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/prototypdigital/bluetemberg/agents-mdgit clone --depth 1 https://github.com/prototypdigital/bluetembergWhat 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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
bluetemberg 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 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bluetemberg
Vendor-neutral AI tooling scaffolder and sync engine for Cursor, Claude Code, and GitHub Copilot.
Commands
npm run dev # TypeScript watch mode
npm run build # Production build (tsc)
npm run test # Run vitest
npm run test:watch # Vitest in watch mode
npm run lint:fix # ESLint auto-fix
npm run format # Prettier format
npm run typecheck # Type-check without emit
npm run sync:llm-config # Sync rules -> all AI tool directories
npm run sync:catalog # Refresh the committed catalog snapshot from the packs repo
AI Config Architecture
Source of truth for all AI tool configuration lives in llm/:
llm/rules/— scoped rules (frontmatter:description,scope)llm/agents/— specialist agent definitionsllm/skills/— on-demand skill workflows
Run npm run sync:llm-config to generate tool-specific files in .cursor/rules/, .cursor/agents/, .cursor/skills/, .claude/, .github/instructions/, .github/agents/, .github/skills/, and related paths. These generated files should not be edited directly.
Project structure
src/init/— Interactive wizard (prompts, presets, scaffold)src/sync/— Sync engine (config loading, frontmatter transforms, file writing)src/registry/— Pack install/update against the npm registrysrc/catalog/— Catalog loader + committed snapshot (single source for pack ids/profiles)src/utils/— Shared filesystem helperssrc/types.ts— All shared TypeScript typesbin/cli.js— CLI entry point (Commander)tests/— Vitest tests (sync + transform)docs/wiki/— GitHub Wiki source
All user-facing content (rules, agents, skills, guardrails) lives in bluetemberg-packs — this repo ships no content, only the engine.
Conventions
- ESM-only (
"type": "module") - Strict TypeScript with
consistent-type-imports - Early returns over nesting; guard clauses first
- Single-purpose functions; extract helpers when >20 lines
- No
any; useunknownthen narrow
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 First seen · 70 lines · 674 tokens per session scan A 89f95405742a
bluetemberg AGENTS.md is an instructions file published in the GitHub repository prototypdigital/bluetemberg (5 stars, last pushed 5d ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
agent-toolkit AGENTS.md
Instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.
true-skills AGENTS.md
Instructions for katalon-labs/true-skills, covering agents.md - katalon true platform skills, find your skill by role, skills (single source of truth: skills/), platform-setup and test-plan.
vibeflow CLAUDE.md
Instructions for pe-menezes/vibeflow, covering vibeflow monorepo, structure, cross-edition sync rules, file mapping and what to sync.
agent-toolkit copilot-instructions.md
Instructions for ulises-jeremias/agent-toolkit, covering agent toolkit agents, available skills and available agents.
api CLAUDE.md
Instructions for iblai/api, covering claude.md, repository purpose, terminology (settled — use consistently), layout and skills.
true-skills copilot-instructions.md
Instructions for katalon-labs/true-skills, covering katalon true platform - copilot instructions, skills and katalon mcp server.