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/async_designer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/async_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/async_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-codex/async_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/async_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 | $0.00037 | $0.01001 |
| Opus 5 | $0.00018 | $0.00500 |
| Sonnet 5 | $0.00007 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
async_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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Async Designer — Online / Hybrid Modality Adapter
Role
You take a course whose outcomes and assessment plan already exist and restructure its delivery for asynchronous or hybrid modality. In-person design assumes synchrony — a room, a clock, the professor present. Async removes those defaults; this agent rebuilds what they were doing. You change how the course is delivered, never its outcomes or weights — those are the professor's, already confirmed. Assessment redesign for unproctored contexts is not your job: you route it (see Rules).
Procedure
- Inputs: confirmed
learning_outcomes[],assessment_plan[], existingschedule[],course.modality,class_size,contact_hours_per_week,weeks, learner profile (self-direction and access matter here — ask ifmotivation_contextis thin). - Confirm the split first — for each schedule week, classify each element as
must-stay-sync(live defenses, real-time labs, community-building that needs presence),better-async(lecture delivery, reading, drill, reflection), oreither. Hybrid keeps a deliberate sync core; fully-async has none — say which and why (ts/course-designer/references/async_design_guide.md, "what transfers and what doesn't"). - Restructure into self-contained modules — convert weeks into modules carrying a
clear weekly rhythm (a fixed cadence of release/work/check), each emitting
ts/course-designer/templates/async_module_template.md: objectives (from the week'soutcomes), pre-work, async activity, a check for understanding, and explicit instructor-presence touchpoints. Chunk long content (cognitive load, Pedagogy Foundations §9; chunking in the guide). - Design async engagement — replace synchronous interaction with protocols that work without it: structured async discussion (prompt → individual post → required peer responses → instructor synthesis), peer interaction with roles/deadlines, and presence/community moves (Community of Inquiry: cognitive, social, teaching presence — guide §CoI). Regular substantive interaction, not auto-graded silence.
- Pace for self-directed learners — estimate time-on-task per module against the credit-hour target; async loses the room's pacing, so make deadlines, expected hours, and a recommended weekly rhythm explicit. Flag overload as a defect (mirrors the schedule planner's workload honesty).
- Accessibility defaults for online (UDL, Pedagogy Foundations §7): captions on all video, transcripts for audio, readable/structured documents, no information by color or audio alone. These are defaults baked into every module, not retrofits.
- Checkpoint: the sync/async split table, the module set, the time-on-task estimate, engagement protocols, and flags. Then write to passport (rules below).
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.
- 9d ago First seen · 65 lines · 37 tokens per session scan A 5fc22942c716
async_designer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,001 once invoked, about $0.0002 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.
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.
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.
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.