A setup guide for adding SmartStack to a code repository and connecting it to AI coding tools. SmartStack keeps project context and working rules in shared repository files.

Use it to install SmartStack, add an adapter for Claude Code, Cursor, Codex, Windsurf, Copilot, or local Ollama, and fill in project details. It also covers repairing or extending the system.

It avoids setting up each AI tool from scratch and helps different tools follow the same project instructions. It also gives new sessions access to the project's background and past work.

setup — Skill by oreum-ai

Install

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.

agentmods

npx agentmods add skills/oreum-ai/smartstack/setup

Any agent

npx skills add oreum-ai/smartstack --skill setup

Clone the repo

git clone --depth 1 https://github.com/oreum-ai/smartstack

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 628 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00628
Opus 5	$0.00000	$0.00314
Sonnet 5	$0.00000	$0.00126
Haiku 4.5	$0.00000	$0.00063

Measured yesterday against content hash ea91e13f650e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

ai-rules/skills/setup/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Setup

When to use

Installing SmartStack into a repo for the first time, onboarding a new AI tool, or repairing/extending the system itself.

What this system is

A portable layer that lives in the repo so every AI session starts with full context, follows the same rules, recalls past work and bugs cheaply, and ships safely. Glued together by AGENTS.md + the ai-rules/ folder, with thin per-tool adapters in /adapters.

First-time install

Place the files at your repo root: AGENTS.md + the ai-rules/ folder.
Install your tool's adapter from /adapters:
- Claude Code → copy adapters/CLAUDE.md to repo root as CLAUDE.md.
- Cursor → copy adapters/.cursorrules to repo root (and optionally .cursor/rules/).
- Codex/OpenAI → AGENTS.md is already the file it reads; or copy adapters/AGENTS.codex.md notes.
- Windsurf/Antigravity → copy adapters/.windsurfrules to repo root.
- GitHub Copilot → copy adapters/copilot-instructions.md to .github/copilot-instructions.md.
- Ollama/local → paste adapters/ollama-system.md into the model's system prompt / Modelfile.
Fill in your project facts — edit ai-rules/context/project.md (10 min, one time; the template guides you). Optionally fill file-map.md, data-model.md, api-map.md, env-keys.md.
Make scripts runnable: chmod +x ai-rules/scripts/*.sh (Git Bash/WSL on Windows).
Confirm .gitignore excludes .env and secret files; run scripts/secret-scan.sh --all.
Verify your tool picks it up: open it in the repo and run the session-start hook.

Onboarding another AI tool

Point it at AGENTS.md first, then context/file-map.md and context/project.md. Tell it to follow ai-rules/rules/ and to use ai-rules/memory/ by index before inventing fixes. The summaries are tool-agnostic, so any capable assistant can resume from them.

Maintaining the system

Keep AGENTS.md short; push detail into context/.
Prune memory/sessions/ (the session-save/prune-sessions scripts do this).
Keep common-errors.md entries short and never delete them.
Update context/file-map.md and context/project.md when the codebase changes shape.
Run the doc-reviewer agent periodically to catch drift and bloat.

Read the full file on GitHub · 38 lines

Changes

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.

yesterday First seen · 38 lines · 0 tokens per session scan A ea91e13f650e

Subscribe to this mod's changes

setup is a skill published in the GitHub repository oreum-ai/smartstack (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 628 tokens. 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens