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.
npx agentmods add commands/robconery/champion/coursegit clone --depth 1 https://github.com/robconery/championWhat 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 | $0.00031 | $0.00699 |
| Opus 5 | $0.00015 | $0.00349 |
| Sonnet 5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
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.
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
championplugin, so every council agent it names is a plugin agent. When spawning any agent mentioned below, use thechampion: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.mdexists. If it does not, stop immediately and tell the user, politely, that the council cannot work without knowing who it fights for: run/champion:setupfirst (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
- Promise & outcome. The one transformation the course delivers. Who finishes it and what can they now do?
- Curriculum. Modules in learning order, each with its outcome.
- Lessons. Per module, the lesson breakdown with objectives.
- Scripts. Draft lesson scripts in the user's voice (
~/.champion/dossier/VOICE.md), starting with the first module. - Offer fit. How it ties to the user's existing offers and the north star.
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.
- 2d ago First seen · 48 lines · 31 tokens per session scan A fa599d194867
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.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".
setup-bigquery.es
Command "setup-bigquery.es" from minicoohei/ai-agent-camp, covering configuración de autenticación bigquery / gcp, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: instalación de gcloud cli.
setup-content
Lesson command — 教材コンテンツの初回セットアップ.
new-workshop
Spin up a new workshop launch package by answering 8 questions. Generates a complete folder with branded landing page, install guide, 21-email campaign, DM outreach, VSL script, agenda, Notion master doc, and 4 phase-walkthrough video compositions. Reads your BUSINESS-BRAIN.md for voice + brand. Triggers on "new…