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/letsgogeeky/aichitect/claude-mdgit clone --depth 1 https://github.com/letsgogeeky/aichitectWrote 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/letsgogeeky/aichitect/claude-md)<a href="https://agentmods.dev/instructions/letsgogeeky/aichitect/claude-md"><img src="https://agentmods.dev/badge/instructions/letsgogeeky/aichitect/claude-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 | $0.05551 | $0.05551 |
| Opus 5 | $0.02776 | $0.02776 |
| Sonnet 5 | $0.01110 | $0.01110 |
| Haiku 4.5 | $0.00555 | $0.00555 |
Grade A, and why
aichitect CLAUDE.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 5d 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
AIchitect — Project Context
Brand: "Cut the noise. Pick your AI stack."
Domain: aichitect.dev | Stack: Next.js 16 + React Flow + Three.js + Tailwind v4 + TypeScript
Scope rule: SCOPE.md — the single source of truth for what belongs in the catalog. Read it before adding a tool.
Engineering philosophy
This is a greenfield project. Always build clean:
- No adapter layers — if the DB schema or TypeScript type is designed a certain way, the rest of the code conforms to it. Never write a mapping/transform function to bridge an old shape to a new one just to avoid touching other files.
- No backwards-compat shims — if a type changes, update all call sites. If a field is renamed, rename it everywhere. The cost of a clean sweep is low at this stage.
- No workarounds — if something is wrong, fix the root cause. Don't patch around it with defensive code, re-exports, or fallback casts that exist only to preserve a broken old shape.
The exception: once we have production data that can't be migrated cheaply, or a public API contract we can't break, we'll revisit. Until then, always reach for the clean solution.
Dev workflow
- Docker only — never run
npmornodelocally. All dev runs through docker-compose. - Hot reload via volume mounts. Rebuild image only when adding new packages to
package.json.
Make targets
| Command | When to use |
|---|---|
make run |
Start dev server (applies local migrations + seeds, then tails logs) |
make down |
Stop and remove containers |
make rebuild |
After adding packages to package.json — full reinstall + rebuild |
make restart |
Restart containers without rebuilding |
make shell |
Open a shell inside the running container |
make logs |
Tail logs without restarting |
make typecheck |
Run tsc --noEmit inside the container |
make lint |
Run ESLint |
make format |
Run Prettier |
make test |
Run Vitest test suite |
make check |
Run lint + typecheck + test in one shot |
make sync-counts |
After modifying data files — syncs tool/stack/relationship counts in README and CLAUDE.md |
make seed-validate |
Validate JSON data integrity without a DB connection |
make db-push-local |
Apply pending migrations to local Postgres |
make db-push |
Promote verified migrations to remote Supabase |
make db-migrate name=X |
Scaffold a new migration file |
make db-reset-local |
Wipe and re-apply all migrations locally (destructive) |
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.
- 5d ago First seen · 410 lines · 5,551 tokens per session scan A adb8fde74a54
aichitect CLAUDE.md is an instructions file published in the GitHub repository letsgogeeky/aichitect (5 stars, last pushed 23d ago), licensed MIT. It adds 5,551 tokens to every session, about $0.0278 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
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.