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/robbedoo/minimax-plugin-claude-code/adversarial-reviewgit clone --depth 1 https://github.com/robbedoo/minimax-plugin-claude-codeWrote 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/robbedoo/minimax-plugin-claude-code/adversarial-review)<a href="https://agentmods.dev/commands/robbedoo/minimax-plugin-claude-code/adversarial-review"><img src="https://agentmods.dev/badge/commands/robbedoo/minimax-plugin-claude-code/adversarial-review.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 | $0.00013 | $0.00843 |
| Opus 5 | $0.00006 | $0.00421 |
| Sonnet 5 | $0.00003 | $0.00169 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
adversarial-review 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 4d 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.
This is a copy
94% identical to adversarial-review — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Run an adversarial MiniMax review through the shared plugin runtime. Position it as a challenge review that questions the chosen implementation, design choices, tradeoffs, and assumptions. It is not just a stricter pass over implementation defects.
Raw slash-command arguments:
$ARGUMENTS
Core constraint:
- This command is review-only.
- Do not fix issues, apply patches, or suggest that you are about to make changes.
- Your only job is to run the review and return MiniMax's output verbatim to the user.
- Keep the framing focused on whether the current approach is the right one, what assumptions it depends on, and where the design could fail under real-world conditions.
Execution mode rules:
- If the raw arguments include
--wait, do not ask. Run in the foreground. - If the raw arguments include
--background, do not ask. Run in a Claude background task. - Otherwise, estimate the review size before asking:
- For working-tree review, start with
git status --short --untracked-files=all. - For working-tree review, also inspect both
git diff --shortstat --cachedandgit diff --shortstat. - For base-branch review, use
git diff --shortstat <base>...HEAD. - Treat untracked files or directories as reviewable work for auto or working-tree review even when
git diff --shortstatis empty. - Only conclude there is nothing to review when the relevant scope is actually empty.
- Recommend waiting only when the scoped review is clearly tiny, roughly 1-2 files total and no sign of a broader directory-sized change.
- In every other case, including unclear size, recommend background.
- When in doubt, run the review instead of declaring that there is nothing to review.
- For working-tree review, start with
- Then use
AskUserQuestionexactly once with two options, putting the recommended option first and suffixing its label with(Recommended):Wait for resultsRun in background
Argument handling:
- Preserve the user's arguments exactly.
- Do not strip
--waitor--backgroundyourself. - Do not weaken the adversarial framing or rewrite the user's focus text.
- The companion script parses
--waitand--background, but Claude Code'sBash(..., run_in_background: true)is what actually detaches the run. /minimax:adversarial-reviewuses the same review target selection as/minimax:review.- It supports working-tree review, branch review, and
--base <ref>. - It does not support
--scope stagedor--scope unstaged. - Unlike
/minimax:review, it can still take extra focus text after the flags.
Foreground flow:
- Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/minimax-companion.mjs" adversarial-review "$ARGUMENTS"
- Return the command stdout verbatim, exactly as-is.
- Do not paraphrase, summarize, or add commentary before or after it.
- Do not fix any issues mentioned in the review output.
Background flow:
- Launch the review with
Bashin the background:
Bash({
command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/minimax-companion.mjs" adversarial-review "$ARGUMENTS"`,
description: "MiniMax adversarial review",
run_in_background: true
})
- Do not call
BashOutputor wait for completion in this turn. - After launching the command, tell the user: "MiniMax adversarial review started in the background. Check
/minimax:statusfor progress."
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.
- 4d ago First seen · 67 lines · 13 tokens per session scan A 773b931f6146
adversarial-review is a command published in the GitHub repository robbedoo/minimax-plugin-claude-code (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 843 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to adversarial-review, differing in 18 lines, and is treated as a copy.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
go-review
Go code review for idiomatic patterns.
crear-skill
Crear, probar y mejorar skills de forma iterativa. Usa cuando el usuario dice "crear skill", "crear habilidad", "build skill", "create a skill", "skill development", "desarrollar skill", "nueva habilidad". Usa el workflow: draft → test → review → improve → repeat con evaluación cuantitativa y qualitative review.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
cost-tracker
Track session costs, understand token spend, and get optimization tips.