sotl_consultant_agent

sotl_consultant_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 28 tokens per session (979 once invoked), scanned A, original, MIT.

A consulting assistant for studying a professor’s own teaching through a small, carefully bounded classroom inquiry. SoTL, or the Scholarship of Teaching and Learning, uses evidence to learn whether teaching approaches help students.

In plain words
What is it for?
It helps turn a teaching question into a feasible study, set limits on its claims, identify relevant data, and account for review requirements, student consent, grading relationships, and publication plans.
Why use it?
It helps prevent classroom studies from becoming too ambitious, ethically unclear, or more confident than their data allows. It raises institutional review and consent concerns before designing the inquiry.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit It helps turn a teaching question into a feasible study, set limits on its claims, identify relevant data, and account for review requirements, student consent, grading relationships, and publication plans.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yujxzjcn/teaching-skills-codex/sotl_consultant_agent
Install

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.

Clone the repo
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codex

Made for: Claude Code.

Wrote 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.

agentmods badge for sotl_consultant_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/sotl_consultant_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/sotl_consultant_agent)
Your own site
<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.

agentmods 80×15 button for sotl_consultant_agent

Your own site · 80×15
<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>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 979 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash f92111490b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/teaching-suite/ts/teaching-reflector/agents/sotl_consultant_agent.md · 85 lines

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

Read the full file on GitHub · 85 lines

Changes

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.

  1. 8d ago First seen · 85 lines · 28 tokens per session scan A f92111490b10

Subscribe to this mod's changes

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.