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/quantum-crowbar/quantum-toolbox/agents-mdgit clone --depth 1 https://github.com/quantum-crowbar/quantum-toolboxWhat 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 | $0.00693 | $0.00693 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
quantum-toolbox 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Setup
Audience: AI Agents Version: 2.5.0 A reusable submodule providing standardized instructions, workflows, and skills for AI coding agents.
Reading Order
Session Start (always read)
- Project root
AGENTS.md- Project-specific guidelines and enabled skills - Project root
CONTEXT.md- Current project state and setup - core/instructions.md - Coding rules and security guidelines
- core/architecture-thinking.md - Mental model: domains, stakeholders, gap analysis, risk, prioritization
- Project root
architecture-thinking.local.md(if it exists) - Project-specific overrides to the mental model. Matching headings replace defaults, new headings are added, sections listed under## Skipare ignored. - core/glossary.md - Standard terminology
- skills/_index.md - Skill catalog, token budget, activation
On Demand (read only when invoking a skill)
- skills/_detail.md - Skill Dependencies + Invokable Skills tables — read before loading any skill
- Skill
README.md+workflows.md- Read when about to use a specific skill - Skill
templates.md,examples.md,checklist.md- Read as needed during execution (see File Loading Guide in each skill README) Large skills have 4-phase loading — only Phase 1 (README + workflows) is required on invocation.
Core Documentation
| Document | Purpose |
|---|---|
| core/instructions.md | Coding rules, security guidelines |
| core/workflows.md | Development processes, autonomous dev loop |
| core/architecture-thinking.md | Architecture domains, stakeholders, gap analysis |
| core/glossary.md | Standard terminology |
Key References
| Resource | Purpose |
|---|---|
| skills/_index.md | Full skill catalog, token budget, activation |
| skills/_detail.md | Skill dependencies + invokable commands (load on skill invocation) |
| scripts/measure-tokens.sh | Measure current token counts per skill |
| specs/ROADMAP-TRACKER.md | Roadmap and planned work |
| templates/ | AGENTS.md, CONTEXT.md, commit, PR templates |
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 · 64 lines · 693 tokens per session scan A 8d4bb14dd5ca
quantum-toolbox AGENTS.md is an instructions file published in the GitHub repository quantum-crowbar/quantum-toolbox (11 stars, last pushed 3d ago), licensed MIT. It adds 693 tokens to every session, about $0.0035 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
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.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.