agentmods.dev

investor_panel

investor_panel is a skill for Claude Code, Codex from agentpit-io/hunter-community. It costs 38 tokens per session (1,054 once invoked), scanned A, original, Apache-2.0.

A simulated panel of 66 investing styles that reviews a stock through nine approaches, including value, growth, trading, and technical analysis. It produces votes, representative comments, and a combined score.

In plain words
What is it for?
Getting a bullish, bearish, or neutral vote distribution, extracting key viewpoints, and producing an overall stock assessment.
Why use it?
It organizes several investing viewpoints in one review instead of presenting only a single analysis style.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 577repo +2 changed 1mo ago A scan SkillSpector: pass 38 tokens original Apache-2.0

Good fit Getting a bullish, bearish, or neutral vote distribution, extracting key viewpoints, and producing an overall stock assessment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentpit-io/hunter-community/investor_panel
View source ↗ agentpit-io/hunter-community hunter-community.agentpit.io
Install

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.

Any agent
npx skills add agentpit-io/hunter-community --skill investor_panel
Clone the repo
git clone --depth 1 https://github.com/agentpit-io/hunter-community

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for investor_panel

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentpit-io/hunter-community/investor_panel/github.svg)](https://agentmods.dev/skills/agentpit-io/hunter-community/investor_panel)
Your own site
<a href="https://agentmods.dev/skills/agentpit-io/hunter-community/investor_panel"><img src="https://agentmods.dev/badge/skills/agentpit-io/hunter-community/investor_panel/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.

agentmods 80×15 button for investor_panel

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentpit-io/hunter-community/investor_panel"><img src="https://agentmods.dev/badge/skills/agentpit-io/hunter-community/investor_panel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,054 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01054
Opus 5.5 $0.00015 $0.00422
Sonnet 5.5 $0.00008 $0.00211
Haiku 4.5 $0.00004 $0.00105

Measured 1mo ago against content hash 3489e4341b23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

investor_panel 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 1mo 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.

skills/investor_panel/SKILL.md · 81 lines

What it actually says

Investor Panel · 大佬评审团（Hunter 适配版）

66 位投资者分成 9 个流派，各自用自己的方法论对同一只股票投票。 这个 SKILL 的价值不在于给出结论，而在于把分歧摆出来 —— 让用户看清同一份数据在不同框架下能读出完全相反的意思。

执行流程

1. 取数

调 uzi_stock_deep_analysis 拿这只股票的真实数据（行情 / K 线 / 财务 / 公告 / 新闻等）。

⚠️ outline 参数只传数据类小节，或者干脆不传。 后端手里只有上面那几段数据，它写不出「投票分布」，也不知道芒格会怎么说； 把角色类小节塞进 outline，它只会写一句「暂无数据」。 66 位大佬的戏份全部在你的正文里完成。

2. 投票

按 references/voting-rules.md 的规则推导 —— 不是拍脑袋编比例：

  • 每个流派有一张打分维度表，逐维对照真实数据打 -2 到 +2 分
  • 分数和 ≥ +3 投牛、-2~+2 投中性、≤ -3 投熊
  • 数据缺失的维度记 0 分；一个流派过半维度缺数据，该流派全部记中性
  • 综合评分 = 50 + (牛票 - 熊票) / 66 × 50

3. 发言

9 个流派的方法论与成员名单：

  • references/group-a-classic-value.md · 经典价值（8 席）
  • references/group-b-quality-growth.md · 质量成长（8 席）
  • references/group-c-disruptive-tech.md · 颠覆式创新（8 席）
  • references/group-d-macro-cycle.md · 宏观与周期（8 席）
  • references/group-e-trend-momentum.md · 趋势与动量（8 席）
  • references/group-f-hot-money.md · 游资与情绪（8 席）
  • references/group-g-quant-systematic.md · 量化与系统化（7 席）
  • references/group-h-contrarian-short.md · 逆向与做空（6 席）
  • references/group-i-tail-risk.md · 尾部风险与对冲（5 席）

每个流派文件末尾都有发言模板：先引真实数字，再下判断。

输出格式

  1. 一句话结论 —— 分歧点在哪
  2. 投票分布 —— 牛 / 中性 / 熊 票数与比例、综合评分与档位
  3. 分流派详述 —— 9 个流派每个都要写到：席位数、态度、打分依据 （引用真实数字）、1-2 位代表人物的第一人称点评
  4. 最大分歧 —— 哪两派结论相反，各自依据是什么
  5. 跟踪清单 —— 什么数据出来能让分歧收敛

第 3 部分是主体。不要只挑两三个流派说完就收尾 —— 用户点这个 SKILL 就是为了看 66 个人怎么吵起来的。

硬约束

  • 所有数字来自工具返回的数据，一个都不许编。没有的就说没有。
  • 人物观点标注是模拟：写「模拟巴菲特的方法论推演」，不要写成 「巴菲特说」。这是按公开方法论做的角色推演，不是本人言论， 也不代表他们的真实持仓或表态。
  • 不给买卖评级、目标价、仓位建议。 综合评分是分歧度指标，不是推荐等级。
  • 全程中文，英文只用于股票代码和 ROE / EPS / PEG 这类缩写。
Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 1mo ago Changed · +52 lines · +1 tokens per session 3489e4341b23
  2. 2mo ago First seen · 29 lines · 37 tokens per session scan A 4c2339734546

Subscribe to this mod's changes

investor_panel is a skill published in the GitHub repository agentpit-io/hunter-community (577 stars, last pushed 23d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,054 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 2026-08-30.

Finance and fintechai-agentsdocker-composefinancial-aimcpopencodeself-hosted
Related

investor_panel compared with skills from other repositories

investor_panel next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
investor_panelagentpit-io/hunter-communitySkill57723d agoApache-2.0A38Claude Code, Codex
stripe-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA56Claude Code
dodo-payments-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA69Claude Code
biltborski/travel-hacking-toolkitSkill895todayMITA44Claude Code
amex-travelborski/travel-hacking-toolkitSkill895todayMITA47Claude Code
chase-travelborski/travel-hacking-toolkitSkill895todayMITA44Claude Code
compare-flightsborski/travel-hacking-toolkitSkill895todayMITA46Claude Code