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 skills add metago-ai/metagolifeform --skill metago-deep-reasoninggit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/skills/metago-ai/metagolifeform/metago-deep-reasoning)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-deep-reasoning"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-deep-reasoning/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/skills/metago-ai/metagolifeform/metago-deep-reasoning"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-deep-reasoning.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 | $0.00032 | $0.01154 |
| Opus 5 | $0.00016 | $0.00577 |
| Sonnet 5 | $0.00006 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
metago-deep-reasoning 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 12d 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
FIPO深度推理
触发条件
当用户明确提到"深度推理"、"FIPO"、"多维度分析"、"深度思考"、"推理链"、"复杂决策分析"等关键词，或面对需要进行多路径推理、交叉验证假设、生成最优解与备选方案的复杂问题域时，自动触发本技能。适用于仅靠直觉或单线逻辑无法给出可靠结论的情境。
适用场景
- 复杂决策分析：在多方利益、多重约束条件下进行决策权衡
- 技术方案评估：对多个候选方案进行多维度对比与验证
- 根因分析：对生产故障、性能瓶颈、组织问题等进行深层归因
- 战略推演：对未来不确定场景进行多路径预判
- 学术研究：对开放性命题进行严谨论证
执行步骤
1. F阶段（Focusing）——聚焦核心问题
- 识别问题本质，剥离表象干扰
- 明确问题边界：时间维度、空间维度、参与主体
- 列出约束条件：硬约束（必须满足）与软约束（可妥协）
- 输出《问题定义书》：含问题陈述、边界、约束清单
2. I阶段（Inferring）——多路径推理
- 基于问题定义生成3-5条独立推理链
- 每条推理链标注前提假设、推理路径、中间结论
- 推理链之间需保持独立性，避免同源偏差
- 记录推理路径的分歧点和汇合点
3. P阶段（Proving）——验证推理链
- 对每条推理链的关键假设进行交叉验证
- 寻找反例和证伪证据，避免确认偏误
- 标注假设的可信度（高/中/低）及验证来源
- 剔除无法验证或被证伪的推理链
4. O阶段（Optimizing）——优化推理结论
- 综合存活的推理链，提炼最优结论
- 生成备选方案集（至少2个），标注差异点
- 对每个方案进行风险评估与可控性分析
- 给出推荐结论与决策路径
5. 推理深度评估
对F、I、P、O四个阶段分别评分（1-5分）：
- 1分：浅层，仅触及表象
- 3分：中层，完成基本分析
- 5分：深层，触及本质并完成交叉验证
- 计算综合推理深度 D = Σ(阶段得分) / 4
6. 输出推理报告
输出包含：问题定义书、推理链全图、验证证据表、最优解+备选方案、推理深度评分、置信度评估（0-100%）、关键风险点。
输出格式
【FIPO深度推理报告】
■ 问题定义：[边界|约束]
■ 推理链：
链1：[前提]→[路径]→[结论]（验证状态：✓/✗）
链2：...
链3：...
■ 最优结论：...
■ 备选方案：方案A | 方案B
■ 推理深度：F=4 I=3 P=4 O=5 综合=4.0
■ 置信度：85%
■ 关键风险：...
核心理论
本技能基于元构生命体理论体系中的 FIPO深度推理算法，来源于《卷2第六章》。FIPO为四阶段递进式深度推理框架，强调从聚焦（F）到推理（I）到验证（P）再到优化（O）的闭环过程，区别于线性单链推理，要求多路径并行与交叉验证。
关联文档
- 卷2第六章：FIPO深度推理算法的完整定义与数学表达
- 卷3第二章：四阶飞轮——FIPO如何嵌入飞轮第二阶"推理"环节
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.
- 12d ago First seen · 85 lines · 32 tokens per session scan A b4b09dc6ea09
metago-deep-reasoning is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 1,154 once invoked, about $0.0002 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 skills, from other repositories
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
loop-orchestration
Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.
slack-notify
Plan a digest-bound Slack notification, then deliver the exact approved channel post through any compatible Slack binding with provider readback.