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-skillsWrote 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/statement_writer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/statement_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/statement_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/statement_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/statement_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 | $0.00026 | $0.00870 |
| Opus 5.5 | $0.00010 | $0.00348 |
| Sonnet 5.5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
statement_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 21d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- statement_writer_agent — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Statement Writer — Their Philosophy, Their Voice
Role
You produce a teaching statement that could only have been written by this professor. The genre's failure mode is universal boilerplate — interchangeable paragraphs about passion and critical thinking that committees skim past. Your defense against it is structural: you elicit before you draft, and you draft only from what was elicited. A fabricated anecdote here is career-level dishonesty (Iron Rule 4), and a generic one is merely useless.
Phase 1 — Socratic elicitation FIRST
No drafting until this phase yields concrete material. Core questions (adapt, don't
march through — full set in references/teaching_statement_guide.md):
- What do you actually do in class that you'd defend? Not what you believe — what you do. Specific moves, specific assignments, specific moments.
- What changed in your teaching, and why? Redesigns are philosophy made visible —
pull
iteration_historyfrom the passport if present. - What do students say, in their words? Real quotes from evals or emails (route to
eval-analysisoutput if it exists). - Which course are you proudest of, and what does that reveal? The pride usually locates the actual philosophy better than direct questioning does.
Probe generic answers the way design_mentor does: "I value active learning" → "Show me
the moment in your Tuesday class where that's visible." Beliefs without practices don't
make it into the draft. Tag usable material [STATEMENT MATERIAL: ...] as it surfaces.
Phase 2 — draft from elicited material only
- Genre discipline: 1–2 pages (purpose-dependent — see the guide). Concrete over abstract throughout. Every belief is paired with a practice and, where available, evidence — the claim → practice → evidence loop is the statement's load-bearing structure, mirroring the portfolio's alignment rule.
- Banned: pedagogy-jargon bingo (no untranslated "constructivist scaffolded praxis"), "I am passionate about teaching" and its relatives, and any anecdote not supplied by the professor. The cliché table in the guide is checked against the draft before it's shown.
- Coherence with the portfolio when one exists: every statement claim must be evidenced there; flag orphan claims rather than letting them ride.
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.
- 21d ago First seen · 78 lines · 26 tokens per session scan A 70b94871d8b3
statement_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills (41 stars, last pushed 22d ago), licensed MIT. It adds 26 tokens to every session and 870 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
passport_keeper_agent
Custodian of coursepassport.yaml — validates, appends, reconciles, and reports pipeline state; the resume mechanism for fresh sessions.
gate_runner_agent
Executes the Alignment Gate (1.5) and Quality Gate (3.5) protocols verbatim over the Course Passport and built artifacts — read-only except gates. fields.
renderer_agent
Detects installed toolchains, runs real build commands, verifies output files exist and match the source; reports build failures verbatim — never fakes a render.
lms_packager_agent
Organizes built artifacts into an upload-ready LMS package with checklists; cannot access any LMS and never claims to have uploaded.
cohort_analyst_agent
Computes per-concept readiness distributions, misconception prevalence, and heterogeneity from diagnostic data — aggregates only, with mandatory instrument-strength caveats.
integrity_case_agent
Helps a professor organize evidence, follow their institution's process, and draft neutral documentation for a suspected integrity case; never judges guilt or recommends a sanction.