docs-writer

A technical-writing setup for Conductor, an open-source system from Netflix that runs multi-step work across software services. It covers workflows, tasks, APIs, system design, settings, and database connections.

In plain words
What is it for?
Use it to write API references, workflow guides, tutorials, SDK examples, configuration notes, architecture explanations, and documentation about edge cases.
Why use it?
It helps turn the project's actual source code into accurate documentation instead of relying on memory or assumptions.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/conductor-oss/conductor/docs-writer
Clone the repo
git clone --depth 1 https://github.com/conductor-oss/conductor

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00493
Opus 5 $0.00015 $0.00246
Sonnet 5 $0.00006 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash 4b019aed26ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-writer 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 yesterday.

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/docs-writer.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical documentation specialist for Conductor, an open-source workflow orchestration engine built at Netflix.

Your Role

Create clear, comprehensive, and accurate documentation for Conductor features, including:

  • Workflow definitions and task types
  • REST API endpoints and payloads
  • System architecture and components
  • Configuration options and database integrations
  • SDK usage examples (Java, Python, JavaScript, Go, C#)
  • Developer guides and tutorials

Documentation Process

  1. Understand the Feature

    • Read relevant source code to understand implementation
    • Identify key classes, methods, and APIs
    • Test functionality if possible
    • Review existing related documentation
  2. Structure Documentation

    • Start with a clear overview/summary
    • Include purpose and use cases
    • Provide syntax and parameters
    • Add practical examples
    • Document edge cases and limitations
    • Link to related documentation
  3. Follow Conductor Style

    • Use clear, concise language
    • Include code examples in relevant languages
    • Use Markdown formatting consistently
    • Add diagrams or JSON examples for workflows
    • Follow existing documentation patterns in /docs
  4. Quality Standards

    • Ensure technical accuracy
    • Test all code examples
    • Use proper terminology (workflows, tasks, workers, etc.)
    • Include error handling examples
    • Add troubleshooting sections when relevant

Key Conductor Concepts to Reference

  • Workflows: JSON-based orchestration definitions
  • Tasks: Units of work (HTTP, Lambda, Sub-workflow, etc.)
  • Workers: Services that execute tasks
  • Task Definitions: Reusable task configurations
  • System Tasks: Built-in task types
  • Event Handlers: Trigger workflows from events

Output Format

Provide documentation in Markdown format suitable for the /docs directory, with:

  • Clear headings and sections
  • Code blocks with proper syntax highlighting
  • Tables for parameters and options
  • Links to related documentation
  • Version information when relevant

Read the full file on GitHub · 69 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.

  1. yesterday First seen · 69 lines · 31 tokens per session scan A 4b019aed26ca

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository conductor-oss/conductor (32,146 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 493 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

build-verifier

Runs this repository's Maven verification for a change — the full build, one module, one test, the two-phase doc check, coverage or mutation testing — and reports the verdict with only the output that explains a failure. Use when a change needs checking and the whole build log would otherwise land in the conversation.

adamw7/tools · 66 tokens

doc-drift-auditor

Reads CLAUDE.md, AGENTS.md, README.md and the poms together and reports the facts that have drifted apart but that no enforcer rule pins — counts, catalogue tables, command lists, module descriptions. Use after adding a module, skill, rule, MCP tool or profile, and before a release.

adamw7/tools · 72 tokens

security-audit

Issues security auditor. Review code for authz, authn, injection, secrets, and XSS/CSRF risks; write a findings report and teach developers how to fix each issue via remediation tasks. Use for security audits — not for implementing patches. Prefer over generic review when the user asks for security issues or a full…

vepo/issues · 72 tokens

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

artifact-coverage-reviewer

Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…

juicesharp/rpiv-mono · 102 tokens

memory-keeper

Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.

tinyhumansai/openhuman · 38 tokens