agentmods.dev

create-pr

create-pr is a skill for Claude Code from rfxlamia/pocketto. It costs 66 tokens per session (3,353 once invoked), scanned A, original, MIT.

A GitHub pull-request tool for a completed Pocket development phase. A pull request is a request to review and merge changes into a shared code branch.

In plain words
What is it for?
Use it to open or reuse a pull request for the current branch, link it to the Pocket issue, and include what changed, why, and how to test it.
Why use it?
It gathers the phase details into a consistent review request and records the resulting pull request for Pocket.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node enterprise/cli.js preflight <project-root> --json.

Part of the pocketto plugin — 16 skills shipped together

not rated 6repo changed 8d ago A scan 66 tokens original MIT

Good fit Use it to open or reuse a pull request for the current branch, link it to the Pocket issue, and include what changed, why, and how to test it.

Compare 6 skills from other repositories ↓
View source ↗ rfxlamia/pocketto pocketto.rfxlamia.xyz
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/rfxlamia/pocketto
agentmods
npx agentmods add skills/rfxlamia/pocketto/create-pr

Made for: Claude Code.

Or install pocketto, the plugin that ships this one along with the rest of its 16 skills.

Wrote 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.

agentmods badge for create-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/rfxlamia/pocketto/create-pr/github.svg)](https://agentmods.dev/skills/rfxlamia/pocketto/create-pr)
Your own site
<a href="https://agentmods.dev/skills/rfxlamia/pocketto/create-pr"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/create-pr/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.

agentmods 80×15 button for create-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/rfxlamia/pocketto/create-pr"><img src="https://agentmods.dev/badge/skills/rfxlamia/pocketto/create-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,353 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.03353
Opus 5.5 $0.00026 $0.01341
Sonnet 5.5 $0.00013 $0.00671
Haiku 4.5 $0.00007 $0.00335

Measured 8d ago against content hash 44140052f7ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 8d 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.

skills/create-pr/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create PR

Enterprise-owned recorder for opening or reusing a pull request for a completed development phase. It has two paths selected from log.json:

  • Stacked plans (header.phase_branches.mode == "stacked"): a manual repair recorder that runs publish-phase against the recorded phase branch. The phase branch is read by ref and is never checked out.
  • Other plans (none or no phase_branches header): creates or reuses the PR for the current branch.

It does not own phase-verdict reporting.

Core principle: This is an explicit user-triggered recorder. It creates or discovers a PR, records its identity, and surfaces preflight warnings verbatim. Phase summaries and inline verdicts belong to the Enterprise adapter, not this skill or Core.

v4 boundary: Package 4.2.2 uses CONTRACT=3, PIPELINE=5, lifecycle schema 2, adapter contract 2, and surface manifest 1. This skill is part of the additive Enterprise role and requires matching Core. Core is local-first: it does not call gh, it does not merge pull requests, and it does not close issues. This recorder may call GitHub only after explicit user invocation and successful Enterprise preflight; it never merges a PR or closes an issue.

Use this when: The user requests a phase PR, or explicitly confirms an Enterprise offer. For a non-stacked plan the target phase is in REVIEW. For a stacked plan the target phase is DONE and its phase-closed event exists (created by log handoff, see pocket-closing's Stacked Handoff).

Do NOT use when: Enterprise is disabled, a compatible Core/adapter preflight fails, or there is no linked issue.

Invocation

/pocketto:create-pr <plan_dir> [<phase_file>]

Examples:

/pocketto:create-pr docs/pocket/plans/2026-09-19-feature/
/pocketto:create-pr docs/pocket/plans/2026-09-19-feature/ execution-plan/phase-1.md
  • <plan_dir> contains log.json and the execution-plan files.
  • <phase_file> is optional. When omitted, select the unique log.phases[] entry that is eligible for the plan's path: status == REVIEW for non-stacked plans, or status == DONE for stacked plans. Zero or multiple matches require an explicit phase file.

Read the full file on GitHub · 262 lines

Files

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.

Changes

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.

  1. 8d ago Changed 44140052f7ad
  2. 11d ago Changed 0c74406e7038
  3. 13d ago Changed · +75 lines · +25 tokens per session 8fa79f770329
  4. 15d ago Changed e9583b6f60e8
  5. 17d ago Changed · -25 lines · -42 tokens per session 499c189f3457
  6. 1mo ago First seen · 212 lines · 83 tokens per session scan A 8344a61191f5

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository rfxlamia/pocketto (6 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 3,353 once invoked, about $0.0003 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.

Claude CodeCode reviewGit and workflowagentic-workflowai-agentsclaude-code-pluginclaude-code-skills
Related

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.

oliver-kriska/claude-elixir-phoenix · 59 tokens

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.

oliver-kriska/claude-elixir-phoenix · 61 tokens

deploy-landed

A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.

avelikiy/great_cto · 103 tokens

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…

avelikiy/great_cto · 105 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

pr-sweep

Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…

harnessprotocol/harness-kit · 115 tokens