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/jellydn/my-ai-tools/draft-pull-requestnpx skills add jellydn/my-ai-tools --skill draft-pull-requestgit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/draft-pull-request)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/draft-pull-request"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/draft-pull-request.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 | $0.00014 | $0.00791 |
| Opus 5 | $0.00007 | $0.00396 |
| Sonnet 5 | $0.00003 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
draft-pull-request 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Pull Request
Create a draft pull request using gh CLI with a structured What / Why / How description that communicates the purpose and approach of your changes clearly.
Usage
/draft-pull-request [title]
- If a title is provided via
$ARGUMENTS, use it as the PR title. - Otherwise, derive a concise title from the branch name and commit history.
Process
1. Gather context
# Detect the repository's default branch
BASE_BRANCH=$(gh repo view --json defaultBranchRef -q '.defaultBranchRef.name')
# Check current branch
git branch --show-current
# Review commit history since branching from base
git log "$BASE_BRANCH"..HEAD --oneline
# Review the full diff
git diff "$BASE_BRANCH"..HEAD --stat
git diff "$BASE_BRANCH"..HEAD
2. Compose the PR description
Write a structured description following the What / Why / How template:
## What
[Concise summary of the changes made. What was added, modified, or removed?]
## Why
[The motivation behind this change. What problem does it solve? What opportunity does it capture?]
## How
[Brief explanation of the approach taken. Key technical decisions, patterns used, or trade-offs made.]
## Checklist
- [ ] Tests added or updated
- [ ] Documentation updated
- [ ] No breaking changes (or breaking changes documented above)
3. Create the draft PR with gh CLI
gh pr create \
--draft \
--title "<PR title>" \
--body "<structured what/why/how description>"
Use --draft to signal the PR is not yet ready for review.
4. Output the PR URL
After creation, display the PR URL:
gh pr view --json url -q '.url'
Guidelines
- Title: Short, imperative, max 72 characters (e.g.,
feat: add user authentication flow) - What: Describe the surface area of changes — files, components, APIs affected
- Why: Explain the business or technical reason — avoid vague phrases like "to improve things"
- How: Highlight non-obvious implementation details or trade-offs, not every line changed
- Keep the description concise but complete — reviewers should understand the PR without reading all the code
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.
- 5d ago First seen · 127 lines · 14 tokens per session scan A 3d8f27720ff1
draft-pull-request is a skill published in the GitHub repository jellydn/my-ai-tools (119 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 791 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
geo-explorer
Only invoke when explicitly requested via "地缘探索"、"@geo-explorer" or "geo explorer". Do NOT auto-trigger.
insight-miner
Only invoke when explicitly requested via "洞见"、"@insight-miner" or "insight". Do NOT auto-trigger.
strategic-product-advisor
Only invoke when explicitly requested via "产品方向"、"怎么赚钱"、"竞品分析"、"@strategic-product-advisor". Do NOT auto-trigger.
ask-first
Use when user input is ambiguous, analogy-driven, meta-level, weakly delegated, missing intent/context, or emotional without clear execution constraints; do not use for operationally clear tasks.
history-autopsy
Only invoke when explicitly requested via "历史速览"、"@history-autopsy" or "history autopsy". Do NOT auto-trigger.
notes-to-blog
Only invoke when explicitly requested via "@notes-to-blog"、"博客知识提取"、"笔记整理成博客". Do NOT auto-trigger. Manual-only skill for turning notes, debugging records, design summaries, code snippets, or rough drafts into a Chinese technical blog.