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/pivoshenko/pivoshenko.ai/git-pr-createnpx skills add pivoshenko/pivoshenko.ai --skill git-pr-creategit clone --depth 1 https://github.com/pivoshenko/pivoshenko.aiWrote 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/pivoshenko/pivoshenko.ai/git-pr-create)<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/git-pr-create"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/git-pr-create.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 | $0.00244 | $0.01385 |
| Opus 5 | $0.00122 | $0.00692 |
| Sonnet 5 | $0.00049 | $0.00277 |
| Haiku 4.5 | $0.00024 | $0.00138 |
Grade A, and why
git-pr-create 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR
Open GitHub PR for current branch. No confirm.
Flow
- Parallel:
git statusgit branch --show-currentgit log <base>..HEAD --oneline(<base>= user-named, elsemain, fallbackmaster)git diff <base>...HEAD- check repo PR template:
.github/PULL_REQUEST_TEMPLATE.md,.github/pull_request_template.md,docs/PULL_REQUEST_TEMPLATE.md, rootPULL_REQUEST_TEMPLATE.md(first match wins)
- 0 commits ahead -> stop. Tell user: nothing to PR; commit first via
git-commit. - Not pushed / behind ->
git push -u origin <branch>. - Read all branch commits (not just latest). Draft title + body.
- Template found -> fill that template's structure (preserve headings, checklist items, comment placeholders).
- No template -> use fallback body below.
- Derive labels (always pass
--label):- Map title
<type>-> label:feat->enhancement,fix->bug,docs->documentation,test->tests,perf->performance,refactor->refactor,build->build,ci->ci,chore->chore. - Breaking change in commits/body -> add
breaking-change. - Verify labels exist:
gh label list --json name -q '.[].name'. Drop any missing; never auto-create. - At least 1 label required -> if all dropped, fall back to
chore. Ifchorealso missing, surface to user and stop.
- Map title
- Heredoc body so markdown survives shell:
gh pr create --title "feat(auth): add oauth login flow" --label enhancement --body "$(cat <<'EOF' # Pull Request Checklist <!-- Resolves: #123 --> ## Summary - swap session cookies for OAuth flow against Google provider - persist user via existing `users` table ## Checklist - [ ] My code follows the project style guidelines - [ ] I have performed a self-review of my code EOF )"'EOF'quoted -> no shell interpolation. - Print PR URL.
Title
Same as commits:
<type>(<scope>): <short summary>
- type:
build|chore|ci|docs|feat|fix|perf|refactor|test(same set + picks asgit-commit) - scope: optional
- summary: imperative present, lowercase, no
. - Whole title ≤ 72 chars (matches
git-commitheader limit).
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 · 115 lines · 244 tokens per session scan A a212223988b9
git-pr-create is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed 6d ago), licensed MIT. It adds 244 tokens to every session and 1,385 once invoked, about $0.0012 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
agent-architecture-planner
Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code agent workflow. Triggers: 'design an agent', 'build an automation', 'agent architecture', 'automate this workflow', 'create a scheduled agent', 'shell script agent'.
agent-curator
Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.
agent-browser
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
agent-builder
Build custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks smart clarifying questions, researches the internet for similar agents (GitHub repos, blogs, Claude Code community patterns), and then architects and builds production-ready Claude Code agents …
agent-creator
Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks…
81-pipecat
Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter.