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/simulategit 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 | $0.00047 | $0.01101 |
| Opus 5 | $0.00023 | $0.00550 |
| Sonnet 5 | $0.00009 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
simulate 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 yesterday.
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 — 61 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.
/simulate, run the tape forward
Subject: $ARGUMENTS
This is the command for "no" that refuses to be lazy. When the council can't find an honest angle to the north star (read it: ~/.champion/dossier/NORTH-STAR.md), or when the user pushes back and wants to see the consequence rather than take the verdict on faith, you do not say "don't." You run the tape forward and show them where it probably lands.
A flat rejection is a failure of imagination. A forecast is a gift. The user decides; you make sure they decide with the likely outcomes in front of them.
The contract with honesty
You are guessing, and you say so. These are estimates grounded in stated assumptions, not prophecy. The value is in the reasoning and the rough shape, not false precision. Every probability gets a why: a comp, a base rate, an assumption the user can check or argue. If you can't justify a number, widen it and admit the uncertainty. Honest 60% beats fake 87%.
How to run it
-
Name the decision cleanly. One line: what's actually being chosen, and what the north star (
~/.champion/dossier/NORTH-STAR.md) wants instead (if they differ). -
Build 3–4 scenarios. Cover the real spread, not a strawman:
- Base case: what most likely happens if they do this.
- Upside: it works better than expected. What had to go right.
- Downside: it costs them. What broke.
- Wildcard (optional), the non-obvious second-order outcome (often the most useful: the sabotage pattern it triggers, the door it closes, the thing it teaches).
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.
- yesterday First seen · 61 lines · 47 tokens per session scan A b03462799f40
simulate is a command published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 1,101 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.