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.
npx agentmods add skills/constellos/claude-code/pr-workflownpx skills add constellos/claude-code --skill pr-workflowgit clone --depth 1 https://github.com/constellos/claude-codeWhat 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 | $0.00052 | $0.01101 |
| Opus 5 | $0.00026 | $0.00550 |
| Sonnet 5 | $0.00010 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
PR Workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Workflow
Complete PR lifecycle management with auto-generated descriptions from commits and issues.
Purpose
PR Workflow provides systematic pull request management with intelligent description generation, template selection based on work type, and automated review requests.
When to Use
- Creating PRs with auto-generated descriptions
- Using templates based on work type (feature/fix/chore/docs/refactor)
- Updating PR metadata (reviewers, labels, milestones)
- Managing PR lifecycle (draft → ready → merge)
Core Capabilities
PR Creation with Auto-Description
# Get commits since base branch
COMMITS=$(git log main..HEAD --oneline --no-decorate)
# Get linked issue
BRANCH=$(git branch --show-current)
ISSUE=$(extractIssueNumber "$BRANCH")
# Generate description
DESC=$(generatePRDescription "$COMMITS" "$ISSUE")
# Create PR
gh pr create --title "Add authentication system" --body "$DESC"
Utilities:
generatePRDescription(commits, linkedIssue?)- Auto-generate from commitsgetPRTemplateByWorkType(workType)- Get template by typerenderPRTemplate(template, vars)- Substitute variablesgroupCommitsByType(commits)- Group by conventional commit typesformatGroupedCommits(grouped)- Format as sections
Template Selection
Templates automatically adapt to work type:
Feature PR:
## Summary
Brief overview
## Changes
- Change 1
- Change 2
## Testing
- [ ] Unit tests
- [ ] Integration tests
## Related Issues
Closes #42
Bug Fix PR:
## Bug Fix
Brief description
## Root Cause
What caused it
## Solution
How we fixed it
## Testing
- [ ] Bug reproduced before fix
- [ ] Bug resolved after fix
Review Requests
# Auto-request reviewers from CODEOWNERS
OWNERS=$(grep "^$(dirname $FILE)" .github/CODEOWNERS | awk '{print $2}')
gh pr edit $PR --add-reviewer "$OWNERS"
# Or manually
gh pr edit $PR --add-reviewer @user1,@user2
PR Updates
# Update labels
gh pr edit 42 --add-label "enhancement,priority:high"
# Update milestone
gh pr edit 42 --milestone "v2.0"
# Convert to draft
gh pr ready --undo 42
# Mark ready for review
gh pr ready 42
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.
- 2d ago First seen · 188 lines · 52 tokens per session scan A 32f86da71579
PR Workflow is a skill published in the GitHub repository constellos/claude-code (5 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,101 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…