agent-pipeline

agent-pipeline is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 10 tokens per session (3,946 once invoked), scanned A, original, MIT.

A multi-agent workflow for carrying out an /auto go SPEC-ID task. It coordinates agents that lead, build, and review work under a defined execution owner.

In plain words
What is it for?
Use it for SPEC implementation with solo work, a Lead/Builder/Guardian team, or additional provider review.
Why use it?
It separates task ownership and review responsibilities when implementing a specification.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for SPEC implementation with solo work, a Lead/Builder/Guardian team, or additional provider review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/agent-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.

Any agent
npx skills add Insajin/autopus-adk --skill agent-pipeline
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

Made for: Claude Code, Codex.

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 agent-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/agent-pipeline/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/agent-pipeline)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/agent-pipeline"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/agent-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 agent-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/insajin/autopus-adk/agent-pipeline"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/agent-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,946 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00010 $0.03946
Opus 5 $0.00005 $0.01973
Sonnet 5 $0.00002 $0.00789
Haiku 4.5 $0.00001 $0.00395

Measured 12d ago against content hash 29ab7c139c1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-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 12d 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.

.omp/skills/agent-pipeline/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OMP Native Agent Pipeline

This is the default multi-agent execution contract for /auto go SPEC-ID [--execution-owner omp|orca] on OMP. Autopus owns phase and quality policy; exactly one selected owner owns the task DAG.

Activation

Flag Execution
omitted --execution-owner owner omp, receipt source default
--execution-owner omp owner omp, receipt source explicit
--execution-owner orca owner orca, receipt source explicit
--solo owner omp current session performs the work directly
--team owner omp task batch with explicit Lead/Builder/Guardian responsibilities
--multi selected owner's normal gates plus risk-tiered provider dissent review

The team and provider axes are orthogonal:

  • --team selects owner omp native task batch with explicit Lead/Builder/Guardian responsibilities.
  • --multi selects provider-diverse planning and review, not team execution topology.
  • --team --multi composes team execution with provider-diverse planning and review.
  • without --team or --solo, owner omp uses the default native task batch pipeline.
  • --team conflicts with --solo and owner orca.
  • Lead, Builder, and Guardian coordinate only through native task, hub, and todo; the main OMP session owns the checklist and DAG.

Parse the owner exactly once before any task, DAG-owning todo, OMP subprocess, or Orca Run effect. Reject repeated, mixed, case-shifted, whitespace-padded, and aliased values; never fuzzy-correct or silently fall back. Omission alone selects omp. --solo and --team are OMP-only topology flags and conflict with owner orca.

Persist .autopus/pipeline-state/<SPEC-ID>.execution-owner.json as a body-free pipeline_execution_owner_receipt.v1: owner, default|explicit source, reason, SPEC/run identity, checked_at, and verification_status only.

  • Owner omp uses native OMP task, hub, and todo and must not create an Orca Run.
  • Owner orca must not create an OMP task/todo DAG. Run and read orca skills get orchestration --full, then use that current contract to create and supervise one durable cross-worktree Run. A plain full handoff does not satisfy this topology.
  • auto pipeline run SPEC-ID --platform omp --execution-owner orca runs the tier integrity gate and persists pipeline_execution_owner_receipt.v1 before any Run, worker, or provider session exists, then executes the pipeline phases on supervised Orca workers. Never retry a failure as owner omp.

Read the full file on GitHub · 324 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. 12d ago First seen · 324 lines · 10 tokens per session scan A 29ab7c139c1a

Subscribe to this mod's changes

agent-pipeline is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 3,946 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.