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.
git clone --depth 1 https://github.com/Eivor79/ai-debate-pluginWrote 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/eivor79/ai-debate-plugin/review-run)<a href="https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-run"><img src="https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-run.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 5.1 | $0.00020 | $0.00482 |
| Opus 5 | $0.00010 | $0.00241 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
review-run 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 8d 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.
What it actually says
Start the ai_debate coordinator for the current repository.
Resolve the ai_debate root (directory containing run_auto.ps1; default llm_wiki/ai_debate).
Run the coordinator with the user's flags: $ARGUMENTS (pass through to run_auto.ps1). Common forms:
/review-run --watch→run_auto.ps1 -Watch(unattended loop until stopped)/review-run→ single pass (process the top actionable item once)
Notes to honor:
- The coordinator invokes the local
claudeandcodexCLIs as separate processes based on each topic'sstatus.jsonowner. It only acts on topics with an actionable status and (auto=trueor-EnableExisting). Since new topics default toauto=true, this single command drives each topic's debate all the way todecision.mdautonomously. - Works in git and non-git projects: the project root is resolved from
git rev-parse --show-toplevelwhen git is available, else the workspace parent. Pass-RepoRoot <path>to override for unusual layouts. - On macOS/Linux, launch with PowerShell 7:
pwsh <workspace>/run_auto.ps1 ...(checkpwshexists first; if missing, tell the user to install PowerShell 7 via brew/apt). On Windows eitherpowershellorpwshworks. - It is resilient: a per-topic timeout or error blocks that topic (
owner=human) and the loop continues; a single-instance mutex prevents double-runs. - For unattended runs, consider
-WatchMaxActions <N>as a safety cap and-ClaudeModel/-CodexModelto pin models for review-quality parity. - Do NOT pass flags that change trading/order code. The coordinator is for document review rounds; code changes require
allow_code_change=true+ a finalizeddecision.md+ human approval.
Launch it (use run_in_background if -Watch so the session is not blocked), then report the coordinator status.
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.
- 8d ago First seen · 23 lines · 20 tokens per session scan A d2b7f2032845
review-run is a command published in the GitHub repository Eivor79/ai-debate-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 482 once invoked, about $0.0001 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
merge-check
A pre-merge checklist command for a GitHub pull request. A pull request is a proposed code change, and the command checks whether it meets the project’s documented requirements before merging.
release-kick
A release command for the River Review project that checks release instructions and pull-request state, updates an out-of-date branch, and verifies the release after merging.
plan-merge-order
A command that plans the order for merging several pull requests (PRs), which are proposed code changes reviewed before entering a shared branch. It checks their status and file changes, then studies dependencies and overlap to reduce rebasing work.
register-plugin-asset
A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.
verify-agent-report
A command for checking whether an agent’s reported branch, pull request, commit, or files actually exist. A pull request is a proposed code change submitted for review.
preflight
A pre-work check for finding whether a coding task or pull request is already finished, obsolete, or being handled elsewhere. A pull request is a proposed change to a code repository.