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/hkuds/deeptutor/agents-mdgit clone --depth 1 https://github.com/HKUDS/DeepTutorWhat 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 | $0.01544 | $0.01544 |
| Opus 5 | $0.00772 | $0.00772 |
| Sonnet 5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
DeepTutor 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 today.
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepTutor — Agent-Native Architecture
Overview
DeepTutor is an agent-native intelligent learning companion organized around a two-layer plugin model — single-shot Tools invoked by the LLM, and multi-stage Capabilities that take over a turn — exposed through three entry points: CLI, WebSocket API, and Python SDK.
Architecture
Entry Points: CLI (Typer) | WebSocket /ws | Python SDK
↓ ↓ ↓
┌─────────────────────────────────────────────────┐
│ ChatOrchestrator │
│ routes UnifiedContext → selected Capability │
│ (defaults to `chat`) │
└──────────┬──────────────┬───────────────────────┘
│ │
┌──────────▼──┐ ┌────────▼──────────┐
│ ToolRegistry │ │ CapabilityRegistry │
│ (Level 1) │ │ (Level 2) │
└──────────────┘ └────────────────────┘
All capabilities emit on a shared StreamBus; the orchestrator fans
events out to consumers. Runtime settings live in
data/user/settings/*.json — project-root .env files are intentionally
ignored.
Level 1 — Tools
Single-function tools the LLM picks on demand. Four user-toggleable tools
surface in /settings/tools:
| Tool | Description |
|---|---|
brainstorm |
Breadth-first idea exploration with rationale |
web_search |
Web search with citations |
paper_search |
arXiv preprint search |
reason |
Dedicated deep-reasoning LLM call |
The rest are context-gated: the chat capability auto-mounts them from
ToolMountFlags (presence of a KB, attachments, sandbox availability, …), and
any of them can also be force-enabled via --tool. Auto-mounted set: rag,
read_source, read_memory, write_memory, read_skill, load_tools,
exec, code_execution (sandboxed Python: NL intent → code → run),
list_notebook, write_note, web_fetch, github, cron,
ask_user (pauses the turn and resumes with the user's reply), plus the
mastery-path tools. geogebra_analysis is parked under
COMING_SOON_TOOL_TYPES.
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.
- today Changed · -3 tokens per session aef66501c445
- 2d ago First seen · 139 lines · 1,547 tokens per session scan A fcfc6783e969
DeepTutor AGENTS.md is an instructions file published in the GitHub repository HKUDS/DeepTutor (38,271 stars, last pushed today), licensed Apache-2.0. It adds 1,544 tokens to every session, about $0.0077 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
adk-python AGENTS.md
Instructions for google/adk-python, covering project overview, key components, adk knowledge, architecture, and style, project architecture and development setup.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
CORAL AGENTS.md
Instructions for Human-Agent-Society/CORAL, covering agents.md — ai-assisted contributions to coral, 1. human accountability, 2. scope discipline, 3. duplicate-work checks and 4. keep agent guidance synchronized.
Shannon CLAUDE.md
Instructions for Kocoro-lab/Shannon, covering claude.md, project overview, essential commands, setup & run and local docker builds.
DocMason AGENTS.md
Instructions for JetXu-LLM/DocMason, covering docmason agent contract, identity, ordinary front door, compatible host mapping and first-contact hints.
DocMason copilot-instructions.md
Instructions for JetXu-LLM/DocMason, covering docmason github copilot notes and copilot-specific delta.