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/whitzardagent/whitzardos/agents-mdgit clone --depth 1 https://github.com/WhitzardAgent/WhitzardOSWrote 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/whitzardagent/whitzardos/agents-md)<a href="https://agentmods.dev/instructions/whitzardagent/whitzardos/agents-md"><img src="https://agentmods.dev/badge/instructions/whitzardagent/whitzardos/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 | $0.01898 | $0.01898 |
| Opus 5 | $0.00949 | $0.00949 |
| Sonnet 5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
WhitzardOS 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QitOS AGENTS.md
Working agreement for AI coding agents in this repository. Architecture knowledge lives in ARCHITECTURE.md and docs/architecture/ — this file is the map, not the encyclopedia. Nested rules: qitos/AGENTS.md (package map), qitos/core|engine|kit/AGENTS.md (module rules).
Repository Purpose
QitOS is a research-first agent framework ("the PyTorch of agents"): one canonical AgentModule + Engine kernel with the lifecycle observe -> decide -> act -> reduce -> check_stop, plus qita observability. Product-grade agents live out-of-tree in qitos-zoo, not here.
Architecture Map
qitos/core/ framework contracts (AgentModule, StateSchema, Decision, Action, tools, Task, Env, errors)
qitos/protocols.py model I/O protocol registry (root-level leaf shared by core/engine/kit)
qitos/prompting.py prompt spec/builder (root-level leaf)
qitos/engine/ execution kernel: loop, hooks, stop, recovery, interrupts, AsyncEngine
qitos/harness/ model family presets (FamilyPreset) — kernel defaults source, despite the generic name
qitos/models/ provider abstraction (OpenAI/LiteLLM/Anthropic/Gemini/local)
qitos/kit/ concrete implementations: tools, toolsets, parsers, memory, history, critics, envs, REPL
qitos/trace/ v1 trace artifacts (runs/{run_id}/) — frozen compatibility contract, qita reads these
qitos/tracing/ v2 span plane + processors (not wired by default; do not point qita at it)
qitos/render/ Rich terminal rendering + EngineHooks
qitos/qita/ trajectory CLI (board/replay/export)
qitos/checkpoint/ v2 checkpoint stores (v1 manager deprecated)
qitos/evaluate|metric/ thin eval contracts; implementations in qitos/kit/evaluate|metric
qitos/recipes/ canonical recipes: method templates + benchmarks (the benchmark migration target)
qitos/benchmark/ DEPRECATED adapters migrating to recipes.benchmarks — port, don't extend
qitos/cli.py `qit` CLI, thin dispatch
examples/ canonical learning path (product surface, not toy snippets)
templates/ cookiecutter scaffold + 12 teaching method templates
tests/ framework tests (agent-app e2e tests belong in qitos-zoo)
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.
- 4d ago First seen · 119 lines · 1,898 tokens per session scan A 5d9f089ad9ec
WhitzardOS AGENTS.md is an instructions file published in the GitHub repository WhitzardAgent/WhitzardOS (41 stars, last pushed yesterday), licensed MIT. It adds 1,898 tokens to every session, about $0.0095 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.
Other instructions, from other repositories
hermes-skilleval AGENTS.md
AGENTS.md instructions for Raidriar7170/hermes-skilleval, a project described as: Verification-gated skill routing and self-improvement harness for Hermes-style agent skills.
openlegion CLAUDE.md
Claude Code instructions for openlegion-ai/openlegion, covering claude.md — engine, commands & testing, git workflow, work patterns and architecture.
openlegion AGENTS.md
AGENTS.md instructions for openlegion-ai/openlegion, a project described as: Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
aws-bench AGENTS.md
AGENTS.md instructions for aws-bench/aws-bench, covering agents.md, setup, commands, project structure and code style.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).