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.
npx skills add handarbeit/fabrik --skill onboardgit clone --depth 1 https://github.com/handarbeit/fabrikWrote 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.
[](https://agentmods.dev/skills/handarbeit/fabrik/onboard)<a href="https://agentmods.dev/skills/handarbeit/fabrik/onboard"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/onboard/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.
<a href="https://agentmods.dev/skills/handarbeit/fabrik/onboard"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00173 | $0.04132 |
| Opus 5 | $0.00086 | $0.02066 |
| Sonnet 5 | $0.00035 | $0.00826 |
| Haiku 4.5 | $0.00017 | $0.00413 |
Grade A, and why
onboard 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 9d 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.
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.
Project Onboarding
Interview the person about the project as a whole and write the result to .specify/memory/constitution.md. Every feature specification written afterwards reads this file, so the work done here stops being re-litigated once per spec.
The value is concentrated in three things: scope boundaries (so features don't wander), non-negotiables (so constraints don't get discovered late), and vocabulary (so ten specs written over three months use one word per concept). Everything else is context that makes the specs read as though one person wrote them.
Run this once at the start of a project. Re-run it when goals or boundaries genuinely shift.
Who this is for, and what's out of bounds
The person you're interviewing is a product manager, business owner, or domain expert. Assume deep knowledge of the business and none of software construction.
Apply one test to every question before you ask it: could they answer this from running their own operation? If answering would need a lawyer, an IT department, or someone who builds software, it's the wrong question — and asking it anyway costs you their confidence as well as the minute. Rewrite it as something they've lived:
| Don't ask | Ask |
|---|---|
| "Are there accessibility standards you must meet?" | "Is there anyone on your team a normal app would lock out — poor eyesight, no reading glasses to hand, colour blindness?" |
| "What are your data residency requirements?" | "Is there anything here you'd be uncomfortable with being stored abroad?" |
| "What systems must this integrate with?" | "Which systems you already pay for would people be annoyed to have to type into twice?" |
| "What's the connectivity like?" | "If someone's standing in the loading bay with no phone signal, does this still need to work?" |
| "What's your data retention policy?" | "If a client asked what you still hold on them from three years ago, what would the answer be?" |
The named jargon in that table isn't a blocklist to memorize — plenty of words that feel like plain English ("connectivity", "sync", "platform", "workflow") fail the same test. Judge each question by whether they could answer it, not by whether it contains a flagged word.
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.
- 9d ago First seen · 226 lines · 173 tokens per session scan A 11b8ffbdca5b
onboard is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed today), licensed Apache-2.0. It adds 173 tokens to every session and 4,132 once invoked, about $0.0009 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.
Other skills, from other repositories
forge-prd
Generate a structured PRD (markdown + meta) for a non-trivial build and auto-create a ticket per acceptance criterion (Forge Mission Control Phase 2, WP3 "PRD generator"). Use before starting a non-trivial feature/build, typically right after Deep Learn Mode. Trigger on "write a PRD", "generate a PRD", "scope this…
ticket
Write or draft a minimal tracker ticket: a type/parent line, a terse " :" title, and 2 to 4 bullets of what should change and why in product language, and nothing else (no headings, no acceptance criteria, no Out-of-scope block, no verification gate). Project tokens read from .claude/harness/profile.md. Use when…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
hr-talent
HR and talent management expertise for talent acquisition, performance management, compensation strategy, organizational design, culture building, succession planning, and D&I programs. Use when hiring, managing performance, designing organizations, or building culture.
leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.
proposal-writer
Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service…