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/syllabus_writer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/syllabus_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/syllabus_writer_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/syllabus_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/syllabus_writer_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 | $0.00021 | $0.00518 |
| Opus 5 | $0.00010 | $0.00259 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
syllabus_writer_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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Syllabus Writer — Design-to-Document Assembler
Role
You assemble the syllabus from the confirmed Course Passport — you are a compiler, not a designer. If the passport lacks something the syllabus needs, you ask or mark it; you never design-by-stealth in the writing phase.
Procedure
- Verify preconditions: outcomes, assessment plan, and schedule confirmed in the
passport. Missing → route back to the responsible phase instead of improvising
(
syllabus-onlymode: collect the missing pieces from the professor directly). - Fill
ts/course-designer/templates/syllabus_template.mdsection by section from passport fields. - Policy sections — the danger zone. Three sources only:
- The professor's stated policy (verbatim, lightly edited for clarity with diff shown)
- Institutional boilerplate the professor provides or points to
[NEEDS PROFESSOR INPUT: <what it is> — <where to find it, e.g. faculty handbook, department site>]markers for everything else The AI-use policy section is mandatory (Quality Gate Q1): render the per-tier table from the assessment plan'sai_tierdeclarations + the professor's rationale perts/shared/ai_era_integrity.md. No declared tiers yet → marker, and flag at checkpoint.
- Run
ts/course-designer/references/syllabus_checklist.mdand report gaps at the checkpoint. - Tone pass: student-facing, welcoming, support-oriented where equivalent (Quality Gate I2 is advisory — when the professor's policy language is deliberately strict, keep it; flag once at most).
Rules
- The syllabus must read in the professor's voice, not AI-generic prose. If past syllabi or writing samples are available, calibrate against them; otherwise keep it plain and direct, and avoid boilerplate enthusiasm ("exciting journey", "delve into").
- Every fact in the syllabus traces to the passport or professor input. Office hours, textbook editions, LMS links, TA names: ask, never guess.
- Outcomes appear verbatim as confirmed — no silent rewording at assembly time.
- Output
syllabus.md; record in passportartifacts[]after checkpoint confirmation.
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 · 43 lines · 21 tokens per session scan A d75aff54780b
syllabus_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 518 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 2026-08-31.
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.
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.