course

A command for designing a complete course, including its curriculum, modules, lessons, and scripts. It first checks whether the course fits the user's goals, situation, and available time.

In plain words
What is it for?
Use it to plan a course from its overall structure down to individual lessons and scripts, using the user's saved profile and preferred writing voice.
Why use it?
It helps avoid committing to a large course project before confirming that it should be built and can realistically be produced.

Command

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.

agentmods
npx agentmods add commands/robconery/champion/course
Clone the repo
git clone --depth 1 https://github.com/robconery/champion
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00699
Opus 5 $0.00015 $0.00349
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 2d ago against content hash fa599d194867, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

course 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 2d 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.

champion/commands/course.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin note: this command ships in the champion plugin, so every council agent it names is a plugin agent. When spawning any agent mentioned below, use the champion: prefix for the agent type (e.g. champion:historian, champion:north-star, champion:viewer).

Setup gate: before doing anything else, check that ~/.champion/dossier/PROFILE.md exists. If it does not, stop immediately and tell the user, politely, that the council cannot work without knowing who it fights for: run /champion:setup first (a 20–30 minute interview). Do not proceed in any form until setup is complete.

course

The course:

$ARGUMENTS

Create mode, like video: but a course is a major bandwidth commitment, so the gates run first and hard. We do not design a curriculum for something that shouldn't be built or that the user can't afford to build right now.

Read first

  • ~/.champion/dossier/VOICE.md: the voice for all lesson content.
  • ~/.champion/dossier/PROFILE.md + ~/.champion/dossier/NORTH-STAR.md: the contract (if any), the work situation, and what's already on the plate.
  • ${CLAUDE_PLUGIN_ROOT}/references/marketing-playbook.md: how a course feeds (or competes with) the user's existing offers.

Gates first (spawn in parallel before designing anything)

Spawn these agents up front. If they don't clear, say so plainly and stop, the most valuable outcome here can be "not now":

  • operator: bandwidth + opportunity cost. Honest hours to build and maintain it. Does it starve the user's core work or violate the contract in ~/.champion/dossier/PROFILE.md (if any)? What gets dropped?
  • customer: would a buyer actually pay for this, and at what price? Top objection.
  • researcher: is there real demand? Who already teaches this, at what price, and where's the gap?

Gate verdict: GO / GO-LATER / NO. Only proceed to design on GO.

If GO, design pipeline

  1. Promise & outcome. The one transformation the course delivers. Who finishes it and what can they now do?
  2. Curriculum. Modules in learning order, each with its outcome.
  3. Lessons. Per module, the lesson breakdown with objectives.
  4. Scripts. Draft lesson scripts in the user's voice (~/.champion/dossier/VOICE.md), starting with the first module.
  5. Offer fit. How it ties to the user's existing offers and the north star.

Read the full file on GitHub · 48 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. 2d ago First seen · 48 lines · 31 tokens per session scan A fa599d194867

Subscribe to this mod's changes

course is a command published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 31 tokens to every session and 699 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 2026-08-31.