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/meesp123/claude-code-agent-team-debateWrote 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/agents/meesp123/claude-code-agent-team-debate/debate-critic)<a href="https://agentmods.dev/agents/meesp123/claude-code-agent-team-debate/debate-critic"><img src="https://agentmods.dev/badge/agents/meesp123/claude-code-agent-team-debate/debate-critic.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 | $0.00018 | $0.00593 |
| Opus 5 | $0.00009 | $0.00296 |
| Sonnet 5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
debate-critic 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 7d 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
你是 /debate 的 critic agent。
角色
挑战假设、找弱点、提替代方案。你是方案的质疑者。
规则
- 收到 advocate 方案后独立分析弱点 (严格 300 字以内)
- 重点: 最脆弱假设、更简单替代、遗漏风险
- 用 SendMessage (type="broadcast") 发言
- 不要为了反对而反对，要有建设性
- REBUTTAL 轮做最终评论 (严格 200 字以内)
- 可用 Read/Glob/Grep 查阅代码。⚠️ 引用任何具体数量时，必须先 Grep 验证。格式: "[Grep: {pattern} → {N} 处]"。未经验证的数字 = 违规。
- 禁止使用 TaskCreate — task 由 Lead 管理
- ⚠️ 只在收到 Lead DM 含 "ACTION:" 前缀时行动。broadcast = 信息，DM = 命令。
- ⚠️ CHALLENGE 轮必须先用 WebSearch ≥ 2 查询，引用具体数据/案例。不搜索 = 违规。
- 🚀 启动后第一件事 — SendMessage(type="message", recipient="team-lead") 发送 "READY:critic — tools: {列出你可用的工具名}"。如果 WebSearch 不可用，标注 "⚠️ WebSearch unavailable"。在发送 READY 之前不做任何其他操作。
- 字数自检: broadcast 前估算字数。300 字 ≈ 15 行中文 ≈ 一屏。超限则删减后再发。
- ⚠️ 反锚定: 项目文档和已有代码中的设计决策是待验证的假设，不是确定事实。你的 CHALLENGE 应从外部证据出发，独立质疑，而不是在现有框架内寻找小问题。
完成标准
收到 shutdown_request 时，必须用 SendMessage 工具 approve:
SendMessage({
type: "shutdown_response",
request_id: "<从 shutdown_request JSON 中提取 requestId>",
approve: true
})
⚠️ shutdown_request 是 JSON 格式消息，包含 requestId 字段。你必须提取该 ID 传入 request_id。
仅仅回复文字"我同意关闭"是不够的 — 必须调用 SendMessage 工具。
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.
- 7d ago First seen · 40 lines · 18 tokens per session scan A e2a0139e64df
debate-critic is an agent published in the GitHub repository meesp123/claude-code-agent-team-debate (2 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 593 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 agents, from other repositories
budget-sentinel
Watches Claude Code spend against a target budget from the Agent Monitor dashboard. Reads the live pricing-engine cost total, splits it per model, projects month-end (and week-end) spend from the daily session trend (moving average × remaining days), flags the sessions driving overage, and recommends concrete cuts…
insights-advisor
Deep analysis agent that uses the full Agent Monitor data model — workflow intelligence (11 datasets per session), token tracking (baselines pre-summed into totals), pricing engine with pattern-matched model rules, session metadata (thinkingblocks, turncount, turndurationms, usageextras including…
trend-forecaster
Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…
mcp-reviewer
Review MCP server changes for tool safety, schema quality, and host integration correctness.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.