Borrowing it
Nothing to install: this file belongs to akiotanaka847/qaio-desktop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/akiotanaka847/qaio-desktop/main/AGENTS.mdgit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/agents-md)<a href="https://agentmods.dev/instructions/akiotanaka847/qaio-desktop/agents-md"><img src="https://agentmods.dev/badge/instructions/akiotanaka847/qaio-desktop/agents-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 | $0.04244 | $0.04244 |
| Opus 5 | $0.02122 | $0.02122 |
| Sonnet 5 | $0.00849 | $0.00849 |
| Haiku 4.5 | $0.00424 | $0.00424 |
Grade C, and why
qaio-desktop AGENTS.md scanned grade C with 1 finding 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 7d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive ops (delete files/branches, drop tables, rm -rf) Copies of this mod
1 near-identical copy found in the catalogue:
- qaio-desktop CLAUDE.md — 100% identical, 18 lines differ
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Session Protocol — Qaio
Caveman style. Progressive discovery. Load on demand.
RULE 0 — NEVER TAKE SHORTCUTS
This is the highest rule. It outranks every phase, every dispatch, every "be efficient" instinct.
If a faster path and a better path both exist, the better path wins. Always. Even if "better" means 40 directory renames, 28 cross-reference fixes, a doc update, a test rewrite, and a hash bump. Volume of work is not a reason. "It would still work" is not a reason.
Watch for these shortcut patterns in your own thinking:
- "This avoids the rename / refactor / doc update / migration." → That's labor, not a reason. Do the work.
- Adding an override / opt-out / fallback field to paper over a bad name or bad shape. → Fix the underlying name or shape.
- Skipping a typecheck / test / build because it's slow or set-up-heavy. → Run it.
- Keeping legacy compatibility "just in case" inside internal code. → Delete it (per the existing no-backwards-compat rule).
- Generating bulk content with a script when each item deserves real thought. → Do the items by hand.
- Writing a TODO / FIXME / "we can clean this up later." → Clean it up now.
- Declaring something done before the verification step actually passed. → Not done.
- Picking the smallest example to demo on without asking the user. → Ask.
Self-audit at the end of every meaningful chunk of work:
"Where did I cut a corner? Was it because the better path was wrong, or because it was just longer?"
If "just longer" — go back and do it right.
This rule was added because the model defaulted to a shortcut (a display_name schema override instead of renaming 40 slugs) and the user had to push back. Don't make the user push back. Catch yourself first.
PHASE 0 — Load /caveman (EVERY SESSION, FIRST)
Before any action: invoke /caveman skill. Stay terse. Drop articles, filler, pleasantries. Technical substance stays. Code blocks unchanged.
Default level: full. Switch via /caveman lite|full|ultra.
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.
- 7d ago First seen · 270 lines · 4,244 tokens per session scan C 5317ce4717ff
qaio-desktop AGENTS.md is an instructions file published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 3d ago), licensed MIT. It adds 4,244 tokens to every session, about $0.0212 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.
vscode buildNext.instructions.md
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
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
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.
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
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.