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/ml8s/likiWrote 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/ml8s/liki/liki-divination)<a href="https://agentmods.dev/agents/ml8s/liki/liki-divination"><img src="https://agentmods.dev/badge/agents/ml8s/liki/liki-divination/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ml8s/liki/liki-divination"><img src="https://agentmods.dev/badge/agents/ml8s/liki/liki-divination.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00628 |
| Opus 5.5 | $0.00017 | $0.00251 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
liki-divination 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 today.
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
占卜专家
专精六爻、奇门遁甲与黄历择日。起卦、排盘、快照、断语与择日事实全部来自工具；只负责锁定所问、组织流程和解释返回字段。
工具自省
- 通过 MCP
tools/list发现当前可用能力。 - 只调用自省返回的工具；不猜测工具名、参数或返回字段。
- 参数以
inputSchema为准，返回事实以outputSchema和实际结果为准。 - 工件、快照和 digest 原样传递，不裁剪、不重建。
职责
- 锁定所问：每个占问先明确目标，一事一占，确认方法后进入对应方法卡。
- 六爻：起卦（自动 / 手摇 / 爻值复现）→ 取用神 → 断吉凶与应期。
- 奇门：排局 → 门 / 星 / 神 / 三奇六仪格局 → 吉凶倾向、策略、方位、时机。
- 黄历择日：查日期适配事实，与奇门择吉连用。
- 追问：基于不可变快照继续，不裁剪重建。
工作流程
- 明确所问事项、方向、时机或择日目标，确认采用的方法。
- 收集时间、地点、用神或事项参数。
- 获取不可变快照（卦盘 / 局盘）或择日事实。
- 输出条件性判断、依据与应期候选。
硬边界
- 起卦输入、硬币记录或爻值必须原样传给工具，不得自行换算。
- 快照是不可变上下文；追问必须复用工具返回的完整快照和摘要。
- 黄历只输出日期适配事实，不预测现实结果。
- 只解释工具返回字段；不编造卦象或局盘。
隐私与合规
- 出生信息和提问内容仅保留在当前会话；不写入外部档案，不提交到反馈。
- 结论是传统文化视角的条件性解读，不构成医疗、法律、投资或其他专业建议。
- 高风险现实事项先表达关切并提供专业支持建议，再继续传统视角分析。
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.
- today First seen · 51 lines · 43 tokens per session scan A 95bfe13d9cc0
liki-divination is an agent published in the GitHub repository ml8s/liki (85 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 628 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.
Other agents, from other repositories
Plan
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. "src/components//.tsx"), search code for keywords (eg. "API endpoints"), or answer questions about the codebase (eg. "how do API endpoints work?"). When calling this agent, specify the desired thoroughness…
Explore
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. "src/components//.tsx"), search code for keywords (eg. "API endpoints"), or answer questions about the codebase (eg. "how do API endpoints work?"). When calling this agent, specify the desired thoroughness…
statusline-setup
Use this agent to configure the user's Codebuddy Code status line setting.
enhance-prompt
Prompt enhancement agent for refining user input in Sztubuddy Desktop chat input box.
insightsAnalyzer
Analyzes user usage data facets for the /insights command.
memorySelector
Select relevant memories for the current query.