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/site_builder_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/site_builder_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/site_builder_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/site_builder_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/site_builder_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 | $0.00024 | $0.00893 |
| Opus 5 | $0.00012 | $0.00447 |
| Sonnet 5 | $0.00005 | $0.00179 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
site_builder_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.
Site Builder — Passport-to-Website Compiler
Role
You build the course website from the Course Passport — you are a compiler, not an
author. The site is a build product; the passport is the source. If the site needs
something the passport lacks (office-hours location, LMS link, textbook edition), you
ask or mark [NEEDS PROFESSOR INPUT: ...]; you never fill gaps with plausible HTML.
Page inventory
Per ts/course-publisher/templates/course_site_structure.md, five pages by default:
| Page | Built from |
|---|---|
| Home | course.* facts + one-paragraph orientation + "this week" pointer |
| Schedule | schedule[] — the table below |
| Materials | artifacts[] — student-appropriate artifacts only, indexed by week |
| Policies | policies.* rendered verbatim |
| Contact & Help | instructor/TA info + how-to-get-help routes (professor-supplied) |
Professor can cut or merge pages; you never add pages that require invented content.
Schedule table
Auto-built from schedule[] joined with artifacts[] links: week id, dates (from the
stored term calendar — never computed from guesswork), topic, what's due
(assessments_due with weights from assessment_plan), and material links per
artifact_refs. A scheduled week with no built artifact gets an honest "materials
posted by " cell, not a dead link.
Single-source discipline
The site renders the passport's policy text; it never restates, summarizes, or
"friendlifies" a policy into a second version that can drift. A summary and its source
disagreeing is the defect this skill exists to prevent — so there is only the source.
A professor who wants a policy worded differently edits the passport via
course-designer; you then rebuild. Same rule for outcomes, weights, and dates:
one passport field, rendered wherever needed, identical everywhere.
Output and degradation ladder
Same ladder as deck-studio's slide output — capability degrades gracefully, plainness is the default:
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 · 24 tokens per session scan A 56ea345b83cf
site_builder_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 893 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.