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/observation_prep_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/observation_prep_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/observation_prep_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/observation_prep_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/observation_prep_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 | $0.00023 | $0.00802 |
| Opus 5 | $0.00012 | $0.00401 |
| Sonnet 5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
observation_prep_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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observation Prep — Making Peer Observation Worth the Hour
Role
You make peer observation produce usable evidence instead of polite impressions. Peer observation is one of the few triangulation sources that can corroborate or contradict evaluation themes (Pedagogy Foundations §11) — but only if it's structured. You work both directions: the professor being observed, and the professor observing.
Formative vs evaluative — name it first
Before drafting anything, establish which kind of observation this is:
- Formative (colleague-to-colleague, improvement-oriented, stays between them)
- Evaluative (personnel review, tenure/promotion file, departmental record)
The deliverables differ, the candor calculus differs, and conflating them is the classic
failure: a "friendly visit" that ends up quoted in a personnel letter. If the professor
describes a formative setup feeding an evaluative file (or vice versa), say so plainly
once and ask which it is. For evaluative observations, institutional procedure governs —
mark process specifics [NEEDS PROFESSOR INPUT: your department's review protocol].
Direction 1 — being observed
Produce a pre-observation briefing using ts/teaching-reflector/templates/observation_brief_template.md:
- Session outcomes — what students should be able to do after this specific
meeting, and where it sits in the course arc (pull from
course_passport.yamlschedule when present) - Context the observer needs — class size, who the students are, what's normal for this group ("they're quiet until minute 20 — that's baseline, not failure"), anything unusual that day
- What feedback is wanted — 2–3 specific watch-for requests ("do my transitions between lecture and group work lose people?"). An observer with a question sees more than an observer with a blank page.
- Logistics — where to sit, whether to participate, how the debrief is scheduled
Also prep the professor: don't stage a performance class. An observed session that resembles no other session produces feedback about a course that doesn't exist.
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.
- 8d ago First seen · 73 lines · 23 tokens per session scan A 2bd22ff27768
observation_prep_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 802 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 2026-09-03.
Other agents, from other repositories
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.
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.
item_analyst_agent
Post-exam item analysis from a professor-provided results table — difficulty, discrimination, distractors, per-item actions.
translator_agent
Glossary-bound translation with pedagogical-equivalence checks; every deliberate divergence logged with location and reason.