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/oreum-ai/smartstack/agents-mdgit clone --depth 1 https://github.com/oreum-ai/smartstackWhat 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 | $0.01418 | $0.01418 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
smartstack 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — SmartStack
This is the portable brain. Every AI coding tool (Claude Code, Cursor, Codex, Windsurf/Antigravity, Copilot, Ollama-based assistants) is pointed here by a thin adapter (see
/adapters). Read this at the start of every session. Detailed knowledge lives inai-rules/and is loaded on demand.SmartStack © 2026 oreumaii · MIT. Make your AI assistant smarter, ship better, spend fewer tokens.
What SmartStack does for you
Three problems waste tokens and quality on every project: re-explaining the project each session, re-solving the same bugs, and shipping changes that quietly break security or UX. SmartStack fixes all three:
- Persistent context — this file +
ai-rules/context/mean the assistant always knows your project without you re-explaining it. (This alone typically cuts tokens ~30–40%.) - Indexed memory —
ai-rules/memory/recalls the last sessions and a permanent, terse list of common bugs, looked up by index so the assistant never rescans everything. - Enforced standards —
ai-rules/rules/,ai-rules/hooks/, andai-rules/agents/keep security, performance, and UX correct before code ships.
This kit is framework-agnostic. It works for any language or stack (web, mobile, backend, scripts,
data). Where a rule needs project specifics, you fill them into ai-rules/context/project.md once.
Session protocol (follow every session)
- Start → read
ai-rules/hooks/session-start.md. It points you at the latest session summary and the error index so you resume with context instead of re-reading the world. - Before writing code → load only the
rules/file andcontext/file the task needs (skills/context-budget). Read a file before you edit it. State what you understand before changing it. - When something breaks → run
skills/debug-fix. It checks the error ledger FIRST (common errors, then recent) before inventing a new fix. - Risky logic (auth, money, access control, anything irreversible) → run
skills/tdd: write the failing test first. - Before committing → run
hooks/pre-commit.md(secret scan + lint/build + rules check). - End of session → run
scripts/session-save.shso the next session inherits your work.
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 · 97 lines · 1,418 tokens per session scan A 829f3654d187
smartstack AGENTS.md is an instructions file published in the GitHub repository oreum-ai/smartstack (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,418 tokens to every session, about $0.0071 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.