pipeline

pipeline is a command for coding agents from fockus/skill-memory-bank. It costs 0 tokens per session (1,262 once invoked), scanned A, original, MIT.

A command for keeping several named execution pipelines in one project, with separate model choices and workflows for different coding agents or working styles.

In plain words
What is it for?
Use it to create, select, or automatically assign pipelines such as a fast setup for one agent and a review-focused setup for another.
Why use it?
It removes the need to force every run and every agent to share one pipeline configuration.

Command

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.

agentmods
npx agentmods add commands/fockus/skill-memory-bank/pipeline
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank

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/fockus/skill-memory-bank/pipeline.svg)](https://agentmods.dev/commands/fockus/skill-memory-bank/pipeline)
Your own site
<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/pipeline"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/pipeline.svg" alt="Measured on agentmods" 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 1,262 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01262
Opus 5 $0.00000 $0.00631
Sonnet 5 $0.00000 $0.00252
Haiku 4.5 $0.00000 $0.00126

Measured 5d ago against content hash 0fb85a57f1be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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.

commands/pipeline.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mb pipeline

Manage multiple named execution pipelines in one project. Where /mb config manages a single <bank>/pipeline.yaml, /mb pipeline lets a project keep several pipelines side by side — each with its own model routing and workflow — and select between them per run or automatically per code-agent host.

Why named pipelines?

One repository is often driven by more than one agent (Claude Code, pi, opencode, codex) and more than one regime (a fast solo loop vs. a governed review-ensemble). Hard-coding a single pipeline.yaml forces one compromise. Named pipelines let you:

  • keep a claude-fast pipeline and a pi-governed pipeline in the same repo;
  • give each its own models (roles.*.model) and workflow (workflow.default);
  • bind a pipeline to a host so /mb work picks it automatically under that agent — no flag needed;
  • pick one explicitly for a single run with --pipeline NAME.

Storage & metadata

Each named pipeline is a full, standalone pipeline file — same schema and validator as pipeline.yaml:

.memory-bank/
├── pipeline.yaml            # legacy / fallback default (back-compat)
└── pipelines/
    ├── claude-fast.yaml      # pipeline_name: claude-fast · agents: [claude-code]
    ├── pi-governed.yaml      # pipeline_name: pi-governed · agents: [pi, opencode]
    └── solo.yaml             # pipeline_name: solo · default: true

Three optional top-level metadata keys distinguish a named pipeline:

Key Meaning
pipeline_name Display name (defaults to the filename stem).
default: true The project default when nothing else selects a pipeline.
agents: [<host>…] Code-agent hosts this pipeline binds to (claude-code, cursor, codex, opencode, pi, windsurf, cline, kilo).

Absent metadata stays valid — a plain copy of pipeline.default.yaml is a legal named pipeline.

Subcommands

bash scripts/mb-pipeline.sh <subcommand> [args...] [mb_path]

Read the full file on GitHub · 112 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. 5d ago First seen · 112 lines · 0 tokens per session scan A 0fb85a57f1be

Subscribe to this mod's changes

pipeline is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,262 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.