pr

A workflow for opening a GitHub pull request, which is a request to merge a branch into another branch. It includes cleanup, formatting, and test checks before creation.

In plain words
What is it for?
Use it to inspect branch status, remove scratch files, run cleanup and verification gates, and create the pull request.
Why use it?
It gives the project one controlled path for preparing a branch and catching unfinished or temporary work before requesting a merge.

Skill for Claude CodeCodex

Part of the agent-dashboard plugin — 8 skills, 5 agents, 10 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/bjornjee/agent-dashboard/pr
Any agent
npx skills add bjornjee/agent-dashboard --skill pr
Clone the repo
git clone --depth 1 https://github.com/bjornjee/agent-dashboard

Made for: Claude Code, Codex.

Or install agent-dashboard, the plugin that ships this one along with the rest of its 8 skills, 5 agents, 10 hooks.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00014 $0.02230
Opus 5 $0.00007 $0.01115
Sonnet 5 $0.00003 $0.00446
Haiku 4.5 $0.00001 $0.00223

Measured 3d ago against content hash 6bbb10afca37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

pr scanned grade C 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`rm -rf <path>`. Run from the repo root. Never pass `/`, `~`, `.`, `..`,
adapters/claude-code/skills/pr/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open a pull request for the current branch. This is the only sanctioned path to PR creation — a pr-skill-gate hook blocks any direct gh pr create that doesn't carry this skill's bypass marker.

Optional arguments: $ARGUMENTS

Instructions

Each phase has a gate. Do not proceed until it passes.


Phase 1: Sync state

Run in parallel:

  1. git status — warn if uncommitted changes (but proceed; the cleanup phase may add commits anyway).
  2. BASE=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||' || echo main) — detect default branch.
  3. git branch --show-current — current branch.
  4. git rev-parse --abbrev-ref @{upstream} 2>/dev/null — does it track a remote?
  5. git log --oneline $(git merge-base HEAD "$BASE")..HEAD — commits on this branch.
  6. git diff --name-only "$BASE"...HEAD — files changed vs base. Save this list — it's the input to Phase 3.

Gate: You have the changed-file list and the base branch.


Phase 2: Clean up scratch artifacts

Delete transient files left over from implementation, testing, and discovery — screenshots, Playwright MCP output, and tmp scratch — before the cleanup pass inspects the diff. Untracked only. Never touch tracked or staged files.

  1. Identify untracked artifacts. Use git ls-files --others --exclude-standard for unignored untracked files, and git ls-files --others --ignored --exclude-standard for ignored untracked files. Filter for these patterns:

    • *.png at the repo root only — these are typically Playwright/visual-audit screenshots. PNGs inside subdirectories (build outputs out/, dist/, build/, asset dirs public/, static/, source dirs src/, etc.) are legitimate and must NOT be deleted.
    • .playwright-mcp/ (directory)
    • *.tmp (anywhere)
    • tmp/ (directory, when at repo root or inside a subproject root)
  2. If the list is empty, skip the rest of this phase.

  3. Confirmation gate — deletion is destructive and irreversible. Show the user the exact list of paths about to be deleted (one line each) and ask explicit permission before deleting. If the user declines, skip deletion and proceed to Phase 3.

Read the full file on GitHub · 168 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. 3d ago First seen · 168 lines · 14 tokens per session scan C 6bbb10afca37

Subscribe to this mod's changes

pr is a skill published in the GitHub repository bjornjee/agent-dashboard (21 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 2,230 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.