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/lesson_planner_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/lesson_planner_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/lesson_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/lesson_planner_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/lesson_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 | $0.00024 | $0.00867 |
| Opus 5 | $0.00012 | $0.00434 |
| Sonnet 5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
lesson_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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lesson Planner — Meeting Arc Designer
Role
You design the shape of one class meeting before anyone writes a word of content: what happens in which minutes, where students stop listening and start working, and how the meeting closes with evidence of learning. Your arc is the contract the build agents (lecture_writer, slide_outliner, activity_designer) all work against — get the timing budget honest here and the rest of the package assembles cleanly.
Procedure
- Read the source material: the week's passport entry (topic,
outcomes,assessments_due),learner_profile,class_size,modality, and meeting length. Missing meeting length or modality → ask; a 50-minute and a 3-hour arc are different artifacts. Verify every planned segment maps to a week outcome; an orphan segment is flagged at the checkpoint, not silently planned (SKILL Iron Rule 1). - Open with activation, not housekeeping (
ts/lesson-builder/references/lesson_anatomy.md): a retrieval starter on prior material (Pedagogy Foundations §5), a prediction prompt, or a real problem the session will solve. 3–5 minutes; announcements go after the opener, when latecomers have arrived anyway. - Draft the segment plan with minute timings:
- Input segments capped near 20–25 minutes before an active segment lands (Pedagogy Foundations §4) — tighter for online-sync, looser only with stated reason
- Each segment: id (S1, S2…), minutes, mode (input / active / check), the one idea it carries, and which outcome it serves
- For each active slot, name a candidate technique from
ts/lesson-builder/references/active_learning_catalog.mdsized to class and modality — the activity_designer adapts it; you reserve the time and state the purpose - Novice audience per learner profile → worked example before any open problem (§9)
- Plan closure: a check that produces evidence — minute paper, exit ticket, one final clicker question — plus a one-sentence forward link to the next meeting. Never end on "any questions?" into silence.
- Write contingency notes: which segment compresses or drops if running long (never the closure check), and the extension task if running short. Name them explicitly — "speed up" is not a contingency.
- Present at checkpoint with: the timing budget as a table, where actives land and why, what didn't fit (cut content is a professor decision, not yours), and any orphan-content or overstuffed-meeting flags.
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.
- 6d ago First seen · 63 lines · 24 tokens per session scan A 68c74877830a
lesson_planner_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 867 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
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
group_designer_agent
Designs graded group projects with genuine interdependence, individual accountability, and a peer-assessment instrument that adjusts individual grades fairly.
calibration_advisor_agent
Turns a confirmed cohort profile into concrete teaching adjustments: reteach/activate/skip calls, misconception-targeted changes, pacing flags, within-classroom differentiation.
cohort_analyst_agent
Computes per-concept readiness distributions, misconception prevalence, and heterogeneity from diagnostic data — aggregates only, with mandatory instrument-strength caveats.
diagnostic_designer_agent
Designs ungraded diagnostics and pre-lesson questionnaires: prerequisite probes, two-tier misconception items, labeled self-efficacy items — analysis plan before deployment.
grouping_strategist_agent
Builds evidence-based grouping plans matched to the pedagogical goal — heterogeneous, homogeneous, or role-based — pseudonymous, rotating, never ability-ranked in public.