An autonomous orchestration skill that combines product discovery, planning, implementation, and code review to take a feature idea to a finished branch. It manages saved run state, approval gates, parallel work, reviewer feedback, and recursive fixes.

Use it when you want an idea clarified, planned, implemented, reviewed, and fixed in one pipeline, including parallel tasks with dependencies and separate worktrees.

It coordinates the handoffs between separate development stages so a long feature run can resume and continue without repeatedly rebuilding context.

pipeline — 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

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

Your own site

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

Your own site · 80×15

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

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,160 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	$0.00024	$0.02160
Opus 5.5	$0.00010	$0.00864
Sonnet 5.5	$0.00005	$0.00432
Haiku 4.5	$0.00002	$0.00216

Measured 1mo ago against content hash 54fe1061c4a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (examples/controller_walkthrough.py, scripts/pipeline_state.py, tests/fixtures/pressure/extract_phase04_stimulus.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/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Superb Pipeline

Purpose

Pipeline is a thin controller around Superpowers. It keeps the approved design, plans, decisions, execution state, and evidence in project files so a compacted or restarted session can continue without inventing requirements or repeating work.

The controller owns orchestration and durable transitions. It does not reimplement the skills that investigate, plan, implement, debug, review, and verify the work.

Invocation

Trim whitespace from this complete argument string, then select exactly one mode:

$ARGUMENTS

Argument	Mode
empty	Full run: begin with planning.
`resume`	Resume one compatible v2 run from its files and Git evidence. Never create or replace a run.
`status`	Strictly read-only inspection. Do not lock, write, reconcile, dispatch, test, fix, or initialize.
anything else	Stop and ask what the user meant. Do not guess a verb or expose an internal remediation mode.

Use the whole argument string, never an indexed positional placeholder.

For resume or status, use references/persistence.md. If no run is identifiable, report that. If multiple runs qualify, ask the user which one. Recency is not selection authority.

Zero-assumption law

Before making any required decision, inspect these sources in order:

the user's explicit instructions;
recorded explicit user answers;
the approved design/specification;
the approved master plan and phase plans;
explicit written repository rules.

If they explicitly answer the question, cite and follow the answer. If they do not, or they conflict:

stop only the affected work;
record the exact question and blocked task/gate;
ask the user and wait;
persist the explicit answer;
update affected approved artifacts transparently when required;
resume through the validated controller transition.

Another agent may investigate facts and explain options, but it cannot decide an unresolved requirement for the user. Generic approval or “continue” does not answer a choice. Do not ask again when an explicit applicable answer is already recorded.

Read the full file on GitHub · 226 lines

Files

What ships with it

34 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.

1mo ago Changed · -1,227 lines · -56 tokens per session 54fe1061c4a5
1mo ago Changed · +87 lines edf006c7042f
1mo ago Changed · +130 lines ed46e240e27b
1mo ago Changed · +211 lines 2f4010563745
1mo ago Changed · +213 lines 455a78348899
1mo ago First seen · 812 lines · 80 tokens per session scan A 8d4b19726a87

Subscribe to this mod's changes

pipeline is a skill published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 21d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,160 once invoked, about $0.0001 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 2026-08-31.

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