Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codexnpx agentmods add skills/yujxzjcn/teaching-skills-codex/teaching-suiteWrote 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/skills/yujxzjcn/teaching-skills-codex/teaching-suite)<a href="https://agentmods.dev/skills/yujxzjcn/teaching-skills-codex/teaching-suite"><img src="https://agentmods.dev/badge/skills/yujxzjcn/teaching-skills-codex/teaching-suite/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/skills/yujxzjcn/teaching-skills-codex/teaching-suite"><img src="https://agentmods.dev/badge/skills/yujxzjcn/teaching-skills-codex/teaching-suite.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 | $0.00613 | $0.03111 |
| Opus 5.5 | $0.00245 | $0.01244 |
| Sonnet 5.5 | $0.00123 | $0.00622 |
| Haiku 4.5 | $0.00061 | $0.00311 |
Grade A, and why
teaching-suite 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 22d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teaching Suite for Codex
Codex adapter for the Teaching Skills suite (course design → build →
assess → deliver → reflect → improve). The vendored upstream content lives
under ts/; route through this file first.
This is the sibling Codex distribution of the Claude Code suite
YujxZJCN/teaching-skills. Same
workflow content, Codex-native packaging.
First Rule — load lazily
Do not load the whole suite by default. Select one workflow, read that
workflow's ts/<skill>/WORKFLOW.md, then load only the agent, reference, or
template files needed for the user's current stage. The vendored workflow entry
files are named WORKFLOW.md (not SKILL.md) so Codex registers only this one
router skill instead of every vendored workflow.
Non-negotiables (apply in every workflow)
These are the suite's standing rules. Read ts/shared/checkpoint_protocol.md
and ts/shared/pedagogy_foundations.md when a task touches them; never violate
them even when reading lazily:
- The professor is the pilot. Surface every consequential default at a checkpoint; respect "just proceed"; never auto-finalize person-affecting output.
- No invented context. Empty learner/institution facts are asked for or
marked
[NEEDS PROFESSOR INPUT: …]; uncertain domain claims get[VERIFY: …]. - Person-affecting outputs are evidence-bound (feedback, letters,
interventions): only material the professor provided, no invented anecdotes,
verify-before-send reminder, and student data never enters the Course
Passport (
ts/shared/course_passport_schema.md). - Integrity by design, not detection (
ts/shared/ai_era_integrity.md): no AI-detection tools, ever. - Evidence honesty. Student evaluations are biased small-N signal, not a score.
Course Passport & validators
State lives in course_passport.yaml (ts/shared/course_passport_schema.md),
not the conversation. The deterministic layer travels to Codex — run it when
Python 3 is available:
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 303 B
- manifest.json 1.2 KB
- ts/accreditation-mapper/agents/evidence_assembler_agent.md 3.9 KB
- ts/accreditation-mapper/agents/matrix_builder_agent.md 4.0 KB
- ts/accreditation-mapper/agents/selfstudy_writer_agent.md 4.1 KB
- ts/accreditation-mapper/agents/standards_analyst_agent.md 4.0 KB
- ts/accreditation-mapper/references/accreditation_frameworks.md 5.9 KB
- ts/accreditation-mapper/templates/evidence_index_template.md 2.8 KB
- ts/accreditation-mapper/templates/outcome_matrix_template.md 2.9 KB
- ts/accreditation-mapper/WORKFLOW.md 9.3 KB
- ts/assessment-architect/agents/accommodation_designer_agent.md 4.6 KB
- ts/assessment-architect/agents/answer_key_agent.md 3.7 KB
- ts/assessment-architect/agents/blueprint_agent.md 3.7 KB
- ts/assessment-architect/agents/grade_analyst_agent.md 4.4 KB
- ts/assessment-architect/agents/group_designer_agent.md 4.7 KB
- ts/assessment-architect/agents/integrity_auditor_agent.md 3.9 KB
- ts/assessment-architect/agents/item_analyst_agent.md 4.1 KB
- ts/assessment-architect/agents/item_writer_agent.md 3.9 KB
- ts/assessment-architect/agents/project_designer_agent.md 4.0 KB
- ts/assessment-architect/agents/rubric_designer_agent.md 3.9 KB
- ts/assessment-architect/references/grade_analysis_guide.md 6.2 KB
- ts/assessment-architect/references/item_writing_rules.md 6.1 KB
- ts/assessment-architect/references/lms_export_format.md 2.0 KB
- ts/assessment-architect/references/peer_assessment_guide.md 5.4 KB
- ts/assessment-architect/references/rubric_patterns.md 5.5 KB
- ts/assessment-architect/templates/grade_report_template.md 4.2 KB
- ts/assessment-architect/templates/group_project_template.md 6.1 KB
- ts/assessment-architect/templates/project_brief_template.md 3.9 KB
- ts/assessment-architect/templates/test_blueprint_template.md 2.6 KB
- ts/assessment-architect/WORKFLOW.md 14 KB
- ts/bilingual-courseware/agents/glossary_keeper_agent.md 3.9 KB
- ts/bilingual-courseware/agents/parallel_sync_agent.md 3.6 KB
- ts/bilingual-courseware/agents/terminology_auditor_agent.md 4.0 KB
- ts/bilingual-courseware/agents/translator_agent.md 4.2 KB
- ts/bilingual-courseware/references/emi_conventions.md 7.4 KB
- ts/bilingual-courseware/templates/glossary_template.md 2.7 KB
- ts/bilingual-courseware/templates/sync_register_template.md 2.2 KB
- ts/bilingual-courseware/WORKFLOW.md 9.1 KB
- ts/cohort-analyst/agents/calibration_advisor_agent.md 4.9 KB
- ts/cohort-analyst/agents/cohort_analyst_agent.md 5.1 KB
- ts/cohort-analyst/agents/diagnostic_designer_agent.md 4.9 KB
- ts/cohort-analyst/agents/grouping_strategist_agent.md 4.6 KB
- ts/cohort-analyst/references/analytics_honesty.md 9.7 KB
- ts/cohort-analyst/references/diagnostic_design_guide.md 8.6 KB
- ts/cohort-analyst/templates/cohort_profile_template.md 4.8 KB
- ts/cohort-analyst/templates/diagnostic_template.md 3.9 KB
- ts/cohort-analyst/WORKFLOW.md 10 KB
- ts/commands/ts-accredit.md 438 B
- ts/commands/ts-activities.md 375 B
- ts/commands/ts-align.md 331 B
- ts/commands/ts-announce.md 361 B
- ts/commands/ts-audit.md 503 B
- ts/commands/ts-calibrate.md 369 B
- ts/commands/ts-cohort.md 476 B
- ts/commands/ts-course.md 377 B
- ts/commands/ts-dashboard.md 599 B
- ts/commands/ts-deck.md 504 B
- ts/commands/ts-diagnostic.md 438 B
- ts/commands/ts-evals.md 396 B
- ts/commands/ts-exam.md 395 B
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.
- 22d ago Changed 170ef70e162a
- 1mo ago First seen · 135 lines · 613 tokens per session scan A 232bafaa9b6c
teaching-suite is a skill published in the GitHub repository YujxZJCN/teaching-skills-codex (7 stars, last pushed 22d ago), licensed MIT. It adds 613 tokens to every session and 3,111 once invoked, about $0.0025 per session on Opus 5.5. 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 skills, from other repositories
evidence-based-classroom-designer
Design or redesign any course, class, or training session using evidence-based instructional principles. Use this skill when a teacher, instructor, or instructional designer wants to improve student retention and achievement through classroom design, course design, quiz design, or active learning strategies — even if…
course-storytelling
Use when lesson or course content is correct but forgettable and a concept has to LAND: profiles the learner, breaks the blocking false belief, then rebuilds it as epiphany story → named model → grounded analogy → proof → so-what. NOT outcomes, assessment or module order (that is course-builder), NOT slide visuals…
assessment-architect
Builds assessment instruments for university professors — pipeline Stage 3. 7-agent team covering test blueprints, exam/quiz/question-bank item writing, rubric design (analytic/holistic/single-point), TILT project briefs, AI-era integrity auditing, verified answer keys with worked solutions, and post-exam item…
student-mentor
During-semester student support for university professors. 5-agent team covering feedback on student work (Hattie & Timperley structured, single or batch), struggling-student intervention plans, recommendation letters with bias-aware language checks, difficult student communications, office-hours preparation, and…
teaching-pipeline
Full teaching-lifecycle orchestrator for university professors. 4-agent team driving the six sibling skills through staged gates over the Course Passport: design → alignment gate → build → assess → quality gate → semester delivery loop → reflection → next-term improvement. Resumable from the passport at any week of…
cohort-analyst
A teaching-analysis skill that uses group-level student information to help university professors make evidence-based course and lesson decisions. It studies the cohort, meaning the class as a whole, rather than individual students.