agentmods.dev

architect CLAUDE.md

A project instruction file for Architect, a terminal-based coding environment built with Zig and SDL3. It tells coding agents how to set up, build, run, test, and check the project.

In plain words
What is it for?
Use it when developing Architect, especially when activating its Nix environment, preparing a worktree, building or running it, running tests, linting, or checking formatting.
Why use it?
It gives agents the project’s expected commands, tools, and environment so they can work consistently in a fresh checkout or worktree.

Instructions file

50 4d ago A scan 4,622 tokens original MIT
View the source file forketyfork/architect
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 instructions/forketyfork/architect/claude-md
Clone the repo
git clone --depth 1 https://github.com/forketyfork/architect
Per session 4,622 This file is loaded in full into every session.
When invoked 4,622 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.04622 $0.04622
Opus 5 $0.02311 $0.02311
Sonnet 5 $0.00924 $0.00924
Haiku 4.5 $0.00462 $0.00462

Measured 3d ago against content hash 5db68071803c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect 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 3d 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.

CLAUDE.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md (symlinked as AGENTS.md)

[Canonical file: CLAUDE.md. Keep AGENTS.md as a symlink to CLAUDE.md.]

Project

Name: Architect Description: A terminal multiplexer and AI-assisted coding environment built on SDL3 and Zig. Architect lets developers run multiple terminal sessions in a tiled layout, annotate diffs, and integrate Claude agents directly into their workflow. Stack: Zig 0.15, SDL3, ghostty-vt (terminal emulation), Nix dev shell, just task runner Status: Active development

Build & Run

# Worktree bootstrap (run in a fresh worktree)
just setup   # pre-caches the ghostty-vt tarball; skip if already cached

# Environment activation
nix develop  # or: direnv allow
#
# Minimal host prerequisites:
# - Nix with flakes enabled (or direnv + nix-direnv)
# - macOS (primary platform; Linux support is partial)

# Build
zig build

# Run
zig build run

# Test
zig build test

# Type check
N/A  # Zig build covers type checking

# Lint
just lint

# Format check
zig fmt --check src/

Infrastructure

  • Source code hosting: GitHub — URL: https://github.com/forketyfork/architect — CLI: gh — Skill: managing-github
  • Issue tracker: GitHub Issues — URL: https://github.com/forketyfork/architect/issues — CLI: gh issue — Skill: managing-github
  • CI/CD: GitHub Actions — config: .github/workflows/
  • Issue/PR linkage convention: Reference issues in commit messages and PR descriptions using #<issue-number>. Use Closes #N or Fixes #N in the PR body to auto-close issues on merge.

Use the managing-github skill for all GitHub operations: creating issues, pull requests, fetching review threads, posting comments, and searching.

Project Documentation

Read these before making any changes:

  • README.md — User-facing product overview; skim for expected behavior, do not duplicate here
  • docs/ARCHITECTURE.md — How it's built (layers, modules, dependencies)
  • docs/configuration.md — Config shape for config.toml and persistence.toml
  • docs/development.md — Developer setup and workflow notes
  • docs/perf-debugging.md — Read before investigating rendering/terminal performance: headless repro via the control socket (scripts/perf/), codex resize behavior, Debug-vs-Release ghostty-vt costs, SDL/Metal pipeline pitfalls

Read the full file on GitHub · 254 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.

  1. 3d ago First seen · 254 lines · 4,622 tokens per session scan A 5db68071803c

Subscribe to this mod's changes

architect CLAUDE.md is an instructions file published in the GitHub repository forketyfork/architect (50 stars, last pushed 4d ago), licensed MIT. It adds 4,622 tokens to every session, about $0.0231 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.

claude-codecodexghosttysdl3terminalzig
Related

Other instructions, from other repositories

orca AGENTS.md

AGENTS.md instructions for stablyai/orca, covering design system, electron ui validation, style, reuse before reimplementing and concise/brief non-obvious comments only.

stablyai/orca · 1,918 tokens

wispterm AGENTS.md

Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.

xuzhougeng/wispterm · 5,997 tokens

liney AGENTS.md

Instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.

everettjf/liney · 1,589 tokens

orca CLAUDE.md

Claude Code instructions for stablyai/orca, a project described as: Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

stablyai/orca · 5 tokens

tui-test-ghost CLAUDE.md

Instructions for hegner123/tui-test-ghost, covering tui-test-ghost — tui testing toolkit, what this is, build commands, architecture and tigerstyle (mandatory).

hegner123/tui-test-ghost · 1,425 tokens

liney CLAUDE.md

Instructions for everettjf/liney, a project described as: Liney is a native macOS terminal workspace built with AppKit, SwiftUI, and Ghostty, designed for multi-repo workflows, worktree switching, and focused vibe coding.

everettjf/liney · 3 tokens