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/review-prgit clone --depth 1 https://github.com/robconery/championWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/robconery/champion/review-pr)<a href="https://agentmods.dev/commands/robconery/champion/review-pr"><img src="https://agentmods.dev/badge/commands/robconery/champion/review-pr.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00076 | $0.01350 |
| Opus 5 | $0.00038 | $0.00675 |
| Sonnet 5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
review-pr 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 5d 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 — 78 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.
/review-pr, put the PR on trial
Subject: $ARGUMENTS
A critique gauntlet for code, not a "should the user do this" decision. It exists to make an oversized, AI-generated PR reviewable by one human, and to find the truth about whether it should merge. The orchestrator runs the rounds. The defender is the author (the developer who wrote the code, on trial), not the champion.
The gate that matters most: is the code correct to the spirit of the spec? Everything else, quality, maintainability, standards, security, scope, is weighed under that.
0, Fetch and frame
- If
$ARGUMENTSis a PR number or URL:gh pr view <pr> --json title,body,files,additions,deletions,baseRefName,headRefNameandgh pr diff <pr>. Pull the linked issue/spec if referenced. - If empty: review the current branch's diff against the main branch (
git diff <main>...HEAD), treat the branch/commit messages and any linked task as the spec. - Read the repo's standards:
CLAUDE.md, the.claude/directory, and any lint/format/structure config. These are the house rules the senior-engineer judges against.
If the diff can't be fetched, stop and say so, don't review a guess.
1, Seed, Round 1: Map (spawn in parallel, no attacks yet)
cartographer→ the compression map: the shape, the load-bearing 20% to actually read, the blast radius, and anything changed that the spec doesn't explain.spec-keeper→ the ground truth: the intent (spirit), explicit + implicit acceptance, the standards in play, what was left to judgment.
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.
- 5d ago First seen · 78 lines · 76 tokens per session scan A 6b856affec7d
review-pr is a command published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,350 once invoked, about $0.0004 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.