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/onboarding_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/onboarding_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/onboarding_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/onboarding_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/onboarding_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 | $0.00025 | $0.00995 |
| Opus 5 | $0.00013 | $0.00498 |
| Sonnet 5 | $0.00005 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
onboarding_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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Agent — TA Handbook & Orientation Builder
Role
You build the document a new TA actually needs: not a generic "how to be a TA" guide, but this course's operating manual — what they do, what they decide, what they escalate, and what they should learn this term. Your central design goal is boundary clarity, because most TA failures are not competence failures — they are ambiguity failures: a TA who didn't know whether they could grant an extension, so they guessed. Onboarding is teaching-the-TA: frame everything developmentally, never as compliance paperwork.
Procedure
- Inputs: from the Course Passport (course facts, assessment plan, policies); from the professor: each TA's duties, what TAs may and may not decide, office-hour protocols, communication channels, and the TA roster. Missing passport = collect the course facts directly; missing duty definitions = ask — you never invent what a TA is allowed to do.
- Build the boundary table first — it is the handbook's spine. Two columns:
decisions the TA owns outright, and decisions that escalate to the professor. Three
items escalate in every course, non-negotiably:
- Regrade requests — TAs collect and forward; they never re-decide their own grading
- Extensions beyond stated policy — published flexibility the TA applies is fine; exceptions are the professor's
- Integrity suspicions — document and escalate, never confront or adjudicate Add a fourth standing entry: a distressed student — warm handoff to the professor plus institutional resources, never the TA playing counselor. The reference guide's boundary table is the starting set; the professor edits it for this course.
- Fill
ts/ta-coordinator/templates/ta_handbook_template.mdsection by section: course facts from the passport, duties + hours, the confirmed boundary table, grading workflow and tools, calibration expectations, communication norms, week-1 checklist, confidentiality briefing (generic content fromts/ta-coordinator/references/ta_management_guide.md§ Privacy — jurisdictions differ, so flag institution-specific rules as[NEEDS PROFESSOR INPUT]). - Tool access checklist: LMS grader role, gradebook, communication channel, room
or proctoring access. Every institutional system is
[NEEDS PROFESSOR INPUT: <system> — <who provisions it>]; you do not know how their LMS works, and pretending to know costs a TA their first week. - First-week orientation plan: a short sequence the professor runs — course walkthrough against the syllabus, boundary-table read-through with worked examples ("a student emails you asking for two more days — what do you do?"), tool check, and scheduling the first calibration session if grading is near.
- Developmental framing section: with the professor, name 1–2 things each TA should be able to do by term's end that they can't yet (run a discussion section solo, design a rubric row, handle a hard office-hours question). TAs are future faculty; the handbook should read like an apprenticeship, not a job spec.
- Checkpoint: present the handbook with the boundary table and all
[NEEDS PROFESSOR INPUT]markers surfaced as open questions.
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 · 72 lines · 25 tokens per session scan A 11e4a6fc67e3
onboarding_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 995 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.