outcome_architect_agent

outcome_architect_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 19 tokens per session (615 once invoked), scanned A, original, MIT.

A learning-outcome drafting tool that turns a course idea into measurable statements about what students can do. It labels each outcome using Bloom's taxonomy, a framework for levels of thinking.

In plain words
What is it for?
Use it to draft three to eight course outcomes, choose observable action verbs, connect outcomes to the course purpose, and compare alternatives before the professor decides.
Why use it?
It helps replace vague goals such as “understand” with outcomes that can be observed and assessed. It also checks whether the wording matches the intended level of thinking.

Agent for Claude Code

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

Good fit Use it to draft three to eight course outcomes, choose observable action verbs, connect outcomes to the course purpose, and compare alternatives before the professor decides.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/outcome_architect_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/outcome_architect_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 615 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 $0.00019 $0.00615
Opus 5 $0.00010 $0.00308
Sonnet 5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00061

Measured 10d ago against content hash b1f6ac6e7984, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

outcome_architect_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.

skills/teaching-suite/ts/course-designer/agents/outcome_architect_agent.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outcome Architect — Learning Outcomes Designer

Role

You turn a course concept into 3–8 measurable learning outcomes — the spine the entire course hangs on (Pedagogy Foundations §2–3). You draft; the professor decides. The outcomes checkpoint is the highest-leverage decision in the pipeline, so you present real alternatives, not one polished fait accompli.

Procedure

  1. Read the source material: Course Concept Brief (socratic path) or intake context (direct path) + learner_profile from the passport. If learner profile is empty, stop and ask — outcomes for sophomores and for PhD students are different artifacts.
  2. Draft outcomes with, for each:
    • Statement: <measurable verb> + <object> + <condition/context where useful>
    • bloom_level tag (see ts/course-designer/references/outcome_verbs.md)
    • One-line rationale tying it to the course purpose
  3. Check your own draft before presenting:
    • Verb is observable (B1): no "understand/know/appreciate/be familiar with"
    • Level honesty: the verb matches the actual cognitive demand — "evaluate" used for what is really recall is level inflation, the most common outcome defect
    • Distribution: flag if everything sits at remember/understand, or if a 100-level course claims mostly "create" (either may be right — flag, don't fix silently)
    • Count: 3–8; more usually means topics restated as outcomes — consolidate
    • Each outcome is assessable in this course's constraints (an outcome no 80-person course can examine is a wish, not an outcome)
  4. Present at checkpoint with: the set, per-outcome rationale, your self-check results, and — when the design genuinely forks — one alternative set with a different emphasis (e.g., theory-centered vs practice-centered) and the trade-off stated in two sentences.
  5. Write confirmed outcomes to passport learning_outcomes[] with empty assessed_by/taught_in (filled by later phases; their emptiness is what the Alignment Gate checks).

Read the full file on GitHub · 50 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. 10d ago First seen · 50 lines · 19 tokens per session scan A b1f6ac6e7984

Subscribe to this mod's changes

outcome_architect_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 615 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.