afm-pipelines

afm-pipelines is a skill for Claude Code, Codex from akopichin/afm. It costs 47 tokens per session (942 once invoked), scanned A, original, MIT.

A tool for finding, installing, configuring, updating, and removing reusable AFM pipelines. A pipeline is a prepared sequence of steps for carrying out a particular kind of work.

In plain words
What is it for?
It helps prepare reusable workflows, choose their models and profiles, and manage their installation in a Git project.
Why use it?
It avoids rebuilding the same workflow for every project and helps keep installed pipeline versions and settings clear. It also checks the pipeline catalog and project before setup.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/pipelines.mjs plan refactor --project /absolute/project/root --options /absolute/options.json --out /absolute/install-plan.json.

Good fit It helps prepare reusable workflows, choose their models and profiles, and manage their installation in a Git project.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/akopichin/afm
agentmods
npx agentmods add skills/akopichin/afm/afm-pipelines

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 afm-pipelines

README.md
[![agentmods](https://agentmods.dev/badge/skills/akopichin/afm/afm-pipelines/github.svg)](https://agentmods.dev/skills/akopichin/afm/afm-pipelines)
Your own site
<a href="https://agentmods.dev/skills/akopichin/afm/afm-pipelines"><img src="https://agentmods.dev/badge/skills/akopichin/afm/afm-pipelines/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 afm-pipelines

Your own site · 80×15
<a href="https://agentmods.dev/skills/akopichin/afm/afm-pipelines"><img src="https://agentmods.dev/badge/skills/akopichin/afm/afm-pipelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 942 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 $0.00047 $0.00942
Opus 5.5 $0.00019 $0.00377
Sonnet 5.5 $0.00009 $0.00188
Haiku 4.5 $0.00005 $0.00094

Measured 3d ago against content hash 115e844de1d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

afm-pipelines 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 3d 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.

assets/claude/skills/afm-pipelines/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AFM pipeline setup

The catalog is https://github.com/akopichin/afm-pipelines. AFM ships this skill; the catalog ships packages and the versioned installer. Do not assume the catalog is already cloned, that a suggested pipeline is installed, or that all projects use the same models. Installing a pipeline does not authorize running it.

Find and prepare

Reuse a user-specified catalog checkout. Otherwise clone the catalog into a new cache directory outside the target project, using Git without executing remote shell snippets. Resolve the selected release/ref to an immutable commit and checkout that commit detached. Keep the commit in the installation report. Do not reset an existing checkout with local edits. A local development checkout is allowed when requested; clearly report that it is not a clean published version.

Read the checkout's README and docs/installer.md. For installer protocol 1, Node.js 22+ and Git are required; install its locked dependency with npm ci --ignore-scripts --no-audit --no-fund in the catalog checkout.

Run node scripts/pipelines.mjs list, then node scripts/pipelines.mjs inspect --project /absolute/project/root. The target must be a Git project root. Inspect manifests and package READMEs to match the user's objective. Present relevant choices; do not install every package or invent entries absent from the catalog.

Choose settings

For the selected package, offer the required AFM settings, each role's client, model and reasoning configuration, and optional project-local skills for Claude and/or Codex. Reuse preferences already supplied. Explain package constraints and missing dependencies. The initial installer supports Claude/Codex Docker recipes, including copies of existing compatible AFM profiles. Arbitrary host commands need a separate adapter; do not pretend the Docker recipes work on host.

Use the documented options JSON format. Each role can use its recommended settings, copy an existing profile, or override client/model/reasoning. Copies are isolated by pipeline and role; never edit a shared profile to customize just one pipeline. Package recommendations are not mandatory model identities.

Read the full file on GitHub · 87 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. 3d ago First seen · 87 lines · 47 tokens per session scan A 115e844de1d2

Subscribe to this mod's changes

afm-pipelines is a skill published in the GitHub repository akopichin/afm (25 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 942 once invoked, about $0.0002 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 2026-10-27.