fabrik-setup

fabrik-setup is a skill for Claude Code from handarbeit/fabrik. It costs 142 tokens per session (3,265 once invoked), scanned A, original, Apache-2.0.

A setup guide for Fabrik, a tool that manages software work through GitHub Project boards and Claude Code workers. Fabrik breaks work into stages such as research, planning, implementation, review, and validation.

In plain words
What is it for?
Use it when installing Fabrik for the first time, checking required access and tools, and preparing a GitHub repository and Project board.
Why use it?
It helps avoid missing the prerequisites or configuring the project board incorrectly when starting Fabrik. It guides the user through setup instead of performing the steps automatically.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the fabrik plugin — 2 skills, 1 command, 1 hook, 1 MCP server shipped together

Good fit Use it when installing Fabrik for the first time, checking required access and tools, and preparing a GitHub repository and Project board.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/handarbeit/fabrik/fabrik-setup
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 handarbeit/fabrik --skill fabrik-setup
Clone the repo
git clone --depth 1 https://github.com/handarbeit/fabrik

Made for: Claude Code.

Or install fabrik, the plugin that ships this one along with the rest of its 2 skills, 1 command, 1 hook, 1 MCP server.

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 fabrik-setup

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/handarbeit/fabrik/fabrik-setup"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,265 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 warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 16
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 62
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 50
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00142 $0.03265
Opus 5.5 $0.00057 $0.01306
Sonnet 5.5 $0.00028 $0.00653
Haiku 4.5 $0.00014 $0.00327

Measured today against content hash 277e1a342b60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fabrik-setup 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 today.

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.

plugin/fabrik/skills/fabrik-setup/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrapping Fabrik

This skill guides a user through installing Fabrik and standing it up for the first time in their project. Don't run any of these steps yourself unsolicited — walk the user through them, confirm their environment, and let them execute. Authoritative docs live at https://fabrik.handarbeit.io — link the user there rather than reproducing details that may drift.

Before you start

Confirm the user has — or help them obtain — each of these. Don't proceed past step 0 until prerequisites are in place.

  1. Claude Code CLI installed and authenticated. They almost certainly have this if they're talking to you, but check with claude --version if uncertain.

  2. A GitHub repo and a GitHub Project (v2) board. The board is non-optional — Fabrik is a board orchestrator. fabrik init --create-board --owner <org> --repo <repo> (organization-owned repos) creates one directly from the stage configs, with columns guaranteed to match — prefer this over hand-building one in GitHub's UI. See Step 4.

  3. A GitHub token with repo, project, and workflow scopes. The real constraint is narrower than "classic only": fine-grained tokens (github_pat_...) don't work with GitHub Projects v2 GraphQL, but both classic PATs (ghp_...) and gh CLI OAuth tokens (gho_...) do. Since gh auth login is already a prerequisite (next item), the shortest path is usually:

    FABRIK_TOKEN=$(gh auth token)
    

    Note this value rotates whenever the user re-runs gh auth login or gh auth refresh — a .env pinned to a stale copy will start failing after a re-auth. A classic PAT (create at https://github.com/settings/tokens, select "Tokens (classic)") is the alternative if they want a token independent of their gh CLI session.

    Identity-mismatch trap: if they're reusing a token copied from another Fabrik project's .env, it may belong to a different GitHub account than the one the Project board is under — a classic, correctly-scoped token, so nothing about it looks wrong. It fails as NOT_FOUND: Could not resolve to a ProjectV2, which reads like a wrong project number, not a wrong identity. Have them check: gh api user --jq .login should match user: in config.yaml.

  4. gh CLI authenticated (gh auth status) — needed for the binary download path, for FABRIK_TOKEN=$(gh auth token) above, and convenient for many Fabrik workflows.

  5. Go 1.27.3+ — only required if they want to build from source instead of downloading a release binary.

Read the full file on GitHub · 180 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. today Changed 277e1a342b60
  2. 10d ago Changed b1dda57e49b3
  3. 12d ago Changed 9c98a1967067
  4. 13d ago Changed · +11 lines cda2ac800352
  5. 14d ago Changed d85a42eae11f
  6. 15d ago Changed · +1 lines e16c01efb04e
  7. 1mo ago Changed · +48 lines d9e1c259bd25
  8. 1mo ago First seen · 120 lines · 142 tokens per session scan A 57fbdb5704c6

Subscribe to this mod's changes

fabrik-setup is a skill published in the GitHub repository handarbeit/fabrik (25 stars, last pushed today), licensed Apache-2.0. It adds 142 tokens to every session and 3,265 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

trailhead-view

Skill "trailhead-view" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, render the map: map [map], 🎯 destination and 🗒️ notes.

ToRvaLDz/trailhead · 116 tokens

trailhead-chart

Skill "trailhead-chart" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, chart a new map / adopt a project: new, adopt, open a ticket on the fly: ticket and triage the inbox: inbox [issue].

ToRvaLDz/trailhead · 138 tokens

trailhead

Start and drive a large project (more than one agent session can hold) as a map of decision tickets on GitHub Issues, resolving one at a time until the way to the destination is clear. Self-contained (zero external-plugin dependencies: trailhead ships its own trailhead- engine agents and needs only an authenticated gh…

ToRvaLDz/trailhead · 158 tokens

trailhead-manage

Skill "trailhead-manage" from ToRvaLDz/trailhead, covering load first, in order and routing: verb to engine.

ToRvaLDz/trailhead · 148 tokens

trailhead-capture

Skill "trailhead-capture" from ToRvaLDz/trailhead, covering load first, in order and routing: verb to engine.

ToRvaLDz/trailhead · 117 tokens

debt-ops-add

Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…

bcanfield/agentic-tech-debt · 115 tokens