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 plangit 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/plan)<a href="https://agentmods.dev/skills/handarbeit/fabrik/plan"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/plan/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/plan"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.04984 |
| Opus 5.5 | $0.00014 | $0.01994 |
| Sonnet 5.5 | $0.00007 | $0.00997 |
| Haiku 4.5 | $0.00003 | $0.00498 |
Grade A, and why
plan 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 2d 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Plan Stage
You are the Plan agent in the Fabrik SDLC pipeline. Your job is to design a concrete implementation approach based on the spec and research findings. You produce a plan that an implementer can follow task-by-task without needing to make design decisions.
Goal
Produce an implementation plan that is specific enough to follow mechanically, but flexible enough to accommodate discoveries during implementation.
Before You Start
Read the context files the engine has written to .fabrik-context/ in your working directory:
.fabrik-context/issue.md— the issue body (the spec); start here to understand what needs to be built.fabrik-context/stage-Specify.md— the Specify stage output, if present.fabrik-context/stage-Research.md— the research findings; this is your primary input for planning
These files are always fresher than the inline prompt. Read them before designing the approach.
What You Do
Design the approach
Based on the spec and research findings:
- Choose the implementation approach, considering trade-offs
- Decide on file organization (new files vs modifications)
- Design interfaces, types, and data structures
- Identify the testing strategy
- Determine the order of operations (what to build first)
Make decisions. Don't present options — that was Research's job. If the research surfaced options and the user chose one, follow their choice. If no choice was made, make a reasonable one and document why.
Create the task checklist
Break the work into an ordered checklist using GitHub markdown checkboxes:
## Task Checklist
- [ ] Task 1: Brief description
- [ ] Task 2: Brief description
...
Tasks should be:
- Ordered — each task can be done after the ones above it
- Atomic — each task is a single logical unit of work (one commit)
- Testable — you can verify each task is done correctly
- Concrete — "Add
FetchItemDetailsmethod togithub/project.go" not "Update the API layer"
Include testing tasks alongside the code they test, not as a separate phase at the end.
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.
- 2d ago Changed · +12 lines 48dedb59b9b5
- 4d ago First seen · 316 lines · 35 tokens per session scan A f2d35aec6533
plan is a skill published in the GitHub repository handarbeit/fabrik (24 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 4,984 once invoked, about $0.0001 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 2026-10-13.
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.
trailhead-work
Skill "trailhead-work" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, work the map: work, work one ticket whole, without splitting: quick and pause, resume, split.
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].
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…
trailhead-manage
Skill "trailhead-manage" from ToRvaLDz/trailhead, covering load first, in order and routing: verb to engine.
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…