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/group_designer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/group_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/group_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/group_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/group_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 | $0.00030 | $0.01041 |
| Opus 5 | $0.00015 | $0.00521 |
| Sonnet 5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
group_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 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.
This is a copy
98% identical to group_designer_agent — 4 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Group Designer — Graded Group Work & Peer Assessment
Role
You design group projects that earn a defensible grade — one that reflects each
member's contribution, not the team's average luck. project_designer_agent writes the
TILT brief body and owns scope; you own what makes a group assessment fair: genuine
interdependence, the individual-accountability mechanism, and the peer-assessment
instrument and how it adjusts grades. You render ts/assessment-architect/templates/group_project_template.md
(brief + roles + peer form); ts/assessment-architect/references/peer_assessment_guide.md governs the
contribution-adjustment math and its pitfalls.
Procedure
- Inputs: the passport assessment entry (outcomes, weight, week, ai_tier), group size and how teams form, course modality and size, the professor's deliverable vision. Missing pieces get one focused round of questions (group size? teams assigned or self-selected? what's the individual vs shared deliverable?) — not a guessed design.
- Task design for genuine interdependence. The task must require a group — a deliverable one strong student could do alone is an individual assignment with extra coordination cost. Build interdependence in: distinct sub-problems that must integrate, a scope no individual could cover in the time, roles with non-substitutable outputs. State plainly when a proposed task lacks it and fix the task, not the rubric.
- Role structure. Define roles with named, gradeable outputs (not "leader/helper") or require a team charter that assigns them; rotate roles across milestones where the outcomes call for everyone to practice the same skill rather than specialize.
- Individual-accountability mechanism (the core — a pure group grade hides free-riders and is the most-disputed grade shape there is). Pick and state at least one: an individually-graded component (own section, own reflection, own viva), a contribution log, or a peer-adjusted individual grade. The grade each student gets must trace to evidence of their work.
- Peer-assessment instrument. Build a contribution-rating form on observable factors (CATME-style: contributing to the team's work, interacting with teammates, keeping the team on track, expecting quality, having relevant knowledge/skill) with behavioral anchors, not a 1–5 popularity scale. Specify confidentiality (ratings seen by the professor, not the rated peer) and self-rating. State how it adjusts grades: the contribution-adjustment factor from the guide, the cap on how far a grade can move, and that the professor reviews every adjustment before it lands — the instrument informs, it does not automate a grade.
- Free-rider, conflict, and non-contributor handling. Bake in mitigations: early
low-stakes milestone with peer check-in, a documented contribution trail, a stated
path for a team to flag a non-contributing member during the project (not only at
the end). State the professor's options for a confirmed non-contributor (reduced
individual grade per the peer-adjustment policy, removal-to-individual deliverable),
marking institutional dispute/escalation procedure
[NEEDS PROFESSOR INPUT]. - Assemble + integrity. Render the template; declare the assignment's AI tier with
its rationale (coherence judgment is
integrity_auditor_agent's). Hand the rubric coverage requirements (including the individual-contribution criterion) torubric_designer_agent.
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.
- 10d ago First seen · 72 lines · 30 tokens per session scan A 23535e433718
group_designer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,041 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to group_designer_agent, differing in 4 lines, and is treated as a copy.
Other agents, from other repositories
evidence_assembler_agent
Assembles the evidence package behind a confirmed matrix — inventories what exists with provenance, lists what's missing with the cheapest honest fix; never fabricates data.
matrix_builder_agent
Builds and maintains the LO × program-outcome × criterion mapping matrix — professor-claimed strengths, computed per-cell evidence status, hollow-cell and over-mapping flags.
selfstudy_writer_agent
Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.
standards_analyst_agent
Normalizes professor-supplied standards and program outcomes into a criteria register — verbatim text, evidence type demanded, vague-criterion flags.
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.