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/justinstimatze/gemot/deliberategit clone --depth 1 https://github.com/justinstimatze/gemotWrote 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/justinstimatze/gemot/deliberate)<a href="https://agentmods.dev/commands/justinstimatze/gemot/deliberate"><img src="https://agentmods.dev/badge/commands/justinstimatze/gemot/deliberate.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 | $0.00000 | $0.00229 |
| Opus 5 | $0.00000 | $0.00114 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
deliberate 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.
What it actually says
Start a gemot deliberation about the current task or dispute.
Use the gemot MCP tools to:
- Create a deliberation about the topic the user specifies (or infer from context)
- Submit your own position based on your analysis
- If other agents are present, wait for their positions, then vote
- Call analyze when all positions are in
- Use get_context to understand the cruxes
- If a compromise is needed, call propose_compromise
- Commit to the outcome
Tips:
- For code disputes: use type "reasoning", submit positions about the technical tradeoff
- For scheduling: use type "negotiation", submit availability windows (not calendar details)
- For policy: use type "policy", submit positions about what the rule should be
- Set conviction (0.0-1.0) to signal how strongly you feel
- Set reservation to declare what outcome is unacceptable
- Use on_behalf_of to clarify who you represent
Example: "deliberate whether we should use a monorepo or polyrepo for the new service"
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 · 21 lines · 0 tokens per session scan A 9cf35563d833
deliberate is a command published in the GitHub repository justinstimatze/gemot (3 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 229 tokens. 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
ai-branch
AI 解读分支（L0 回退） — 演示无 keywordAliases 时由 AI Agent 解读自然语言触发分支.
buzz-crawling
外部舆情策略更新全流程 — /buzz-crawling run 启动外部舆情策略更新全流程.
cct-sop-alert
营销智评分流（告警测试） — 测试钉钉告警通知的分流工作流，botId带test前缀会触发失败.
kf-direct-support
TeamClaw 直接技能支持 — 直接调用 teamclaw-support 技能处理用户问题，跳过多阶段编排.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
ap
The user invoked the /approval facade command from the approval-node-pipeline pack.