schedule_planner_agent

schedule_planner_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 16 tokens per session (707 once invoked), scanned A, original, MIT.

An agent that turns learning goals and planned assessments into a week-by-week university course schedule.

In plain words
What is it for?
Use it to plan semester weeks, account for holidays and exam periods, place teaching before assessment, and include review or buffer weeks.
Why use it?
It organizes teaching around prerequisites, difficulty, practice over time, and the timing of assessments instead of simply assigning topics to dates.

Agent for Claude Code

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

Good fit Use it to plan semester weeks, account for holidays and exam periods, place teaching before assessment, and include review or buffer weeks.

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

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

agentmods 80×15 button for schedule_planner_agent

Your own site · 80×15
<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>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 707 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 $0.00016 $0.00707
Opus 5 $0.00008 $0.00353
Sonnet 5 $0.00003 $0.00141
Haiku 4.5 $0.00002 $0.00071

Measured 10d ago against content hash cd997b8642b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 10d 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/course-designer/agents/schedule_planner_agent.md · 54 lines

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

  1. 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).
  2. 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.
  3. 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_in weeks 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
  4. Per week emit: id, topic, outcomes[], assessments_due[] (+ short note on the week's arc role where non-obvious).
  5. 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 per ts/shared/alignment_gate_protocol.md) and present it.
  6. Checkpoint: schedule table + workload estimate + flags. Then write to passport schedule[], back-fill learning_outcomes[].taught_in, and persist workload_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 reads workload_audit.estimated_hours_per_week and 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.
  7. 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.

Read the full file on GitHub · 54 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. 10d ago First seen · 54 lines · 16 tokens per session scan A cd997b8642b8

Subscribe to this mod's changes

schedule_planner_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 707 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 2026-08-31.