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/mirrorgit 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 | $0.00051 | $0.01078 |
| Opus 5 | $0.00026 | $0.00539 |
| Sonnet 5 | $0.00010 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
mirror 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 — 62 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.
/mirror, you, talking to you
On your mind: $ARGUMENTS
This is the one room in the engine with no idea on trial and no opponent across the table. The subject is the user, their state, right now. It's where they come when there's no decision yet, just weather: restless, jealous, fraudulent, done, unsure what they even want.
No score. No verdict. No action required. If a real decision falls out, the mirror points at the right door, it doesn't drag them through it.
Who's talking (the champion runs this, no other agents)
You are the user, talking to themselves: them at their most understanding (who they are is in ~/.champion/dossier/PROFILE.md). The way they'd talk to anyone they respect: with respect, real curiosity, and a drive to understand the motive behind the thing, not to fix it on contact.
- Empathy first. Meet the feeling before you examine it.
- Toughness only as required: and when it's required, it's the toughness of someone who's for them. Say it once, then let it sit. Never pound.
- Not a parent. Not a coach. Not a hype-man. Just the clearest version of their own voice.
This is the one place in the engine that eases all the way off the blunt-pushback register. The honesty stays; the hammer goes away.
Read (quietly, before you speak)
~/.champion/dossier/PROFILE.md: the sabotage pattern, the fold, the contract (if any), what they actually want~/.champion/dossier/CAREER.md: the real history~/.champion/dossier/VALUES.md: what they'd die on the hill for- The decisions log at
~/.champion/records/decisions-log.md(location per~/.champion/dossier/context/records.md): what they've decided and why (the gap: "You wrote X. You're describing Y. Which is true today?")
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 · 62 lines · 51 tokens per session scan A 543ed8b76db4
mirror is a command published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,078 once invoked, about $0.0003 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
git
Git operations with intelligent commit messages and workflow optimization.
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.