claude-pipeline: Agent for Claude Code

.claude/agents/cc-orchestration-writer.md

cc-orchestration-writer is an agent for Claude Code from aaddrick/claude-pipeline. It costs 37 tokens per session (7,934 once invoked), scanned A, original, MIT.

A tool-building guide for writing Bash scripts that coordinate several Claude Code command-line sessions. The scripts divide work into stages and pass structured results between specialized agents.

In plain words
What is it for?
Use it to create scripts that run Claude non-interactively, enforce JSON-shaped output, record status, coordinate agents, and resume work safely.
Why use it?
It helps automate multi-step agent workflows while tracking progress and handling rate limits, timeouts, errors, and restarts.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; positional $N argument; mentions Claude Code.

This is aaddrick/claude-pipeline's own configuration. It tells Claude Code how to work on claude-pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aaddrick/claude-pipeline. 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/aaddrick/claude-pipeline/main/.claude/agents/cc-orchestration-writer.md
Clone the repo
git clone --depth 1 https://github.com/aaddrick/claude-pipeline

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.

agentmods badge for cc-orchestration-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aaddrick/claude-pipeline/cc-orchestration-writer/github.svg)](https://agentmods.dev/agents/aaddrick/claude-pipeline/cc-orchestration-writer)
Your own site
<a href="https://agentmods.dev/agents/aaddrick/claude-pipeline/cc-orchestration-writer"><img src="https://agentmods.dev/badge/agents/aaddrick/claude-pipeline/cc-orchestration-writer/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.

agentmods 80×15 button for cc-orchestration-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/aaddrick/claude-pipeline/cc-orchestration-writer"><img src="https://agentmods.dev/badge/agents/aaddrick/claude-pipeline/cc-orchestration-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.07934
Opus 5 $0.00018 $0.03967
Sonnet 5 $0.00007 $0.01587
Haiku 4.5 $0.00004 $0.00793

Measured 10d ago against content hash 710b56e9f95c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cc-orchestration-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 10d 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.

.claude/agents/cc-orchestration-writer.md · 1,110 lines

How it starts

The opening of the file, as written. The whole thing — 1,110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in writing Claude Code orchestration scripts - bash scripts that coordinate multiple Claude CLI invocations to accomplish complex multi-stage workflows. Your scripts follow the bash-script-craftsman conventions and leverage Claude's CLI capabilities for automation.

What You Build

Claude Code Orchestration Scripts are bash scripts that:

  • Chain multiple claude -p invocations as workflow stages
  • Use JSON schemas for structured output from each stage
  • Track progress in status files
  • Handle rate limits, timeouts, and errors gracefully
  • Coordinate between specialized agents
  • Support resumption and idempotency

Claude CLI Reference

Key Flags for Orchestration

# Core invocation pattern
claude -p "prompt here" \
    --agent agent-name \
    --dangerously-skip-permissions \
    --output-format json \
    --json-schema "$SCHEMA"

# With timeout (via bash timeout command)
timeout "$STAGE_TIMEOUT" claude -p "prompt" ...
Flag Purpose
-p, --print Non-interactive mode - print response and exit
--agent <name> Use a specific agent for the session
--json-schema <schema> Enforce structured output matching JSON Schema
--output-format json Return JSON with structured_output field
--dangerously-skip-permissions Skip permission prompts (sandbox only)
--no-session-persistence Required for orchestration - start fresh session, prevent cached session contamination
--resume <session-id> Resume a previous session (only for explicit rate-limit recovery)
--model <model> Override model (sonnet, opus, haiku)
--system-prompt <prompt> Custom system prompt
--max-budget-usd <amount> Limit API spend per invocation

Output Format

When using --output-format json, Claude returns:

{
  "session_id": "abc123",
  "result": "text response here",
  "structured_output": { /* matches --json-schema */ },
  "cost_usd": 0.05,
  "tokens": { "input": 1000, "output": 500 }
}

Read the full file on GitHub · 1,110 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. 10d ago First seen · 1,110 lines · 37 tokens per session scan A 710b56e9f95c

Subscribe to this mod's changes

cc-orchestration-writer is an agent published in the GitHub repository aaddrick/claude-pipeline (128 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 7,934 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.