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 agentmods add instructions/handarbeit/fabrik/claude-mdgit 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/instructions/handarbeit/fabrik/claude-md)<a href="https://agentmods.dev/instructions/handarbeit/fabrik/claude-md"><img src="https://agentmods.dev/badge/instructions/handarbeit/fabrik/claude-md.svg" alt="Measured on agentmods" 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 | $0.14442 | $0.14442 |
| Opus 5 | $0.07221 | $0.07221 |
| Sonnet 5 | $0.02888 | $0.02888 |
| Haiku 4.5 | $0.01444 | $0.01444 |
Grade A, and why
fabrik CLAUDE.md 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 6d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik — Development Guide for Claude
Project Overview
Fabrik is a Go CLI that orchestrates Claude Code through an SDLC pipeline defined on a GitHub Project board. Issues are the unit of work. The pipeline stages (Specify → Research → Plan → Implement → Review → Validate) are configured via YAML files.
Build & Test
go build -o fabrik . # Build
go test ./... # Run all tests
go test -race ./... # Run with race detector
go vet ./... # Lint
Four test layers (unit → sim e2e → wire-contract → live e2e)
The sim bed is a fast, free pre-gate — it is never a replacement for the live
integration suite, which has no substitute and is never reduced. See
adrs/1454-sim-pre-gate-not-replacement.md for the full decision.
| Layer | Where | Runs |
|---|---|---|
go test ./... (unit) |
repo-wide | every PR |
sim e2e (tests/sim) |
scenario-driven, deterministic, -race-clean, $0 tokens |
every PR — no build tag, already inside go test -race ./...; also scripts/sim/run.sh for on-demand runs |
github wire-contract tests (github/wire_contract_test.go + github/testdata/) |
schema validation + recorded fixtures | every PR — no build tag, already inside go test -race ./... |
live e2e (tests/e2e, -tags e2e) |
real Claude, real review bots, real GitHub, real merge-queue semantics | release-gate only — CI compiles it but never runs it; scripts/e2e/run.sh (standalone, or invoked from scripts/cut-release.sh) is the only thing that executes it, before every release |
scripts/e2e/run.sh refuses to spend live budget (bed preflight, build, or any live
GitHub/Claude call) until the sim suite and the wire-contract tests pass first —
see its run_pregate. scripts/cut-release.sh mirrors that ordering and makes the
live suite mandatory by default; --skip-integration=<reason> is a loud,
release-notes-recorded escape hatch, never a silent skip. See tests/sim/README.md
and tests/e2e/README.md for the full detail, including each layer's blind spots
(the sim's inability to see GitHub wire correctness, most prominently) and the
fidelity-drift policy: any live-e2e failure the sim passed is a fidelity bug in the
sim, fixed there as well as in the engine.
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.
- 6d ago First seen · 316 lines · 14,442 tokens per session scan A 598428d605a1
fabrik CLAUDE.md is an instructions file published in the GitHub repository handarbeit/fabrik (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14,442 tokens to every session, about $0.0722 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 instructions, from other repositories
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
agentcat-go-sdk CLAUDE.md
Claude Code instructions for agentcathq/agentcat-go-sdk, covering claude.md, what this is, build & test commands, module layout and architecture.
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.