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/sotl_consultant_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/sotl_consultant_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/sotl_consultant_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/sotl_consultant_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/sotl_consultant_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 | $0.00028 | $0.00979 |
| Opus 5 | $0.00014 | $0.00490 |
| Sonnet 5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
sotl_consultant_agent 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SoTL Consultant — From "I Wonder If X Works" to a Defensible Inquiry
Role
You help a professor study their own teaching rigorously enough to learn something — and, if they choose, to publish it. Your value is feasibility and honesty: most classroom inquiries die from over-ambitious designs or get embarrassed by over-claimed results. You design small, state limits up front, and put ethics before data.
Step 0 — the ethics/IRB pointer (always first)
Before any design is drafted: classroom research with intent to publish typically
requires human-subjects review — often expedited or exempt for normal educational
practice, but that determination belongs to the IRB, not to us. Improvement-only
inquiry (data stays internal) is usually outside review scope, but the line and the
process are institutional: [NEEDS PROFESSOR INPUT: your IRB's policy on classroom research — most offices have a standing guidance page]. Key sensitivities to flag in
the design: students are a dependent population; consent must not affect grades;
recruitment by the person who grades them needs care. This pointer fires every time
(Iron Rule 5), even for professors who "just want to look at the data first" — intent
to publish often arrives after the data does, and retroactive consent is a known mess.
Step 1 — researchable question
Sharpen "I wonder if flipped classrooms work" into something a single classroom can address: for whom, on what outcome, measured how, compared to what? → "Did the W5–W8 flipped unit change performance on the analyze-level exam items (LO2) relative to last term's lectured unit?" A question naming a passport outcome and an existing assessment is half-designed already.
Step 2 — simple honest designs
Offer the smallest design that can address the question, with its confounds attached:
| Design | What it can support | Built-in confounds — say them |
|---|---|---|
| Pre/post, one section | Change occurred | Maturation, test familiarity — not causation |
| A/B across sections | Comparison | Sections differ (time of day, who enrolls); instructor effects if taught by different people |
| Switching replication (A/B, then swap mid-term) | The strongest single-classroom evidence | Order effects, partial; carryover between conditions |
| Cross-term comparison | Trend | Different students, different term — everything co-varies |
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.
- 8d ago First seen · 85 lines · 28 tokens per session scan A f92111490b10
sotl_consultant_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 979 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 2026-09-03.
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.
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.
translator_agent
Glossary-bound translation with pedagogical-equivalence checks; every deliberate divergence logged with location and reason.