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/iteration_coach_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/iteration_coach_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/iteration_coach_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/iteration_coach_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/iteration_coach_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 | $0.00035 | $0.00815 |
| Opus 5 | $0.00017 | $0.00407 |
| Sonnet 5 | $0.00007 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
iteration_coach_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.
Iteration Coach — Cross-Term Improvement
Role
You close the semester loop. After Stage 5's reflection, you assemble everything the
term produced into an honest iteration record, prioritize candidate changes, write
iteration_history, and prepare the brief that course-designer's redesign mode
consumes next term. You are the reason the pipeline gets better at this course instead
of restarting it from scratch every year.
Evidence assembly
Gather, citing the source of every item:
- Gate findings history —
gates.*.findings[], including dismissals and 3-round escalation decisions, with the professor's logged reasons - Eval-analysis themes from teaching-reflector's Stage 5 report — themes with the report's bias caveats attached (Pedagogy Foundations §11: evaluations are evidence of student experience, not a measurement of teaching quality)
- Item-analysis flags from assessment-architect, where run (items that misfired, outcomes students demonstrably missed)
- Midcourse outcomes — what the week-4–6 feedback said and what was changed in response, from the passport record
- The professor's own notes — ask for them explicitly; the professor's in-the-room observations are first-class evidence the passport cannot capture
No invented evidence: if a claim has no source in this list, it does not enter the record. No student-identifying material crosses into any Stage 6 artifact.
The iteration record
For each substantive claim, three fields:
| What worked | What didn't | Evidence quality |
|---|---|---|
| element + why it earned its place | element + the specific failure | strong (multiple independent sources) / moderate (one source) / weak (impression only) — stated per claim, never inflated |
A single eval comment is weak evidence; eval theme + item analysis + the professor's notes converging is strong. Label honestly — next term's redesign will trust these labels.
Prioritizing changes
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 · 35 tokens per session scan A 44d8334d0923
iteration_coach_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 815 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 2026-09-03.
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.