kc-pr-create

kc-pr-create is a skill for Claude Code from iamcxa/kc-claude-plugins. It costs 48 tokens per session (5,021 once invoked), scanned B, original, MIT.

A skill for creating a GitHub pull request and taking it through review and delivery. It can create a draft, run self-review, mark it ready, check CI, and announce it.

In plain words
What is it for?
Use it to open a draft or standard pull request, add review comments, run a limited self-review loop, wait for CI and an AI review gate, and announce the result.
Why use it?
It organizes the steps from completed code changes to a reviewed pull request, including optional continuous-integration checks.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kc-pr-flow plugin — 7 skills, 3 agents shipped together

Good fit Use it to open a draft or standard pull request, add review comments, run a limited self-review loop, wait for CI and an AI review gate, and announce the result.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add iamcxa/kc-claude-plugins
Claude Code
/plugin install kc-pr-flow

Made for: Claude Code.

Or install kc-pr-flow, the plugin that ships this one along with the rest of its 7 skills, 3 agents.

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 kc-pr-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-pr-create.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-pr-create)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-pr-create"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-pr-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00048 $0.05021
Opus 5 $0.00024 $0.02511
Sonnet 5 $0.00010 $0.01004
Haiku 4.5 $0.00005 $0.00502

Measured 7d ago against content hash 305be5ceb283, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

kc-pr-create scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find .claude/e2e/reports -name "report.md" -newer .git/HEAD 2>/dev/null | head -3
kc-pr-flow/skills/kc-pr-create/SKILL.md · 499 lines

How it starts

The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.

All text output follows unified language preference. See plugin CLAUDE.md for query flow.

Create PR — Full Lifecycle

Default: create draft PR → self-review & fix → mark ready → announce. One command, no stops.

Invocation

/kc-pr-create [--draft-only] [--ci] [--no-announce] [--max-rounds N]
Flag Default Effect
(none) ship mode Draft → review loop → ready → announce
--draft-only Create PR only (Steps 1-9), skip ship chain
--ci off After ready: poll CI + offer AI reviewer wait
--no-announce Ship but skip announce
--max-rounds N 3 Self-review loop iteration limit

Process

1.  Analyze          ─┐
1.5 E2E Suggestion    │
2.  Title              │ Part A: Create Draft PR
3.  Body               │ (always runs)
4.  Confirm            │
5.  Create (--draft)   │
6.  Annotate           │
7.  Confirm comments   │
8.  Post comments      │
9.  Linear Comment    ─┘
    │
    ├─ --draft-only → Step 13 (Announce, legacy behavior) → Done
    │
10. Self-Review Loop  ─┐
11. Mark Ready          │ Part B: Ship Chain
12. CI + AI Gate (--ci) │ (default, skip if --draft-only)
13. Announce            │
14. Done              ─┘

Small PR shortcut (<100 lines, single file): skip Steps 6-8.

Step 1: Analyze

Read → ${CLAUDE_PLUGIN_ROOT}/reference/gh-api-patterns.md § "PR Detection"

If PR exists, ask user: update or skip.

Step 1.5: E2E Verification Suggestion (conditional)

Skip conditions (any one → skip silently):

  • No .claude/e2e/mappings/ directory (e2e pipeline not set up in this project)
  • Diff is single-layer only (frontend-only or backend-only)
  • PR is docs-only, deps-only, or test-only

Detection: Read → ${CLAUDE_PLUGIN_ROOT}/reference/e2e-verification.md for layer classification patterns.

After analyzing the diff (Step 1), classify changed files into layers. If diff touches 2+ layers → integration change detected.

Present suggestion:

⚡ This PR modifies frontend-backend integration:
  - Backend: <list of backend files>
  - Frontend: <list of frontend files>

E2E verification creates a repeatable flow proving the feature works.
  1. /e2e-walkthrough --verify — interactive verification (generates reusable flow)
  2. /e2e-test <existing-flow> --video — replay existing flow with recording
  3. Skip — proceed to PR creation

Read the full file on GitHub · 499 lines

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. 7d ago First seen · 499 lines · 48 tokens per session scan B 305be5ceb283

Subscribe to this mod's changes

kc-pr-create is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 5,021 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens