Borrowing it
Nothing to install: this file belongs to earthtojake/step.parts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/earthtojake/step.parts/main/AGENTS.mdgit clone --depth 1 https://github.com/earthtojake/step.partsWrote 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/earthtojake/step.parts/agents-md)<a href="https://agentmods.dev/instructions/earthtojake/step.parts/agents-md"><img src="https://agentmods.dev/badge/instructions/earthtojake/step.parts/agents-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 | $0.02574 | $0.02574 |
| Opus 5 | $0.01287 | $0.01287 |
| Sonnet 5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
step.parts AGENTS.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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
This repo is a Next.js catalog for open-source CAD parts. The source of truth is STEP files plus human-authored catalog metadata; GLB previews, PNG thumbnails, and the SQLite catalog are generated artifacts. Generated previews are published to Vercel Blob rather than committed.
Quick Commands
- Dev server:
npm run dev - Catalog SQLite metadata only:
node scripts/generate-catalog.mjs - Catalog build:
npm run catalog:build - Preview asset sync:
npm run catalog:sync-assets - Non-mutating catalog validation:
npm run catalog:check - Lint:
npm run lint - TypeScript check:
npx tsc --noEmit - Full app check:
npm run check
npm run catalog:build rebuilds local GLB/PNG preview artifacts only; it does not update catalog/parts.sqlite. Preview Blob paths are derived from each part's STEP SHA-256, so SQLite is reproducible from source catalog metadata plus STEP files. Tune paired export lanes with STEP_PARTS_EXPORT_CONCURRENCY; it defaults to 2. Production npm run catalog:sync-assets uploads only missing deterministic Blob assets and generates local GLB/PNG files only for those missing parts.
For metadata-only changes to catalog/parts.json, do not run npm run catalog:build. Run node scripts/generate-catalog.mjs instead to refresh catalog/parts.sqlite without rebuilding GLB/PNG artifacts. Only run catalog:build when STEP files or preview assets need to be added, refreshed, or repaired.
The thumbnail exporter starts a local render server on 127.0.0.1; sandboxed runs may need approval/escalation.
Repo Shape
catalog/parts.json: human-authored part records only.catalog/parts.sqlite: generated catalog metadata used by the app.catalog/taxonomy.json: narrow guardrails for rigid, repeatable families only.catalog/step/{id}.step: canonical STEP assets.public/glb/{id}.glb: local generated interactive previews, ignored by Git and synced to Vercel Blob.public/png/{id}.png: local generated 512x512 thumbnails, ignored by Git and synced to Vercel Blob.scripts/add-part.mjs: single-part helper for local STEP files.scripts/generate-catalog.mjs: regenerates catalog SQLite metadata only.scripts/export-assets.mjs: converts STEP to GLB and renders PNGs.scripts/check-catalog.mjs: validates source schema, taxonomy guardrails, STEP sanity, generated SQLite rows, and optionally published Blob assets.src/components/part-directory.tsx: searchable catalog UI and card previews.src/components/part-viewer.tsx: detail-page 3D viewer with PNG fallback.src/lib/part-query.ts: server-side search/filter/sort behavior.src/app/v1/*: catalog API routes.
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 · 173 lines · 2,574 tokens per session scan A cb28ab4966f9
step.parts AGENTS.md is an instructions file published in the GitHub repository earthtojake/step.parts (345 stars, last pushed 2mo ago), licensed MIT. It adds 2,574 tokens to every session, about $0.0129 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.