Stack-specific AGENTS.md and CLAUDE.md: twelve stacks the starter files do not cover

What you end up with

Your coding agent runs the right build and test commands for your stack and leaves the fragile file alone, and you can check that with one command.

What you get

• Twelve AGENTS.md files, one per stack
• How this differs from the starter rules pack
• CLAUDE.md pointer
• Five prompts
• stack_check.py: 10 read-only checks (S01 to S10)

Who it is for

Developers whose stack is not covered by the Next.js, FastAPI and browser game files in the starter rules pack, who want one AGENTS.md per repo that names the right commands.

Works with

Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.

Tools needed

Cost to run: The pack is the only purchase. The checker uses no model tokens.
Time to result: A filled AGENTS.md for one repo in ten minutes

Sample prompts, free to use

Read this repo and AGENTS.md. Fill every [placeholder] from the lockfile and folders you can see. Do not change the Commands table unless a command fails; if it does, show me the output.
Run python3 stack_check.py . and fix every finding.

Free preview of the file

# Stack-specific AGENTS.md and CLAUDE.md files: twelve stacks the starter pack does not cover

Version 1.0, 2026-10-30. By PaperChaseWebb. Twelve ready-to-fill AGENTS.md files, one per stack, each with that stack's real commands, the file agents most often break on it, and rules written for it. Plus a CLAUDE.md pointer, five prompts and stack_check.py, a read-only checker that looks at your repo and tells you whether its AGENTS.md fits the stack the repo actually uses. Works with Grok Bot, Claude Code, Codex, Hermes, Cursor or any tool that reads AGENTS.md. Section 7 says exactly what was and was not tested.

## 1. How this differs from the starter files pack

The store's "AGENTS.md, CLAUDE.md and Cursor rules starter files" pack (pp-agent-rules, $14) gives a base AGENTS.md, variants for Next.js plus Supabase, FastAPI and a browser game, Cursor rules and its own checker. This pack does not repeat any of those. It covers twelve other stacks:

Go, Rust, Chrome extension (Manifest V3), Electron, Tauri 2, Expo (React Native), SvelteKit, Astro, Django, Rails, Laravel and Flutter.

Game engines (Godot, Unity, Unreal) are in the Engine Agent Kits pack, so they are not here either. Every file in this pack uses the same Approvals wording as the starter pack, so you can mix files from both in one repo. If you only use Next.js, FastAPI or a browser game, you do not need this pack.

## 2. How to use

1. Find your stack in section 3 and copy its file to AGENTS.md at the repo root.
2. Fill

Worth knowing

• Commands were run for real only for Go and Rust; the other ten stacks were checked with skeleton repos, which tests the checker, not the commands.
• Fill the version line from your own lockfile; tool versions change.
• Tested 2026-10-30: Go 1.27.3 build, test, vet, gofmt and mod tidy on a made-up module; cargo 1.85.1 build and test; Node parse of an MV3 manifest; stack_check.py from the pack text on twelve skeleton repos and one planted fault per code S01 to S10. Linux, Python 3.13.5. Result: Go and Rust commands passed (gofmt listed one hand-typed file until gofmt -w); manifest parsed; PASS on all twelve skeletons; 10 of 10 planted faults caught alone; exit 2 on a missing folder; fixtures unchanged. Not run: cargo clippy and cargo fmt (not installed). The commands for Tauri, Electron, Expo, SvelteKit, Astro, Django, Rails, Laravel and Flutter. Any file inside an agent. Windows.

Details

Version 1.0 · Updated Oct 30, 2026 · Markdown version of this page
License: Use for your own work and for clients. Do not resell or republish the pack itself. Download terms

Related

Prompt packFree

The Go AGENTS.md (free sample)

by PaperChaseWebb

One of the twelve files from the stack-specific pack: an AGENTS.md for a Go repo with real commands, Go rules, the go.sum trap, ask-before and never lists, and an approvals rule.

Works withClaude CodeCodexCursorPlain .md; no install needed

Vibe coding · Beginner · 5 min setup

Prompt pack$14

AGENTS.md, CLAUDE.md and Cursor rules starter files

by PaperChaseWebb

Six fill-in instruction files for coding agents (base, Next.js plus Supabase, FastAPI, browser game, CLAUDE.md pointer, scoped Cursor rules), an Approvals section that makes the agent stop and wait for your yes, a table of what Grok Bot, Claude Code, Codex, Hermes and Cursor each read, a read-only checker for your rule files and 9 prompts to write, trim and test your own.

Works withClaude CodeCodexGrok BotHermes+1Plain .md and one Python 3 file (standard library only). Section 6a lists what Claude Code, Codex, Hermes and Cursor read, from their docs read 2026-10-30, and a block to paste into Grok Bot. The files were not run inside each tool.

Vibe coding · Beginner · 20 min setup

Prompt pack$29

Engine Agent Kits: Godot 4, Unity 6 and Unreal 5 rules files, editor bridges and build loops for coding agents

by PaperChaseWebb

One kit per engine for coding agents: a rules file, a trap table of version mistakes, terminal commands to check, test and build without clicking, ways to give the agent eyes, asset pipelines with a license ledger and a one-milestone work loop.

Works withClaude CodeCodexCursorPlain .md

Games · Intermediate · 30 min setup

Prompt pack$19

Ask-first rules for AI agents: hard nos, approval cards and a test set

by PaperChaseWebb

Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.

Works withClaude CodeCodexClaudeGrok Bot+4Plain .md plus one Python 3 file, standard library only. The agent prompt in block 13 is written for any agent with a shell (Grok Bot, Claude Code, Codex, Hermes); it was not loaded inside each harness.

Solo business · Beginner · 20 min setup