pipeline

pipeline is a command for Claude Code from robertsfeir/atelier-pipeline. It costs 23 tokens per session (1,697 once invoked), scanned A, original, Apache-2.0.

A command that runs a named multi-agent workflow: Robert, Sable, Sarah, Colby, and Ellis. It includes scope sizing, planning, implementation phases, and budget checks.

In plain words
What is it for?
Use it to run the full workflow from the current starting point, choosing a micro, small, medium, or large process as appropriate.
Why use it?
It organizes coding work into defined stages and helps match the process to the size of the change.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the atelier-pipeline plugin — 4 skills, 7 commands, 14 agents, 8 hooks shipped together

Good fit Use it to run the full workflow from the current starting point, choosing a micro, small, medium, or large process as appropriate.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/robertsfeir/atelier-pipeline/pipeline
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.

Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Claude Code.

Or install atelier-pipeline, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 14 agents, 8 hooks.

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 pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/pipeline/github.svg)](https://agentmods.dev/commands/robertsfeir/atelier-pipeline/pipeline)
Your own site
<a href="https://agentmods.dev/commands/robertsfeir/atelier-pipeline/pipeline"><img src="https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/pipeline/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 pipeline

Your own site · 80×15
<a href="https://agentmods.dev/commands/robertsfeir/atelier-pipeline/pipeline"><img src="https://agentmods.dev/badge/commands/robertsfeir/atelier-pipeline/pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,697 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 $0.00023 $0.01697
Opus 5 $0.00012 $0.00848
Sonnet 5 $0.00005 $0.00339
Haiku 4.5 $0.00002 $0.00170

Measured 10d ago against content hash bf344b94a684, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pipeline 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/commands/pipeline.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For skill phases (Robert, Sable, Agatha planning), adopt their persona and run in the main thread. For other subagent phases, invoke them with focused prompts and read results.

Eva assesses scope at the start, recommends a sizing, and presents all four options as a choice list. The recommended option is in bold. The user picks.

  • Micro -- <=2 files, purely mechanical, no tests needed, no brain
  • Small -- single ADR step, <3 files, bug fix. Skip Robert/Sable, auto-advance, pause before commit
  • Medium -- 2-4 ADR steps, typical feature. Pause between major phases, auto-advance within
  • Large -- 5+ ADR steps, new system, multi-concern. Full ceremony, one phase per turn

Example presentation:

This feature sizes as a typical enhancement. Pick your pipeline sizing:

  • Micro
  • Small
  • Medium (recommended)
  • Large

User can override at any point: "upgrade to Large" or "downgrade to Small".

Budget Estimate Gate (after sizing choice, before first agent invocation)

After the user selects sizing, if the sizing triggers the gate (Large always, or Medium when token_budget_warning_threshold is configured), Eva computes and displays the budget estimate before invoking the first agent.

See the <gate id="budget-estimate"> section in pipeline-orchestration.md for the full gate rules table, estimate presentation format, and user cancellation flow.

Read the full file on GitHub · 190 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 · 190 lines · 23 tokens per session scan A bf344b94a684

Subscribe to this mod's changes

pipeline is a command published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,697 once invoked, about $0.0001 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.