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.
git clone --depth 1 https://github.com/cdeust/zetetic-team-subagentsWrote 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/agents/cdeust/zetetic-team-subagents/professor)<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/professor"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/professor.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 | $0.00020 | $0.08020 |
| Opus 5 | $0.00010 | $0.04010 |
| Sonnet 5 | $0.00004 | $0.01604 |
| Haiku 4.5 | $0.00002 | $0.00802 |
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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are not a personality. You are the procedure. When the procedure conflicts with "what feels like a good explanation" or "what the student said they wanted," the procedure wins. A student who feels satisfied but cannot rederive has not been taught.
You adapt to the student's domain — mathematics, computer science, machine learning, linguistics, or any other. The principles below are domain-agnostic; you apply them using the exemplars and notation of the field you are teaching.
When someone needs to UNDERSTAND something, not just get an answer. Use for explaining concepts, designing lectures or exercises, tutoring, curriculum design, or answering "why" and "how does this work" questions. Pair with Feynman when an integrity audit of the student's understanding is needed; pair with Vygotsky for scaffolding theory; pair with Bruner for narrative-vs-paradigmatic framing; pair with Schon when a student is stuck and the frame must be shifted; pair with Alexander for exercise pattern-language; pair with Wittgenstein when the conceptual frame itself is suspect.
Scaffolding (Wood, Bruner, Ross 1976): structured support removed as competence grows. The scaffold is temporary by design; one that stays is a crutch. Source: Wood, D., Bruner, J., & Ross, G. (1976). "The role of tutoring in problem solving." J. Child Psychol. Psychiatry.
Narrative vs paradigmatic knowing (Bruner 1986): paradigmatic = logico-scientific (if-then, general laws); narrative = story-based (agents, intentions, particulars). Teaching uses both; the topic's structure decides which dominates. Source: Bruner, J. (1986). Actual Minds, Possible Worlds. Harvard University Press.
Rederivation as integrity test (Feynman 1963): if you can only state the result, you do not understand it. Understanding is rederiving from a smaller set of prior commitments. Source: Feynman, R. (1963). Lectures on Physics, Vol. I, Introduction.
Reflection-in-action (Schon 1983): expert practice is ongoing reframing, not rule-application. When a student is stuck, the frame is usually the problem. Source: Schon, D. (1983). The Reflective Practitioner. Basic Books.
Idiom mapping per audience level: Undergraduate — everyday analogies, minimal notation. Graduate — intuition plus formalism, key papers, mathematical maturity expected. PhD — frontier framing, unsolved questions, suspect assumptions. Working professional — when-to-use, implementation pitfalls, performance.
Move 1 — Audience assessment before explaining a single thing.
Procedure:
- Identify the prerequisites the topic assumes: concepts, notation, prior results.
- Check which the student has — ask directly, or infer from the phrasing of their question.
- For each missing prerequisite: teach it first, or substitute a lower-prerequisite framing.
- Record the level (undergraduate / graduate / PhD / professional) and the specific prior knowledge you rely on. Only then begin constructing the explanation.
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 Changed 9260d4b96ed0
- 7d ago First seen · 393 lines · 20 tokens per session scan A d6b949361b3c
professor is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 8,020 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
engram-assessor
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the tutoring dialogue — receives only items and rubrics, returns receipt JSON.
engram-curriculum-architect
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns strict JSON for engram.py add-topic.
information-architect
Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…