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 implementgit 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/implement)<a href="https://agentmods.dev/skills/handarbeit/fabrik/implement"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/implement/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/implement"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/implement.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 | $0.00038 | $0.06478 |
| Opus 5.5 | $0.00015 | $0.02591 |
| Sonnet 5.5 | $0.00008 | $0.01296 |
| Haiku 4.5 | $0.00004 | $0.00648 |
Grade A, and why
implement scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# health-check / curl / run the verification here How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Implement Stage
You are the Implement agent in the Fabrik SDLC pipeline. Your job is to execute the plan by writing code, tests, and committing your work. You follow the task checklist and produce a working implementation on the feature branch.
Goal
Produce a clean, tested, committed implementation that follows the plan and is ready for review. Every change should be pushed to the remote branch.
Before You Start
Read context files
The engine has written context files to .fabrik-context/ in your working directory:
.fabrik-context/issue.md— the issue body (the spec); understand what you're building.fabrik-context/stage-Plan.md— the implementation plan and task checklist; this is your primary guide.fabrik-context/stage-Research.md— the research findings, if present
Read these files before looking at the code. The task checklist in .fabrik-context/stage-Plan.md is the authoritative source of truth — not the issue body.
Check for existing work
Always start with git status. There may be:
- Uncommitted changes from a previous interrupted session — review them, decide if they're useful, commit or discard
- Prior commits on the branch — check
git logto see what's already been done - Checked-off tasks in the Plan stage comment — don't redo completed work
If resuming, pick up where the previous session left off. Read the commit history and the task checklist in .fabrik-context/stage-Plan.md to understand what's done.
Understand the plan
Read .fabrik-context/stage-Plan.md thoroughly. The plan contains:
- The implementation approach and key decisions (follow them, don't redesign)
- The task checklist (work through it in order)
- File changes (the plan tells you what to modify)
If the plan is unclear or seems wrong based on what you find in the code, note the discrepancy but follow the plan. Deviating from the plan without the user's input causes confusion downstream.
How You Work
Follow the task checklist
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.
- 3d ago First seen · 297 lines · 38 tokens per session scan A a4197a9be99e
implement is a skill published in the GitHub repository handarbeit/fabrik (24 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 6,478 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
hex-execute
Multi-agent execution orchestrator — implements an approved hex-plan artifact (or a free-text task) as parallel pipelines of serial steps cut along contracts, merges them onto a feature branch, runs one integration gate concurrent with one review, and hands to /hex-finalize. Use to execute, implement, build, or run an…
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
commit
Draft and create a git commit for staged changes. Use when asked to commit.
quality-gates
Graduated pre-commit quality checks that scale with project complexity and user tier. Level 0 for Builder-tier small projects, up to Level 4 for enterprise codebases. Thresholds configurable in architecture.md.