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/joshukraine/dotfiles/create-prnpx skills add joshukraine/dotfiles --skill create-prgit clone --depth 1 https://github.com/joshukraine/dotfilesWrote 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/joshukraine/dotfiles/create-pr)<a href="https://agentmods.dev/skills/joshukraine/dotfiles/create-pr"><img src="https://agentmods.dev/badge/skills/joshukraine/dotfiles/create-pr.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 | $0.00025 | $0.01227 |
| Opus 5 | $0.00013 | $0.00613 |
| Sonnet 5 | $0.00005 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
create-pr 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Pull Request
Create a pull request from the current branch with proper formatting and issue linking.
Command Options
All flags are optional. By default, the issue number is inferred from the branch name and the PR is created as ready-to-review.
--issue N: Override automatic issue linking with a specific issue number (or comma-separated list:--issue 123,175)--skip-issue-link: Skip issue linking entirely--draft: Create PR as draft
Your task
-
Verify prerequisites:
- Confirm current branch is not
main/master - Check that branch has commits ahead of base branch
- Ensure branch is pushed to remote (push if needed)
- Confirm current branch is not
-
Generate PR title:
- Use branch name as fallback
- If single commit ahead: use commit message as title
- If multiple commits: create descriptive title based on branch name and commit themes
- Follow Conventional Commits format from global CLAUDE.md
-
Analyze commits for description:
- Get commit history:
git log origin/<base-branch>..HEAD --oneline(use the base branch identified in step 1) - Group commits by type (feat, fix, docs, etc.)
- Identify patterns and overall theme
- Get commit history:
-
Create comprehensive description:
- Summary section: 2-3 bullet points describing what this PR does
- Changes section: Categorized list of changes from commits
- Testing section: How the changes should be tested
- Notes section: Any implementation details or decisions
-
Update ROADMAP:
- Check if the work corresponds to a checkbox item in
docs/prd/ROADMAP.md - If a matching item exists, mark it complete (
[x]) and commit the change to the branch before creating the PR - If no matching item exists, skip this step
- Check if the work corresponds to a checkbox item in
-
Identify and link related issues (discover → classify → confirm; don't rely on recall):
- If
--skip-issue-link: skip this step entirely. - Determine the primary issue(s) P:
--issue N(accepts a comma-separated list, e.g.--issue 123,175) → use directly as Close targets; skip discovery.- Otherwise extract from the branch name (
fix/gh-123-...→ P=123). If none can be determined, warn and ask whether to proceed with no linking.
- Discover candidates mechanically (do not depend on having read the issue earlier in the session):
- Fetch the primary issue's body and comments:
gh issue view P --json number,title,body,comments - Extract every
#<number>reference from that output. - For each referenced issue M, get its state:
gh issue view M --json number,title,state— drop anything already closed or that is a PR.
- Fetch the primary issue's body and comments:
- Classify each open candidate by the language around the mention:
closes/fixes/resolves #M, or M is an unchecked task-list item this PR completes → Close (Closes #M)part of/blocked by/relates to/see/parent #M→ Reference (Refs #M, no closing keyword)- ambiguous → default to Reference and flag it
- Confirm before creating the PR:
- Only the primary issue P, no other open candidates → proceed silently with
Closes #P. - More than one candidate, or any ambiguous one → print a short table (issue · title · proposed Close/Ref) and ask for a one-line confirm/override first.
- Only the primary issue P, no other open candidates → proceed silently with
- Format: one keyword per line so GitHub parses them all —
Closes #Nper close target,Refs #Nper reference.
- If
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.
- 4d ago First seen · 111 lines · 25 tokens per session scan A 132307c3e281
create-pr is a skill published in the GitHub repository joshukraine/dotfiles (422 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 1,227 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
factory-mcp
Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket / description, and pull a task down to test or iterate locally and hand it back.
github-issue-create
Create a GitHub issue with an auto-generated description. Use when the user asks to open an issue for a bug, feature request, or task.
there-there
Manage There There helpdesk tickets, contacts, and channels using the there-there CLI. Use when the user wants to list, view, reply to, search, or manage tickets; assign team members; manage tags; view contacts; or interact with there-there.app from the command line.
review-pr
Review an existing GitHub PR — one verified single-pass read of the diff, inline P1–P3 findings, fixes for the P1/P2s pushed to the PR branch, scoped verification, resolved threads, a summary. Escalates to a two-reader second opinion only for large source changes. Use when asked to review and fix a PR, or to run the…
cmux-fork-session
Fork the current agent session — Claude Code or pi — into a new cmux split pane (or tab): opens a split beside the caller, relaunches this session forked (claude --fork-session / pi --fork), titles it 'fork: ', and keeps that title. Use when the user asks to fork/duplicate/branch the current session into a new split…
cmux-rebuild
Manage the user's durable dev sessions — zellij sessions on remote hosts (bonbon, taffy) reached over mosh, plus the local host's (trifle) own detached zellij sessions, surfaced as cmux tabs via ssh::durable / zellij::resume. Load when the user wants to rebuild/resurrect lost cmux durable surfaces after a cmux restart…