What is select-final-version?

A governance tool for choosing the final version of an open-xquant research strategy after candidate versions have been audited and compared. It applies a selection policy confirmed by the user.

Use it to select, confirm, promote, or mark a final strategy version in an open-xquant workspace. It is for research-version governance, not investment advice.

It prevents a final choice from being made from incomplete, unaudited, or poorly compared research results. It also keeps the decision and its supporting records organised.

select-final-version — Skill for Claude Code and Codex by xingwudao

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 xingwudao/open-xquant --skill select-final-version

Clone the repo

git clone --depth 1 https://github.com/xingwudao/open-xquant

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xingwudao/open-xquant/select-final-version.svg)](https://agentmods.dev/skills/xingwudao/open-xquant/select-final-version)

Your own site

<a href="https://agentmods.dev/skills/xingwudao/open-xquant/select-final-version"><img src="https://agentmods.dev/badge/skills/xingwudao/open-xquant/select-final-version.svg" alt="Measured on agentmods" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 16,639 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.16639
Opus 5	$0.00017	$0.08320
Sonnet 5	$0.00007	$0.03328
Haiku 4.5	$0.00003	$0.01664

Measured 8d ago against content hash 91160f86be40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

select-final-version 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 8d 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.

agent/skills/select-final-version/SKILL.md · 1,494 lines

How it starts

The opening of the file, as written. The whole thing — 1,494 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Final Version Selector

Round 26: current decision schema 5 includes report_revision and selection_request_id; schema-4 pointers are historical and rejected. Candidate, policy, comparison, and lineage schema 3.

This skill performs final version governance. It chooses a final research candidate only from eligible audited candidates and only after the user confirms the selection policy. It is not investment advice.

Workspace Path Resolution

Read .open-xquant/workspace.yaml before reading or writing final-governance artifacts. Resolve each key independently from paths: use paths.versions_dir, paths.experiment_registry, paths.comparisons_dir, paths.governance_dir, paths.final_dir, and paths.conversations_dir. Use versions, experiments.jsonl, comparisons, governance, final, or conversations, respectively, only when that key is absent; never derive one key from another configured key. Each configured value must be a safe workspace-relative path. Reject absolute paths, traversal outside the workspace, and symlink escapes whose resolved target leaves the workspace.

Call the resolved paths <version_root>, <experiment_registry>, <comparisons_dir>, <governance_dir>, <final_dir>, and <conversations_dir> below.

Phase Path Containment Preflight

Before any phase artifact read, write, directory creation, command, or handoff, run this preflight completely and block on any failure:

Resolve <version_root> canonically and require it to stay inside the workspace. Read current.json for active-state context. This contract explicitly owns cross-version inspection, so for each candidate set expected_version_id from the referenced version id candidate.version_id; do not substitute current.json.active_version.
Set the intended version directory to <version_root>/<expected_version_id>/ and resolve it canonically. Require the intended version directory to remain inside the canonical version root and workspace. Read version_manifest.json only from that exact directory and the manifest version_id must equal expected_version_id.
Before using phase_paths.09_backtests or phase_paths.10_reports, require a non-empty workspace-relative string. Reject an absolute path and any .. path segment. Resolve each path canonically, including symlinks, and require it to be the intended version directory or a descendant of it. A symlink escape outside the intended version directory is invalid.
On any identity or path failure, block before reads, writes, directory creation, commands, or handoffs. Do not normalize an unsafe path into acceptance and do not fall back to default phase paths.

Read the full file on GitHub · 1,494 lines

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.

8d ago First seen · 1,494 lines · 35 tokens per session scan A 91160f86be40

Subscribe to this mod's changes

select-final-version is a skill published in the GitHub repository xingwudao/open-xquant (126 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 16,639 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 2026-08-30.

Finance and fintech

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

tradermonty/claude-trading-skills · 28 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

select-final-version