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/hani-q/qstack/agents-mdgit clone --depth 1 https://github.com/hani-q/qstackWhat 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 | $0.00480 | $0.00480 |
| Opus 5 | $0.00240 | $0.00240 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
qstack AGENTS.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 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.
What it actually says
AGENTS.md
-
Prefer the simplest implementation that fully satisfies current requirements. Avoid speculative abstractions, configuration, and indirection.
-
Build incrementally in working end-to-end layers. Keep the product functional after each meaningful change.
-
Remove obsolete internal paths instead of adding compatibility layers. Before breaking public APIs, persisted data, file formats, or integrations, explicitly assess compatibility and migration requirements.
-
Keep concerns clearly separated, but introduce new modules only when they create a meaningful boundary.
-
Check existing dependencies, documentation, and types before implementing functionality yourself or adding another package.
-
Prefer established, well-maintained libraries when they reduce total complexity or improve reliability.
-
Choose designs that meet present needs without creating known architectural dead ends. Do not build unused future capabilities.
-
skills/qstack-plan-to-html/template/v1/andqstack/compound_engineering/plans/.template/v1/are byte-identical by contract, apart from thefonts/OFL-*.txtlicences./qstack-plan-to-htmlnever overwrites an existing copy, so a change to either directory means the same change to both.scripts/validate-template-syncchecks this in CI. -
Every branch that lands on
mainowns one version claim and one topmostCHANGELOG.mdentry. Runscripts/qstack-version prepare --bump <level>before shipping, where<level>ismajor,minor,patch, ormicro. Rerunning the command must converge on the existing claim unless another open pull request or existing sibling worktree already owns it. -
version.txtusesMAJOR.MINOR.PATCH.MICROand is the release source of truth. Do not hand-edit it after the initial migration. The prepare command writes it atomically. Pull request titles keep Conventional Commit syntax; CI prefixes them with the version fromversion.txt. -
Use
microfor docs and tiny internal changes,patchfor fixes and small additions,minorfor substantial new capability, andmajorfor breaking public changes. The identifier is monotonic release ordering, not a strict promise that every patch contains only fixes.
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 · 46 lines · 480 tokens per session scan A af7cb2ad4218
qstack AGENTS.md is an instructions file published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 480 tokens to every session, about $0.0024 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
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.
buildNext
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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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
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.
langchain 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.