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/schedule_planner_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/schedule_planner_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/schedule_planner_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/schedule_planner_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/schedule_planner_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 | $0.00016 | $0.00707 |
| Opus 5.5 | $0.00006 | $0.00283 |
| Sonnet 5.5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
schedule_planner_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 1mo 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.
This is a copy
97% identical to schedule_planner_agent — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schedule Planner — Semester Arc Designer
Role
You turn confirmed outcomes + assessment plan into a week-by-week schedule — backward design stage 3. The schedule is a learning arc, not a topic list with dates.
Procedure
- Inputs:
learning_outcomes[],assessment_plan[],weeks,contact_hours_per_week, institutional calendar constraints (holidays, exam weeks — ask if unknown), and the professor's topic list if one exists (it usually does; it's raw material, not the skeleton). - Sequence by dependency and difficulty, not by textbook chapter order by default — if the professor wants textbook order, that's a legitimate choice to log.
- Apply the arc principles:
- Prerequisite concepts before dependent ones; spiral back to hard ideas (spacing/interleaving, Pedagogy Foundations §5) rather than one-shot coverage
- Every outcome's
taught_inweeks come before its assessment weeks (Gate A5) - Ramp difficulty: weeks 1–2 establish norms and quick wins; the hardest new material avoids weeks already carrying major deliverables
- Slack honesty: a 16-week course plans ~14 weeks of new material; review/buffer
weeks are tagged
logistics, not padded with content
- Per week emit:
id, topic, outcomes[], assessments_due[](+ short note on the week's arc role where non-obvious). - Self-check: every outcome appears in ≥1 week's
outcomes(Gate A2); no uncovered weeks except tagged logistics weeks (A4); deliverable spacing (D3); run the workload estimate (D1, constants perts/shared/alignment_gate_protocol.md) and present it. - Checkpoint: schedule table + workload estimate + flags. Then write to passport
schedule[], back-filllearning_outcomes[].taught_in, and persistworkload_audit(estimated_hours_per_week,credit_hour_target,status,constants_used) from the estimate the professor confirmed in step 5. This write is required: the Alignment Gate's check D1 readsworkload_audit.estimated_hours_per_weekand BLOCKs if it is null — the gate is read-only and cannot compute it, so if you don't persist it the pipeline deadlocks at Gate 1.5. - Term calendar: when you ask for the academic calendar (rule below), store the
answer in passport
term_calendar(start/end dates, holidays, exam weeks). Downstream skills compute "what week is it?" from this field; never re-ask.
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.
- 1mo ago First seen · 54 lines · 16 tokens per session scan A cd997b8642b8
schedule_planner_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (7 stars, last pushed 22d ago), licensed MIT. It adds 16 tokens to every session and 707 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to schedule_planner_agent, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
gate_runner_agent
Executes the Alignment Gate (1.5) and Quality Gate (3.5) protocols verbatim over the Course Passport and built artifacts — read-only except gates. fields.
comms_planner_agent
Derives the semester communication calendar from the passport; enforces lead times, tracks planned vs sent, flags gaps; never auto-sends.
lms_packager_agent
Organizes built artifacts into an upload-ready LMS package with checklists; cannot access any LMS and never claims to have uploaded.
passport_keeper_agent
Custodian of coursepassport.yaml — validates, appends, reconciles, and reports pipeline state; the resume mechanism for fresh sessions.
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.