evaluate

A command for evaluating an idea, business venture, job listing, or offer through three rounds of review by a council of agents. It produces a logged score from 1 to 5.

In plain words
What is it for?
Use it when deciding whether to pursue a product idea, accept a job or offer, or take another significant opportunity, with research on markets, companies, roles, demand, and pay where relevant.
Why use it?
It gives a structured process for a real decision instead of relying only on an impulse or a single point of view.

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/evaluate
Clone the repo
git clone --depth 1 https://github.com/robconery/champion
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,121 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 $0.00046 $0.01121
Opus 5 $0.00023 $0.00561
Sonnet 5 $0.00009 $0.00224
Haiku 4.5 $0.00005 $0.00112

Measured 2d ago against content hash c0cfb8b504b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate 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/evaluate.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 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.

/evaluate, run the gauntlet

Subject: $ARGUMENTS

Full decision engine. Read ${CLAUDE_PLUGIN_ROOT}/gauntlets/README.md first. The orchestrator agent runs the session; the champion is the user's advocate inside the room.

0, Frame the conversion

Identify what's actually being decided and who the buyer is:

  • Venture / product → customer = the target buyer; researcher fetches market, comps, pricing, demand
  • Job listing → customer = the hiring manager and the user-as-candidate; researcher fetches company (funding, news, sentiment), role, and salary bands. If a URL is in the argument, fetch it first.
  • Offer / contract / partnership → customer = the counterparty; researcher fetches comps and the other side's incentives
  • Pure idea → customer = whoever the idea ultimately has to win over

1, Seed (spawn in parallel, before any rounds)

Spawn two agents simultaneously. Each returns its output contract:

  • researcher → the fact brief (balanced, sourced)
  • historian → precedent + sabotage-pattern/brave-walk read from the decisions log at ~/.champion/records/decisions-log.md (location per ~/.champion/dossier/context/records.md) and ~/.champion/dossier/CAREER.md

Both briefs feed every voice in every round.

2, Round 1: Diverge

Spawn in parallel, giving each the researcher brief:

  • expansionist (leads), biggest version, the nugget, the reframe
  • opportunist: money math and leverage

Read the full file on GitHub · 79 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 · 79 lines · 46 tokens per session scan A c0cfb8b504b6

Subscribe to this mod's changes

evaluate is a command published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 46 tokens to every session and 1,121 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.