS.md
Instructions for adamw7/tools, covering agents.md, project overview, the adoption pipeline, further reading and module layout.
tools CLAUDE.md
Instructions for adamw7/tools, covering claude.md, project, java version, maven and principles for java development.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
joint CLAUDE.md
Claude Code instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目（模块集由 jdk 版本自动选择 —— 见下方说明）.