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/wbh604/uzi-skill/model-updategit clone --depth 1 https://github.com/wbh604/UZI-SkillWrote 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/wbh604/uzi-skill/model-update)<a href="https://agentmods.dev/commands/wbh604/uzi-skill/model-update"><img src="https://agentmods.dev/badge/commands/wbh604/uzi-skill/model-update.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 | $0.00050 | $0.01182 |
| Opus 5 | $0.00025 | $0.00591 |
| Sonnet 5 | $0.00010 | $0.00236 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
model-update 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/model-update <股票代码> [新假设]
财报发布 / 公司更新指引 / 修正假设后，用新数据增量更新已有财务模型， 而不是从头重算。输出关键假设 before→after 的 delta 表，并把改动传导到 DCF 内在价值、Comps 隐含价、投资逻辑各支柱，给出更新后的 verdict。
A 股 / 港股 / 美股通用；估值参数沿用 UZI（A 股 rf 2.5% / ERP 6% / 税 25%）。
触发词：「更新模型 / 改假设重算 / 新指引 / 财报更新数字 / 修正估计 / revise estimates」。
输入
| 来源 | 说明 |
|---|---|
| 新财报实绩 | 营收 / 毛利率 / 净利率 / capex 的最新实际值 |
| 新管理层指引 | 营收增速、利润率、资本开支前瞻 |
| 修正假设 | 分析师调高/调低 stage1 增速、终值 g、beta、目标 PE/目标价 |
支持的假设键（updates dict）：
rev_growth · gross_margin · net_margin · capex_pct ·
stage1_growth · terminal_g · beta · target_pe · target_price
（百分比传数字如 26.0 表示 26%；倍数 beta=1.5；价格 target_price=24.0）
工作流
- 采集/复用最新 features（
extract_features）。 - 若要算估值影响，先有 DCF / Comps 结果（复用
/dcf、/comps的输出）。 - 调用：
from lib.tier1.model_update import build_model_update from lib.fin_models import compute_dcf, build_comps_table dcf = compute_dcf(features) # 可选 comps = build_comps_table(target, peers) # 可选 result = build_model_update( features, raw, updates={"rev_growth": 26.0, "net_margin": 16.0, "capex_pct": 7.0}, dcf_result=dcf, comps_result=comps, )updates=None→ 演示模式：从 features 推断「最新 vs 上期」自动出 delta。- 不传
dcf_result/comps_result→ 对应影响段标记「未提供」，函数照常返回结构。
输出
- ① 假设 delta 表：每条假设 before → after（↑/↓/→）+ 影响通道。
- ② DCF 内在价值影响：每股内在价值 before→after、delta%、WACC 变化、安全边际变化。
- ③ Comps 隐含价影响：中位 PE × EPS 隐含价 before→after、delta%。
- ④ 投资逻辑影响：每条改动映射到对应支柱（成长性/盈利质量/现金流/估值锚），💪 强化 / ⚠️ 削弱。
- ⑤ 更新后 verdict：综合分 → 上修 / 维持 / 下修 + 建议动作。
展示示例
📊 模型更新 · 测试科技 (000001.SZ) · 显式模式
① 关键假设 delta
营收增速 15.0% → 26.0% (↑) [→DCF]
净利率 14.0% → 16.0% (↑) [→DCF/Comps]
Capex/营收 6.7% → 7.0% (↑) [→DCF]
② DCF 内在价值 ¥20.00 → ¥23.05 (+15.3%) ↑
WACC 8.50% → 8.50% · 安全边际 +8.1% → +24.6%
③ Comps 隐含价 ¥22.00 → ¥25.15 (+14.3%) ↑（净利率放大 EPS）
④ 投资逻辑
成长性（营收增速） 15.0%→26.0% (↑) 💪 强化
盈利质量（净利率） 14.0%→16.0% (↑) 💪 强化
现金流/资本纪律 6.7%→7.0% (↑) ⚠️ 削弱
⑤ 更新后评级：🟢 上修 (Upgrade)（综合分 +31.5）→ 上调目标价 / 加仓候选
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 · 85 lines · 50 tokens per session scan A 7dcee5c465de
model-update is a command published in the GitHub repository wbh604/UZI-Skill (6,737 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 1,182 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.
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.
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
scan
Scan AWS account for cost optimization.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…