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 skills/travisun/opptrix/thesis-trackernpx skills add Travisun/Opptrix --skill thesis-trackergit clone --depth 1 https://github.com/Travisun/OpptrixWrote 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/travisun/opptrix/thesis-tracker)<a href="https://agentmods.dev/skills/travisun/opptrix/thesis-tracker"><img src="https://agentmods.dev/badge/skills/travisun/opptrix/thesis-tracker.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 | $0.00070 | $0.00944 |
| Opus 5 | $0.00035 | $0.00472 |
| Sonnet 5 | $0.00014 | $0.00189 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
thesis-tracker 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 yesterday.
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
论点跟踪板（Thesis Tracker）
何时使用
用户要维护 多标的/多论点的状态跟踪板（支柱状态、证伪进度、下次检查点），以 workspace 为单一事实源（SSOT）。边界：vs @skill:watchlist-digest——后者是关注池行情/资讯摘要；本技能跟 论点生命周期。单次修订用 @skill:thesis-update。
分析架构（投研方法）
- 问题/假设：当前跟踪中的论点各自处于何状态？哪些接近证伪/验证？
- 证据清单：workspace 跟踪表、关注列表（可选范围）、近期资讯
- 多维交叉验证：看板条目 vs 最新资讯；避免把价格涨跌直接等同论点验证
- 结论与不确定：状态标签为工作分类；变更须引用证据
- 风险与缺口：workspace 空、关注列表与看板不一致
- 事实 | 假设 | 推断 分栏强制
数据维度
| 维度 | 取数方向 | 缺失时 |
|---|---|---|
| 跟踪 SSOT | workspace_read |
初始化模板并 ask_user 录入首批论点 |
| 范围辅助 | get_watchlist |
仅跟踪 workspace 已有条目 |
| 资讯刷新 | get_instrument_news |
状态章仅基于旧记录并标注陈旧 |
| 写回 | workspace_write |
至少网页交付；提醒 SSOT 未更新 |
| 交付 | list_web_vendor → create_web |
用户只要口头要点时可跳过 |
步骤
- 读取 workspace 跟踪板；无则创建最小 schema（标的、论点一句、状态、证伪条件、下次检查）。
- 按条目刷新相关资讯（可限关注列表交集）。
- 更新状态：验证中/削弱/证伪/搁置——每条附证据与时间。
workspace_write写回 SSOT（默认应做）。- 交付网页（默认）：
list_web_vendor→create_web看板页；已有则read_web/update_web。
网页报告建议目录
- 跟踪板元信息与时效
- 看板总表（标的 / 状态 / 下次检查）
- 条目详情：论点、支柱、证伪进度
- 本期变更日志
- 事实 | 假设 | 推断分栏
- 与关注列表差异说明（若有）
- 风险与缺口
- 免责声明（无买卖建议）
禁止
- 把关注列表涨跌摘要冒充论点跟踪（应转 watchlist-digest）
- 荐股；无证据改状态
- 禁止无交付就结束（默认须有 web 产物，除非用户明确只要口头要点）
- 跳过 workspace SSOT 却声称「已跟踪」
- assumption / not-feasible 须诚实降级
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.
- yesterday First seen · 68 lines · 70 tokens per session scan A 7d19f6f35dfb
thesis-tracker is a skill published in the GitHub repository Travisun/Opptrix (229 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 944 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 2026-09-03.
Other skills, from other repositories
national-team-position
估计中国 A 股"国家队"(中央汇金)的宽基 ETF 持仓变动趋势——追踪上交所沪深300/上证50/中证500/中证1000/中证A500/科创50 的 ETF 份额变化,叠加各自指数走势,生成六合一总图与各指数单图。Estimates China's "national team" (Central Huijin) broad-base ETF positioning by tracking Shanghai Stock Exchange ETF share changes. Use when the user asks about 国家队持仓 / 国家队仓位 / 中央汇金持仓 / 国家队加仓 / 国家队减仓 /…
integration-roadmap
并购整合路线图 — 制定并购后整合计划，明确整合目标、时间表、 关键任务和责任分工，确保整合顺利推进。 适用情形：并购交易完成后 [X] 天内，或用户要求"制定整合路线图"时执行。 核心：整合范围确认 + 整合计划制定 + 协同效应追踪 + 风险管理。.
close-checklist-executor
月结清单执行 — 对照公司月结清单，逐项检查每项前置任务的完成状态。 适用情形：月末结账开始前，作为第一个执行的 Skill， 确认所有前置条件已满足，未满足项给出明确的补做指引。 核心：清单式检查 + 节点状态追踪 + 未完成项的补做路径。.
project-new
新建项目 — 创建项目目录 + project.md 模板，引导填写项目信息。 适用情形：开始一个新的财务周期项目（年度审计启动、Q2 预算审查立项、税务申报周期开启）。 触发词：新建项目、创建项目、立项、新财年审计、Q2 预算立项、税务申报周期。 核心：项目类型选择 → 代码生成 → project.md 模板填充 → 关联场景激活。.
payroll-master
薪资核算管理主流程 — 整合薪资计算 + 社保审核 + 个税审核的综合薪资管理。 适用情形：月度薪资管理报告时执行，整合 payroll-calculation、 social-insurance-review 和 tax-withholding-review，输出完整的薪资核算报告。 核心：薪资准确 → 社保合规 → 个税合规 → 按时发放。.
m-and-a-master
M&A 并购主流程 — 整合尽调支持、估值分析、交易结构建议与整合追踪。 适用情形：M&A 项目全周期（意向/尽调/谈判/交割/整合）执行时启动， 整合 financial-due-diligence、dcf-modeling、comparable-analysis、valuation-integration 和 integration-roadmap，输出完整的并购决策与执行包。 核心：尽调风险识别 → 估值锚定 → 交易架构 → 整合落地。.