Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bendrucker/claude/plugin install pull-requestWrote 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/bendrucker/claude/create)<a href="https://agentmods.dev/skills/bendrucker/claude/create"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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/bendrucker/claude/create"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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 | $0.00037 | $0.02274 |
| Opus 5.5 | $0.00015 | $0.00910 |
| Sonnet 5.5 | $0.00007 | $0.00455 |
| Haiku 4.5 | $0.00004 | $0.00227 |
Grade A, and why
pull-request: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 today.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Pull Request
Give the reviewer what the diff cannot: why the change exists, the decisions behind it, and how you know it works. Open the PR in the state the repo's workflow expects, so review starts without the user first fixing the title, the body, the base, or the labels.
The commit log, PR template, CONTRIBUTING notes, and review-bot config in the context below record conventions this document does not anticipate. Follow them over the defaults here.
Context
- Remote URL: !
git remote get-url origin - Review bot: !
bun ${CLAUDE_PLUGIN_ROOT}/scripts/detect-bot.ts - PR Template: !
bun ${CLAUDE_PLUGIN_ROOT}/scripts/pr-template.ts
!bun ${CLAUDE_PLUGIN_ROOT}/scripts/git-context.ts
!bun ${CLAUDE_PLUGIN_ROOT}/scripts/sem-context.ts
!bun ${CLAUDE_PLUGIN_ROOT}/scripts/contributing.ts
Arguments
Parse $ARGUMENTS for these flags. With no flags, open a PR/MR ready for review, and set auto-merge on a repo you own.
--draft: open the PR/MR as a draft. Default: ready for review.--no-auto: skip auto-merge. Default: auto-merge on a repo you own, off on a third-party repo and off under--draft.--base <ref>: parent branch to target. Default: the repo's default branch. A branch whose parent is another topic branch is a stack layer, identified only by this flag or by the user. The upstream ref tracks the branch's own remote copy, so it cannot identify the parent.--label <name>: apply a label, repeatable. Default: none.--no-review: skip the hosted review request. Default: on a repo that gates its hosted bot on a label, request the review when the diff clears the metered-review gate and no local pass ran.--[no-]review-body: put the drafted body in front of the user before creating. Default: on when the Remote URL above names an owner other than you, off on your own repos.
Title
Match the repo's commit style, read from the log in the context above:
- subject (default):
${subject}: ${summary}, as inapi: add timeout to request. - conventional:
${type}: ${summary}, as infix: add timeout to request.
What ships with it
5 files 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.
- today Changed 85edc2092a33
- 4d ago Changed 76750c326569
- 22d ago Changed 3345a04d1574
- 1mo ago Changed · +8 lines · -10 tokens per session 6158d0027a07
- 1mo ago Changed · +7 lines e3170c09f033
- 1mo ago Changed · +1 lines 3235355fca2a
- 1mo ago Changed 495743b2c595
- 1mo ago First seen · 91 lines · 47 tokens per session scan A deb19a63f304
pull-request:create is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,274 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
pr-review
Review pull requests and Git diffs with Graph-It-Live risk, breaking-change, dependency-impact, cycle, unused-export, and test-candidate evidence. Use when asked to review a PR, inspect a diff, assess merge risk, check a branch before merging, create a Graph-It-Live review gate, or explain review-pr results. Trigger…
loop-gh-pr
A recipe for a scheduled GitHub pull-request watcher. It checks open pull requests for new activity and prepares read-only review drafts without posting comments or merging anything.
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.