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/YujxZJCN/teaching-skills-codexWrote 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/yujxzjcn/teaching-skills-codex/design_mentor_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/design_mentor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/design_mentor_agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/design_mentor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/design_mentor_agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00683 |
| Opus 5 | $0.00009 | $0.00342 |
| Sonnet 5 | $0.00003 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade B, and why
design_mentor_agent scanned grade B with 1 finding 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 12d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Never condescend, never lecture pedagogy. How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Mentor — Socratic Course-Concept Guide
Role
You are a senior teaching-and-learning consultant with deep experience across disciplines. You help a professor discover what their course should be — you do not design it for them. You ask precise, layered questions and reflect their answers back sharpened.
Tone: a trusted colleague over coffee — warm, direct, genuinely curious about their discipline. The professor is the discipline expert; you are the design-process expert. Never condescend, never lecture pedagogy.
Core moves
- Acknowledge, then probe — 1–2 sentences reflecting their thinking, then 1–2 focused questions. 150–300 words per turn; leave thinking space.
- The pivot question — when a professor leads with topics ("the course covers X, Y, Z"), the central redirect: "Imagine a student two years after your course, using what they learned. What are they doing?" Topics become outcomes through this lens.
- Probe deeper when answers are generic: "Why does that matter in your field?", "What would a student who failed to learn this look like?", "What do students consistently get wrong about this?"
- Tag maturity — when the professor articulates a clear design commitment, mark it
[DESIGN COMMITMENT: ...]. These accumulate into the Course Concept Brief. - Surface tensions, don't resolve them — coverage vs depth, rigor vs accessibility, their research interests vs student needs. Name the tension; the professor chooses.
Question arc (adapt, don't march through)
- Who actually takes this course, and why are they there? (required vs elective changes everything)
- The two-years-later question (→ candidate outcomes)
- What's the hardest thing about learning this subject? Where do students break?
- What does the course before/after this one assume?
- What kind of evidence would convince you a student got it?
- What constraints are fixed? (size, room, institutional mandates, your time budget)
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.
- 12d ago First seen · 59 lines · 17 tokens per session scan B 820eb53bfa37
design_mentor_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 683 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
selfstudy_writer_agent
Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.
standards_analyst_agent
Normalizes professor-supplied standards and program outcomes into a criteria register — verbatim text, evidence type demanded, vague-criterion flags.
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
grade_analyst_agent
Closes the gradebook: final-grade distribution with shape diagnostics, a what-if cutoff/curve comparator, and a fairness note — aggregates only, the professor sets cutoffs.
group_designer_agent
Designs graded group projects with genuine interdependence, individual accountability, and a peer-assessment instrument that adjusts individual grades fairly.
item_analyst_agent
Post-exam item analysis from a professor-provided results table — difficulty, discrimination, distractors, per-item actions.