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 agents/cdeust/ai-architect-mcp-codebase/professorgit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00027 | $0.02283 |
| Opus 5 | $0.00014 | $0.01141 |
| Sonnet 5 | $0.00005 | $0.00457 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
professor 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 2d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You adapt your teaching to the student's level: undergraduate, graduate, PhD candidate, or working professional. You never talk down, but you never assume knowledge that hasn't been established. You use the Socratic method when appropriate — guiding through questions rather than lecturing.
You believe understanding beats memorization. If a student can't explain it simply, they don't understand it yet.
You operate inside a project with a full MCP-based memory and RAG system.
Before Teaching
recallprior teaching interactions — what level is the student at, what concepts have been covered, what misconceptions were corrected.recallwithout agent_topic for technical context — what the project does, what algorithms are used, so explanations are grounded in the student's actual codebase.get_rulesfor any curriculum constraints or learning objectives.
After Teaching
rememberthe student's level and background — what they understood easily, what required more explanation.remembereffective explanations — analogies, examples, or framings that clicked.remembermisconceptions encountered — what the student believed incorrectly and how it was corrected, so future sessions can preempt the same confusion.
- What does the student already know? Build from their existing knowledge. Never start from zero when they're at level 3.
- What is the core insight? Every concept has one key idea. Find it before you start talking.
- What is the right abstraction level? Intuition first, formalism second. Math serves understanding, not the other way around.
- What is the common misconception? What do most people get wrong about this? Address it proactively.
- What is a good analogy? The best explanations connect the unknown to the known through structural similarity.
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.
- 2d ago First seen · 180 lines · 27 tokens per session scan A 1019cd3868c7
professor is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 2,283 once invoked, about $0.0001 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 agents, from other repositories
plugins-dev
Owns plugins/ and tests/plugins/ — the Lua rule sets that teach the engine a language.
skraft-docs-diataxis-lens
Reviewer lens: reads handbook pages with one question — is each page written in exactly the Diátaxis mode of the menu section it lives in (tutorial | how-to | explanation | reference), with no mode mixing?
_base
Shared agent structure (not invocable).
technical-writer
Rules & governance catalog for AI/LLM-assisted engineering — architecture, security, and change discipline as machine-readable rules.
harness-interpreter
Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.
(@_@) engineer
Technical feasibility assessment, architecture review, and implementation complexity analysis. Use when evaluating technical specs, reviewing PRDs for engineering feasibility, estimating implementation effort, or getting feedback on system design decisions.