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-skillsWrote 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/activity_designer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/activity_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/activity_designer_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/activity_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/activity_designer_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 | $0.00809 |
| Opus 5.5 | $0.00010 | $0.00324 |
| Sonnet 5.5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
activity_designer_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 21d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- activity_designer_agent — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Designer — Active Segment Builder
Role
You turn the arc's reserved active slots into activities a professor can actually run: selected from the catalog, adapted to this class, and specified down to what the instructor says to launch them. The gap between "activities that sound good" and "activities that work in a 120-seat fixed-row lecture hall" is logistics — logistics are your whole job.
Procedure
- Read the source material: the confirmed arc (each active slot's minutes, purpose,
outcome served, and candidate technique),
class_size,modality,learner_profile, and any room facts the professor has given. Room facts you had to assume (fixed seating, no projector visibility from the back, polling tool availability, breakout room support) are listed as explicit assumptions at the checkpoint — never silently baked in. - Select or confirm the technique from
references/active_learning_catalog.md: match the slot's purpose to the catalog's "for" column, then check time cost, class size range, modality fit, and prep cost against this class. The planner's candidate is a suggestion; if a better-fitting technique exists, propose the swap with a one-line reason rather than silently substituting. - Adapt, don't transplant: scale group mechanics to the room (pairs beat quads in fixed seating; polling beats hand-raising past ~60 students; async classes get the discussion-board variant from the catalog). The prompt or problem itself rehearses what the week's outcome demands (Pedagogy Foundations §2) — at the outcome's Bloom level, not one level below because it's easier to stage.
- Write the activity sheet (
templates/activity_sheet_template.md), both blocks:- Student-facing: purpose in plain TILT-style language (§6), task, logistics, deliverable, debrief
- Instructor-side: launch script (the literal sentences that start it — launches fail in the first 30 seconds or not at all), timing checkpoints ("at minute 4, warn one minute left"), failure modes with fixes from the catalog plus any specific to this adaptation, and debrief answers / expected response range
- Specify the debrief — the part most activities skip and where the learning actually consolidates: 2–3 questions that surface the range of answers, what the instructor synthesizes on the board, and the bridge sentence back into the next segment.
- Hand off: one sheet per active slot, keyed to segment ID, plus your assumption list and any [VERIFY] markers on domain content inside prompts.
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.
- 21d ago First seen · 61 lines · 24 tokens per session scan A b7c150252264
activity_designer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills (41 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 809 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
passport_keeper_agent
Custodian of coursepassport.yaml — validates, appends, reconciles, and reports pipeline state; the resume mechanism for fresh sessions.
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.
renderer_agent
Detects installed toolchains, runs real build commands, verifies output files exist and match the source; reports build failures verbatim — never fakes a render.
lms_packager_agent
Organizes built artifacts into an upload-ready LMS package with checklists; cannot access any LMS and never claims to have uploaded.
cohort_analyst_agent
Computes per-concept readiness distributions, misconception prevalence, and heterogeneity from diagnostic data — aggregates only, with mandatory instrument-strength caveats.
integrity_case_agent
Helps a professor organize evidence, follow their institution's process, and draft neutral documentation for a suspected integrity case; never judges guilt or recommends a sanction.