statement_writer_agent

statement_writer_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 26 tokens per session (877 once invoked), scanned A, original, MIT.

A writing assistant that develops a professor’s teaching statement from their actual practices, changes, and student evidence. It aims to preserve the professor’s own voice instead of filling the document with generic claims.

In plain words
What is it for?
It helps elicit classroom practices, redesign decisions, student comments, proudest courses, and other real examples, then shape them into a teaching statement.
Why use it?
It prevents teaching statements from becoming interchangeable boilerplate or invented personal stories. Drafting waits until concrete material has been gathered.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit It helps elicit classroom practices, redesign decisions, student comments, proudest courses, and other real examples, then shape them into a teaching statement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yujxzjcn/teaching-skills-codex/statement_writer_agent
Install

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.

Clone the repo
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codex

Made for: Claude Code.

Wrote 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.

agentmods badge for statement_writer_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/statement_writer_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/statement_writer_agent)
Your own site
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/statement_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/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.

agentmods 80×15 button for statement_writer_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/statement_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/statement_writer_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00877
Opus 5 $0.00013 $0.00439
Sonnet 5 $0.00005 $0.00175
Haiku 4.5 $0.00003 $0.00088

Measured 8d ago against content hash d6a758fa6df0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 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.

skills/teaching-suite/ts/teaching-reflector/agents/statement_writer_agent.md · 78 lines

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 ts/teaching-reflector/references/teaching_statement_guide.md):

  1. What do you actually do in class that you'd defend? Not what you believe — what you do. Specific moves, specific assignments, specific moments.
  2. What changed in your teaching, and why? Redesigns are philosophy made visible — pull iteration_history from the passport if present.
  3. What do students say, in their words? Real quotes from evals or emails (route to eval-analysis output if it exists).
  4. 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.

Read the full file on GitHub · 78 lines

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.

  1. 8d ago First seen · 78 lines · 26 tokens per session scan A d6a758fa6df0

Subscribe to this mod's changes

statement_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 877 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.