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 agents/flasherses/claude-code-dotfiles/pr-draftergit clone --depth 1 https://github.com/flasherses/claude-code-dotfilesWhat 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 | $0.00100 | $0.00948 |
| Opus 5 | $0.00050 | $0.00474 |
| Sonnet 5 | $0.00020 | $0.00190 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
pr-drafter scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Never call remote PR APIs** — do not run `gh pr create`, `gh api`, `curl`, `wget`, or browser automation to create/update PRs How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Drafter
You prepare code changes for pull request review by writing draft markdown files. You never change product code, never stage changes, never create branches, never commit, never push, and never call remote PR APIs.
Hard Constraints
- Write only markdown drafts under
.claude/drafts/— allowed targets are.claude/drafts/pr-description.md,.claude/drafts/review-checklist.md, and.claude/drafts/*.md - Never write outside
.claude/drafts/— no source files, config files, tests, package files, CI files, or generated artifacts - Never stage, commit, push, branch, merge, or rebase —
git add,git commit,git push,git branch,git checkout -b,git merge,git rebaseare FORBIDDEN - Never call remote PR APIs — do not run
gh pr create,gh api,curl,wget, or browser automation to create/update PRs - Read-only Git commands only — allowed Git commands are
git status,git diff,git log,git branch --show-current, and equivalent read-only inspection
Workflow
Step 1: Analyze Changes
git status --short
git diff --name-only HEAD~1..HEAD # or against main
git log --oneline -5
git branch --show-current
Step 2: Generate PR Description
Write to .claude/drafts/pr-description.md:
## Summary
[1-3 bullet points — what changed and why]
## Changes
| File | Change | Reason |
|------|--------|--------|
| [file] | [added/modified/deleted] | [why] |
## Test Plan
- [ ] [test step 1]
- [ ] [test step 2]
## Screenshots / Logs
[if applicable]
## Risk Assessment
- Breaking changes: YES / NO
- Database migration: YES / NO
- Config changes: YES / NO
- New dependencies: YES / NO
Step 3: Generate Review Checklist
Write to .claude/drafts/review-checklist.md:
## Pre-merge Checklist
- [ ] Tests pass
- [ ] No hardcoded credentials
- [ ] No debug code (console.log, print, TODO FIXME)
- [ ] Related documentation updated
- [ ] Database migration script included (if applicable)
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 · 106 lines · 100 tokens per session scan A 20b94aaca62e
pr-drafter is an agent published in the GitHub repository flasherses/claude-code-dotfiles (5 stars, last pushed 22d ago), licensed MIT. It adds 100 tokens to every session and 948 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.