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/quantmind/quantflow/update-doc-indexesnpx skills add quantmind/quantflow --skill update-doc-indexesgit clone --depth 1 https://github.com/quantmind/quantflowWhat 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 | $0.00017 | $0.00500 |
| Opus 5 | $0.00009 | $0.00250 |
| Sonnet 5 | $0.00003 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
update-doc-indexes 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update API index pages
Update every top level API index page so it references all the relevant documented pages and classes of its section.
Scope
The top level index pages are docs/api/<section>/index.md, one per section
listed under API Reference in the nav of mkdocs.yml
(currently: data, dists, options, rates, sp, ta, utils).
If arguments name one or more sections, restrict the update to those.
Procedure
For each section:
- Read the section entry in the
navofmkdocs.ymland list its pages. - For each page, collect what it documents: the H1 title and the
mkdocstrings entries (
::: fully.qualified.pathlines). - Read the section
index.mdand identify pages or classes that are not mentioned anywhere on it. - Add the missing entries to the index page:
- Follow the existing layout of that index page. If it uses tables with
| Class | Description |columns, extend or add tables in the same format. Only introduce a new H2 section when the missing entries do not fit an existing one, and match the style of the sections already there. - Ask the developer where to place a new section if the page layout does not make the placement obvious.
- Link classes and functions with mkdocstrings cross-references
(
[ClassName][fully.qualified.path]) and pages with relative markdown links (e.g.[SVI Volatility Smile](svi.md)). - Write a one line description for each entry, based on the docstring or
the page introduction. Link concepts to
docs/glossary.mdinstead of redefining them.
- Follow the existing layout of that index page. If it uses tables with
- Do not remove or rewrite existing content: this skill only adds what is missing and fixes references that are broken.
Conventions
- Follow the documentation rules in
.github/copilot-instructions.md(no dashes as punctuation, short paragraphs, relative links). - Do not edit generated files (
docs/bibliography.md,readme.md). - After the update, list for the developer which entries were added to which index page.
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.
- 2d ago First seen · 50 lines · 17 tokens per session scan A b4e6ad1358ba
update-doc-indexes is a skill published in the GitHub repository quantmind/quantflow (52 stars, last pushed 16d ago), licensed BSD-3-Clause. It adds 17 tokens to every session and 500 once invoked, about $0.0001 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 skills, from other repositories
html-ppt-zhangzara-bold-poster
OpenDesign's Series A growth story: the traction curve, the expansion motion, and why it's venture-scale. Built as a decision-grade fundraising pitch deck for Series A partners.
html-ppt-zhangzara-long-table
OpenDesign's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
invoice
标准发票: 寄件/收件 + 明细 + 税 + 总额 + 付款指引.
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.