agentmods.dev

sdk: Skill for Claude Code

.agents/skills/pull-request/SKILL.md

pull-request is a skill for Claude Code, Codex from WaniWani-AI/sdk. It costs 68 tokens per session (585 once invoked), scanned A, original, MIT.

A workflow for opening a GitHub pull request for the latest commit and linking it to a Linear ticket. GitHub pull requests are proposed code changes reviewed before they are merged.

In plain words
What is it for?
It checks the branch and commit messages for a ticket, creates one when needed, assigns it to the current user, sets it in progress, and creates and pushes the pull request.
Why use it?
It removes the repeated setup of finding or creating the right ticket, assigning it, pushing the branch, and connecting the work for automatic tracking.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is WaniWani-AI/sdk's own configuration. It tells Claude Code and Codex how to work on sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sdk configures →

not rated 18repo 2d ago A scan 68 tokens original MIT
View source ↗ WaniWani-AI/sdk docs.waniwani.ai
Reuse

Borrowing it

Nothing to install: this file belongs to WaniWani-AI/sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/WaniWani-AI/sdk/main/.agents/skills/pull-request/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/WaniWani-AI/sdk

Made for: Claude Code, Codex.

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 pull-request

README.md
[![agentmods](https://agentmods.dev/badge/skills/waniwani-ai/sdk/pull-request/github.svg)](https://agentmods.dev/skills/waniwani-ai/sdk/pull-request)
Your own site
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/pull-request"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/pull-request/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 pull-request

Your own site · 80×15
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/pull-request"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/pull-request.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 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 $0.00068 $0.00585
Opus 5.5 $0.00027 $0.00234
Sonnet 5.5 $0.00014 $0.00117
Haiku 4.5 $0.00007 $0.00059

Measured 1mo ago against content hash f39d9b76298c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pull-request 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 1mo 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.

.agents/skills/pull-request/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Pull Request

Create a GitHub pull request immediately using the following rules:

Step 1: Ensure a Linear ticket exists (do this BEFORE pushing)

  1. Check whether a Linear ticket is already associated with this work. Look for a ticket identifier (e.g. WAN-123) in the current branch name and in the latest commit message(s).
  2. If a ticket identifier is found, reuse it - no need to create a new one.
  3. If NO ticket is found, create one with the Linear MCP:
    • Do NOT hardcode an email. The Linear MCP is authenticated as the person running this skill, so assign the issue with assignee: "me" - this is the reliable team-safe way to assign to the current user. (Git/GitHub email may differ from the Linear email, so matching by email is unreliable; only fall back to list_users matching if "me" is unavailable.) Use list_teams to resolve the team.
    • Create the issue with a concise title derived from the latest commit message, assigned to "me".
    • Set its state to "In Progress".
    • Capture the returned ticket identifier (e.g. WAN-123) and its URL.
    • Verify the assignment took effect (the created issue's assignee should be the current user); if it didn't, retry the assignment explicitly with save_issue.

Step 2: Create the PR

  1. Push any uncommitted changes first if needed. If there are uncommitted changes, commit them first before creating the PR.
  2. Ensure we're on the correct branch (not main/master).
  3. Use gh pr create --assignee @me to create the PR and auto-assign it to the user.
  4. Use the latest commit message as the PR title.
  5. Make sure the Linear ticket is referenced so Linear links and auto-closes the PR: include the ticket identifier (e.g. WAN-123) either in the branch name or in the PR description body. If the ticket identifier is NOT already in the branch name, the PR body MUST contain a line Closes WAN-123 (using the real identifier). If it is already in the branch name, leave the body empty.

Important:

  • Keep the PR title simple - just use the commit message as-is.
  • Do not add extra formatting or emoji to the title.
  • The Linear ticket check/creation MUST happen before pushing.

Read the full file on GitHub · 34 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. 1mo ago First seen · 34 lines · 68 tokens per session scan A f39d9b76298c

Subscribe to this mod's changes

pull-request is a skill published in the GitHub repository WaniWani-AI/sdk (18 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 585 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 2026-08-30.

Code reviewGit and workflowchatgptclaudeconversational-ailead-generationmcpmodel-context-protocol
Related

Other skills, from other repositories

code-review

Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep…

asgeirtj/system_prompts_leaks · 224 tokens

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

gh-issues

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…

spinabot/brigade · 116 tokens

github

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…

spinabot/brigade · 101 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/obsidian-mcp-server · 136 tokens

github-commenting

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.

juspay/neurolink · 41 tokens