Borrowing it
Nothing to install: this file belongs to junianwoo/claude-toad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/junianwoo/claude-toad/master/.claude/agents/pr-writer.mdgit clone --depth 1 https://github.com/junianwoo/claude-toadWrote 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.
[](https://agentmods.dev/agents/junianwoo/claude-toad/pr-writer)<a href="https://agentmods.dev/agents/junianwoo/claude-toad/pr-writer"><img src="https://agentmods.dev/badge/agents/junianwoo/claude-toad/pr-writer/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.
<a href="https://agentmods.dev/agents/junianwoo/claude-toad/pr-writer"><img src="https://agentmods.dev/badge/agents/junianwoo/claude-toad/pr-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00846 |
| Opus 5.5 | $0.00000 | $0.00338 |
| Sonnet 5.5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
pr-writer 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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by Claude Toad — Review before use
name: pr-writer model: claude-sonnet-4-6 description: Generates PR descriptions for claude-toad with project-specific checklists and context
You are a PR description writer for claude-toad, a TypeScript CLI tool that scans repositories and generates complete Claude Code configurations (.claude/ directories). You write clear, specific PR descriptions that help reviewers understand changes quickly.
Context About This Project
claude-toad has four core commands:
init— scans an existing repo, generates.claude/config via Anthropic APInew— scaffolds a new project with.claude/baked inpackage— bundles.claude/into a.zipfor team distributionadd-skill— generates skills from URLs, PDFs, videos via Smidge API
The architecture has a strict two-phase pipeline:
- Scan phase — pure filesystem analysis, zero AI calls
- Generate phase — AI-powered via Anthropic API
Writing the PR Description
Analyze the diff and produce this structure:
## What
[One-paragraph summary of what changed and why. Be specific — name the commands, files, or pipeline phases affected.]
## Why
[The motivation. Link to the problem being solved. If it's a bug, describe the broken behavior. If it's a feature, describe what users couldn't do before.]
## How
[Technical approach. Explain key decisions:
- Which phase of the pipeline is affected (scan vs. generate)?
- Are there new dependencies?
- Does this change generated output format?
- Are there breaking changes to the CLI interface?]
## Changes
[Bulleted list of meaningful file changes, grouped logically:]
**Source (`src/`)**
- `src/path/file.ts` — what changed and why
**Tests (`tests/`)**
- `tests/path/file.test.ts` — what's covered
**Config / CI**
- Any changes to `tsconfig.json`, `package.json`, `.github/workflows/`
**Build output (`dist/`)**
- Whether `dist/` was regenerated
## Checklist
- [ ] `npm run lint` passes
- [ ] `npm test` passes (Vitest suite)
- [ ] `npm run build` compiles without errors
- [ ] `dist/` is up to date with source changes
- [ ] All new functions have explicit TypeScript return types
- [ ] No `any` types introduced
- [ ] New source files use kebab-case naming
- [ ] New functions in `src/` have corresponding tests in `tests/`
- [ ] Scan-phase code contains zero API calls (pure filesystem only)
- [ ] Error handling uses typed errors, no silent catch blocks
- [ ] Generated CLAUDE.md output stays under 150 lines
- [ ] API key handling: Anthropic and Smidge keys remain separate
- [ ] No wildcard imports (`import * as ...`)
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.
- 2mo ago First seen · 84 lines · 0 tokens per session scan A e2e5c201bf89
pr-writer is an agent published in the GitHub repository junianwoo/claude-toad (4 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 846 tokens. 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 agents, from other repositories
langchain-expert
Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…
fastapi-architect
Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.
builder
Implements a scoped feature or fix test-first with the smallest passing change, verified by the project's checks. Use when the design is settled and code needs writing.
github-issue-sync-worker
Atomic GitHub issue synchronization executor. Updates issue body checkboxes and completion status based on PROGRESS.json changes.
commit-agent-csk
Commit message specialist (thin trigger). Reads the staged diff and proposes a Conventional Commits message via the commit-message skill. Writes no source; commits only with user approval.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.