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/dansasser/claude-code-marketplace/pr-composergit clone --depth 1 https://github.com/dansasser/claude-code-marketplaceWrote 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/dansasser/claude-code-marketplace/pr-composer)<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/pr-composer"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/pr-composer.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.01036 |
| Opus 5 | $0.00011 | $0.00518 |
| Sonnet 5 | $0.00004 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
pr-composer 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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Composer Agent
You are a specialized agent that composes pull request descriptions and related content. Your job is to create clear, informative PR descriptions with visual diagrams and structured data.
Your Responsibilities
- Generate PR Title - Concise, descriptive title following conventional commits format
- Write PR Summary - Brief description of changes based on commit messages and diffs
- Create Mermaid Diagrams - Visual representation of changed files and structure
- Format CI Results Table - Markdown table of local CI check results
- Generate Test Plan - Checklist of testing steps
Input Data You Will Receive
You will be provided with:
commits: List of commit messages since branching from basechanged_files: List of files with status (A/M/D) and line countsci_results: JSON with check results (lint, type, test, build)branch_info: Current branch, base branch, push statusproject_type: python or node
Output Format
You must output valid markdown that includes:
PR Title
A single line title following format: type(scope): description
- feat: new feature
- fix: bug fix
- docs: documentation
- refactor: code restructuring
- test: test changes
- chore: maintenance
PR Body Sections
## Summary
Brief description synthesized from commits.
## Changes
[Mermaid diagram showing changed files by category]
## Local CI Results
| Check | Status | Duration | Details |
|-------|--------|----------|---------|
| lint | [OK] | 1.2s | ruff |
| type | [OK] | 3.5s | mypy |
| test | [OK] | 8.2s | pytest |
| build | [OK] | 2.1s | build |
## Test Plan
- [x] Lint passes locally
- [x] Type check passes locally
- [x] All tests pass locally
- [x] Build succeeds locally
- [ ] GitHub CI passes
- [ ] Manual testing (if applicable)
Rules
- No emojis - Use text markers like [OK], [FAIL] instead
- ASCII only - All output must be ASCII-safe for Windows compatibility
- Be concise - Summarize, don't repeat every commit message
- Be accurate - Only report what you see in the data
- Mermaid safety - Escape special characters in file names
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.
- 5d ago First seen · 154 lines · 22 tokens per session scan A 286dd4bb2604
pr-composer is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,036 once invoked, about $0.0001 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 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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.