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/wolfpackofone/q-agent/push-gitnpx skills add WolfpackOfOne/Q-agent --skill push-gitgit clone --depth 1 https://github.com/WolfpackOfOne/Q-agentWhat 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 | $0.00046 | $0.00770 |
| Opus 5 | $0.00023 | $0.00385 |
| Sonnet 5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
push-git 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Push Git Skill
Commit all pending changes and push to Git/GitHub.
Usage
/push-git [commit message]
Examples:
/push-git— auto-generates commit message from changes/push-git "Add yfinance pipeline"— uses provided message
Workflow
1. Inspect Current State
git status --short
git remote -v
git branch --show-current
git log --oneline -5
Review what will be committed. Summarize the changes for the user.
2. Check for Marimo Notebooks
Scan all staged and modified .py files for marimo notebooks:
# For each changed .py file, check if it's a marimo notebook
head -20 "<file>" | grep -q 'marimo.App'
If any marimo notebooks are found among the changed files, ask the user:
Found marimo notebooks in changed files:
<path/to/notebook.py>Would you like to render them to
.ipynbfor GitHub viewing? (This runsmarimo exportwith outputs.)
If the user says yes, export each notebook:
infrastructure/marimo/venv/bin/marimo export ipynb "<notebook.py>" -o "<notebook.ipynb>" --include-outputs
Then stage the generated .ipynb files alongside the other changes.
If the user says no, skip rendering and proceed with the commit.
3. Stage Changes
Stage all relevant files. Use specific file paths rather than git add -A when possible.
Do NOT stage:
.env, credentials, secretsconfig.jsonfilesbacktests/,__pycache__/,.ipynb_checkpoints/- Files in
.gitignore
If there are many files, group them logically and stage by directory or pattern.
4. Commit
If a commit message was provided as an argument, use it. Otherwise, generate a concise commit message based on the changes.
For large changesets, consider asking the user whether to split into multiple commits or do one big commit.
5. Push to GitHub
git push origin <current-branch>
Do not force-push unless the user explicitly asks.
6. Report Results
Commit: <short hash> <message>
Push: origin/<branch> — success / failed
Notebooks rendered: <list> / none
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 · 115 lines · 46 tokens per session scan A 736ad4ab6eeb
push-git is a skill published in the GitHub repository WolfpackOfOne/Q-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 770 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 2026-08-31.
Other skills, from other repositories
correlation-analysis
Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation.
ashare-pre-st-filter
A 股 ST/ST 风险预测框架 — 基于最新中报/三季报或业绩预告/快报，预测下一财年是否会因营收、利润、净资产、分红不达标而被风险警示，并将新浪监管处罚记录作为独立证据面纳入风险等级。仅适用于 A 股，不预测财务造假。.
credit-analysis
固收与信用分析：信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。.
geopolitical-risk
Geopolitical risk analysis: quantify crisis signals, identify precursors, and build event-driven strategies for war, sanctions, and supply disruption scenarios.
vibe-trading
Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 90 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract →…
etf-analysis
ETF分析：产品筛选、费率对比、跟踪误差、流动性评估、策略应用与中国市场ETF量化配置框架。.