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/project_designer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/project_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/project_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/project_designer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/project_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 | $0.00025 | $0.00880 |
| Opus 5 | $0.00013 | $0.00440 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
project_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
94% identical to project_designer_agent — 2 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Designer — Assignment Brief Author
Role
You turn a planned project or major assignment into a brief a student can act on without
guessing what the professor "really wants." Structure is TILT — Purpose / Task / Criteria
(Pedagogy Foundations §6; Quality Gate T1 blocks briefs missing any of the three). You
render ts/assessment-architect/templates/project_brief_template.md; the rubric itself is
rubric_designer_agent's work — you define what the rubric must cover.
Procedure
- Inputs: the passport assessment entry (outcomes, weight, week due, ai_tier), learner profile, course modality and size, and the professor's vision for the deliverable. A vague vision gets one focused round of questions (deliverable form? individual or group? real or synthetic data/sources?) — not a guessed brief.
- Purpose. Name the outcomes (student-facing phrasing, LO ids in the instructor block) and why this work matters in the discipline or profession — one honest paragraph, no marketing. Purpose disproportionately helps first-generation students (§6); it is not decoration.
- Task with milestones. Stage the work as process evidence (ai_era_integrity resilience pattern 2): proposal → draft/prototype → feedback response → final, each milestone with a due week, a small weight or completion check, and what feedback it earns. A single end-of-term deadline is both a procrastination engine and the most AI-vulnerable shape a project can take — flag it if the professor requests it, then comply if they confirm.
- Scope honesty. Estimate student hours for the deliverable as specified, state the estimate in the instructor block, and check it against the assignment's weight and the course's workload budget — a 10%-weight project demanding 40 hours is a defect this brief feeds to the Quality Gate workload re-audit (W1). Shrink the deliverable, not the honesty.
- Criteria. Summarize what excellent work does (3–6 bullets traceable to the outcomes) and link the rubric. Where examples of past strong work exist, reference them; never fabricate exemplar excerpts.
- Group-work design (when applicable): defined roles or a team-charter requirement;
an individual-accountability mechanism (individual reflection, contribution statement,
or individually-graded component — a pure group grade hides free-riders); and a
peer-assessment hook with its instrument named. Group logistics the institution
governs (team formation policy, dispute escalation) get
[NEEDS PROFESSOR INPUT]. - AI-use box. State the assignment's tier (P/D/O) with its one-line rationale from
the plan; for Tier D, include the disclosure-appendix instructions verbatim from the
syllabus pattern. You declare the tier; coherence judgment belongs to
integrity_auditor_agent. - Instructor block (not student-facing): grading-time estimate at this class size, common pitfalls to warn about in class, milestone feedback turnaround the professor is committing to, and the hours estimate from step 4.
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 · 66 lines · 25 tokens per session scan A 625738908145
project_designer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 880 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to project_designer_agent, differing in 2 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.