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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00173 | $0.02392 |
| Opus 5.5 | $0.00069 | $0.00957 |
| Sonnet 5.5 | $0.00035 | $0.00478 |
| Haiku 4.5 | $0.00017 | $0.00239 |
Grade A, and why
git-pr-create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git PR Create
Open GitHub PR for current branch. No confirm.
Flow
- Base: user names one -> use it. Else detect:
git symbolic-ref --short refs/remotes/origin/HEAD-> strip theorigin/; ref missing ->git remote set-head origin -a, re-read; no remote -> stop; a PR needs a GitHub remote. Why -> a wrong base makes the PR diff include commits that aren't yours git fetch origin <base>. Why -> everything below compares againstorigin/<base>, not the local ref: the local base is often stale or absent entirely (git-branch-createbranches offorigin/<base>without ever creating it), so a local-ref diff either errors or replays commits already merged- Parallel:
git statusgit branch --show-currentgit log origin/<base>..HEAD --onelinegit diff origin/<base>...HEAD- Linked issue, three sources, merged and deduped: the branch link
git config --get branch.$(git branch --show-current).issue(git-issue-startrecords it there), the branch's commit footersgit log origin/<base>..HEAD --format=%B | grep -oiE '(closes|fixes|resolves) #[0-9]+', and a trailing ticket id on the branch name (git-branch-create's optional-PROJ-123suffix). Why ->git-issue-startopens the branch from an issue andgit-commitwrites the closing trailer, so the number is already on the branch; nobody retypes it- Exactly 1 distinct issue -> fill the
Resolves:line with it - More than 1 -> first fills
Resolves:, the rest becomeRefs: #<n>lines under it. Why -> a PR closing several issues is normal, but only the primary one belongs in the template's Resolves slot - None -> drop the line entirely. Never emit a
#<n>placeholder
- Exactly 1 distinct issue -> fill the
- 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 / ahead ->
git push -u origin <branch>. Diverged from upstream (post-rebase) -> stop; tell user togit push --force-with-leasethemselves (same rule asgit-branch-sync) - 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):- Fetch the repo's labels once:
gh label list --limit 200 --json name -q '.[].name'. Why -> detection, not hardcoding: this skill syncs globally and runs on forks and third-party repos, where the bare names exist and a namespaced taxonomy does not - Resolve the title
<type>through its candidate chain, first existing name wins:
- Fetch the repo's labels once:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago Changed fefce59cb411
- 1mo ago Changed · -19 lines 3c41e74ed28b
- 1mo ago Changed · +24 lines · -56 tokens per session 0df7ad487877
- 1mo ago Changed 7125360fd34e
- 1mo ago Changed 07dcdc703e65
- 1mo ago Changed · +42 lines · -15 tokens per session da322c339d25
- 1mo 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 (6 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 2,392 once invoked, about $0.0007 per session on Opus 5.5. 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
skill-upstream-pr
Improve an open-source GitHub skill and open a friendly suggestion PR upstream: fork, run skill-creator's retrofit, attach asm eval before/after metrics. Don't use for local-only skills, authoring from scratch, bulk repos, or registry publish.
meanest-editor
Roast a pitch or press release with the eye of a veteran PR director. Honest, sharp, constructive — never cruel for its own sake.
headline-generator
Generate headline candidates from a story's raw facts: news-style headlines, press-release headlines, and pitch subject lines. A pure generation skill — it finds the charge in the facts, then runs ten proven moves (consequence, picture, number-as-hero, two-beat turn, naming, reader's-own-story, open question, voice…
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…
docs-updater
Provides automated documentation updates by analyzing git changes between the current branch and the last release tag. Performs git diff analysis to identify modifications, then updates README.md, CHANGELOG.md following Keep a Changelog standard, and discovers documentation folders for contextual updates. Use when…
loom-plan-writer
REQUIRED skill for creating Loom execution plans.