Claude-Pipeline: Command for Claude Code

.claude/commands/auto-pipeline.md

auto-pipeline is a command for Claude Code from TheAstrelo/Claude-Pipeline. It costs 0 tokens per session (1,234 once invoked), scanned A, original, MIT.

A command that starts a repository's automated pipeline engine with a task and optional settings. The engine runs multiple phases, routes work to models, applies checks, retries failures, and saves results.

In plain words
What is it for?
Use it to start or resume automated development pipelines, choose execution settings, skip selected phases, control commits, and manage saved run history.
Why use it?
It provides one entry point for running the existing pipeline without duplicating its implementation. Resume, provider, profile, policy, testing, commit, and retention options can adjust the run.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions Codex.

This is TheAstrelo/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 TheAstrelo/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/TheAstrelo/Claude-Pipeline/main/.claude/commands/auto-pipeline.md
Clone the repo
git clone --depth 1 https://github.com/TheAstrelo/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 auto-pipeline

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/auto-pipeline"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/auto-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,234 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 $0.00000 $0.01234
Opus 5 $0.00000 $0.00617
Sonnet 5 $0.00000 $0.00247
Haiku 4.5 $0.00000 $0.00123

Measured 11d ago against content hash 36a4580c9f0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

auto-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 11d 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/auto-pipeline.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automated Pipeline

Run: /auto-pipeline [--provider=auto|claude|codex] [--profile=yolo|fast|standard|paranoid] [--policy-rollout=legacy|shadow|enforced] [--resume=RUN_ID] [--skip-arm] [--skip-ar] [--skip-pmatch] [--model-strong=MODEL] [--model-fast=MODEL] [--no-commit] [--allow-untested-commit] [--retention-days=N] [--retention-max-runs=N] <task>

$ARGUMENTS


What this is

A thin wrapper over the real pipeline engine, run-pipeline.sh at the repo root. It does not reimplement the 13 phases — it launches the one script that actually executes them and relays the result. The engine owns model routing, gates, validators, retries, and artifacts.

(This replaced ~2,400 lines of bash-embedded-in-markdown that no interpreter ever ran. If you are editing pipeline behavior, edit run-pipeline.sh, not this file.)

How to run it

  1. Parse $ARGUMENTS into flags plus a task description. If there is no task, ask the user for one and stop — do not run the engine without a task.

  2. Launch the engine once, from the project root, via the Bash tool. Pass the flags through and give the task as a single quoted argument. Set PIPELINE_NONINTERACTIVE=1 so a failed HARD gate halts (exit 3) instead of blocking on a prompt with no TTY:

    PIPELINE_NONINTERACTIVE=1 bash run-pipeline.sh --profile=<profile> "<the task>"
    

    The engine parses --profile, --skip-arm, --skip-ar, --skip-pmatch, --provider, --resume=RUN_ID, --model-strong=, --model-fast=, --no-commit, --allow-dirty, --allow-untested-commit, --policy-rollout=, retention controls, budget caps, and --mode itself — pass whatever the user supplied.

    A resume invocation must repeat the original task and effective options. The engine proceeds only if its atomic checkpoint and all bound engine, configuration, Git, worktree, verification-policy, ledger, attempt, and artifact hashes still match.

    This is long-running (it spawns up to 13 provider subprocesses, several minutes, real API spend). Launch it in the background and monitor, or tell the user it will take a while before starting.

Read the full file on GitHub · 97 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. 11d ago First seen · 97 lines · 0 tokens per session scan A 36a4580c9f0e

Subscribe to this mod's changes

auto-pipeline is a command published in the GitHub repository TheAstrelo/Claude-Pipeline (45 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,234 tokens. 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.