What is pipeline-auto?

A controller for carrying a substantial software feature from an idea through implementation with limited interruption. It coordinates agents, checks their evidence, controls scope and budgets, and sends unresolved decisions to a human.

It is for managing long, multi-step implementation runs, including planning, dispatching workers, checking results, handling questions, and escalating decisions that need human input.

It reduces the need to manually coordinate many steps while preventing agents from silently deciding unclear requirements or expanding the work.

pipeline-auto — Skill for Claude Code by kardebadas/claude-plugin

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.

Any agent

npx skills add kardebadas/claude-plugin --skill pipeline-auto

Clone the repo

git clone --depth 1 https://github.com/kardebadas/claude-plugin

Made for: Claude Code.

Or install superb, the plugin that ships this one along with the rest of its 8 skills, 5 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kardebadas/claude-plugin/pipeline-auto/github.svg)](https://agentmods.dev/skills/kardebadas/claude-plugin/pipeline-auto)

Your own site

<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/pipeline-auto"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/pipeline-auto/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/pipeline-auto"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/pipeline-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,830 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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.03830
Opus 5.5	$0.00037	$0.01532
Sonnet 5.5	$0.00019	$0.00766
Haiku 4.5	$0.00009	$0.00383

Measured 21d ago against content hash b1aa8c95cbca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pipeline-auto 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 21d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (examples/controller_walkthrough.py, scripts/pipeline_auto_state.py, tests/check_baseline_evidence.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/superb/skills/pipeline-auto/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pipeline-auto: controller rules

Machines may unblock work. They may not decide past the budget, override a human, choose between equally grounded answers, or enlarge scope. When a rule says escalate, escalating is the decisive action. Deadline, billing and "too cautious" pressure change none of these rules.

The rule this skill reverses

superb:pipeline forbids "a Brain Agent that decides user requirements" (skills/pipeline/references/planning.md:177-181), and its zero-assumption law (skills/pipeline/SKILL.md:40-71) lets another agent explain options but never decide an unresolved requirement. This skill is that Brain Agent, built on purpose. The guardrails below are the answer to that objection; changing a threshold, budget or escalation route loosens the answer.

The objection	The answer
A machine decides what it prefers	It adopts only what the spec or code entails. `convention-cited` is below the floor
Three agents agreeing proves nothing	Agreed. The bar is grounding rung, not votes; reading assignments decorrelate the three
It will decide more and more	3 adoptions per phase, 10 per run, checked before dispatch; only a human extends, at most twice
It will overrule the user	A candidate contradicting `Provenance: human` is rejected at any rung
It will build what nobody asked for	Stage 06 seals the phase set; the tracker creates phases only at stage 07 and only for sealed ids (the ids themselves are not checked against the master plan); `MISSING-FROM-SPEC` is frozen
It will drift from the request	Depth cap 2 from the last human answer
It grades its own homework	Every adoption is labelled `Provenance: quorum`; the terminal report leads with them, weakest first

Want the user consulted at each decision? Use superb:pipeline. This is a different trade, not a better version.

Invocation

Trim $ARGUMENTS and select exactly one mode:

Argument	Mode
empty	Full run from stage 01
`resume`	Resume one compatible `pipeline-auto/v1` run from its files and Git. Never create or replace a run
`status`	Strictly read-only: no lock, write, reconcile, dispatch, test, fix or initialize
anything else	Ask what the user meant. Do not guess a verb

Read the full file on GitHub · 267 lines

Files

What ships with it

51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

21d ago First seen · 267 lines · 93 tokens per session scan A b1aa8c95cbca

Subscribe to this mod's changes

pipeline-auto is a skill published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 18d ago), licensed Apache-2.0. It adds 93 tokens to every session and 3,830 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-24.

Building agents Planning claude-code-plugin claude-code-skills claude-plugin claude-skills codex-cli codex-plugin

import

Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.

XTSoftwareLabs/neatcontext-plugins · 54 tokens

save

Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.

XTSoftwareLabs/neatcontext-plugins · 49 tokens

pipeline-auto