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 commands/dansasser/claude-code-marketplace/prep-prgit 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/commands/dansasser/claude-code-marketplace/prep-pr)<a href="https://agentmods.dev/commands/dansasser/claude-code-marketplace/prep-pr"><img src="https://agentmods.dev/badge/commands/dansasser/claude-code-marketplace/prep-pr.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 | $0.00008 | $0.00765 |
| Opus 5 | $0.00004 | $0.00382 |
| Sonnet 5 | $0.00002 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
prep-pr 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare PR
Automate the complete PR preparation workflow from any branch state to published package.
What This Command Does
- Detects your environment and project type (Python or Node.js)
- Validates CI workflow exists (creates one if missing)
- Analyzes git state (uncommitted, unstaged, unpushed changes)
- Checks lock file consistency
- Runs local CI (lint, type, test, build) with smart error recovery
- Commits changes if needed
- Pushes to remote
- Creates detailed PR with Mermaid diagrams
Usage
/prep-pr # Full pipeline
/prep-pr --no-push # Run CI only, don't push
/prep-pr --resume # Resume from last failure
/prep-pr --merge # Auto-merge after CI passes
/prep-pr --release # Create version tag after merge
Options
--no-push- Run local CI validation only, don't push or create PR--resume- Resume from last saved state (useful after fixing errors)--merge- Wait for GitHub CI, then auto-merge the PR--release- After merge, create a version tag for release
Requirements
- Git repository with a remote configured
- Python 3.10+ (for running helper scripts)
- For Python projects: ruff, mypy, pytest, build
- For Node projects: npm/yarn/pnpm/bun, eslint, tsc
Example Workflow
$ /prep-pr
[INFO] Starting PR preparation...
[OK] Environment: Windows 11, PowerShell
[OK] Project: Python (pip), pyproject.toml detected
[OK] Workflow: .github/workflows/ci.yml exists
[INFO] Analyzing git state...
[OK] Branch: feature/auth (3 commits ahead of main)
[INFO] Running local CI...
[OK] lint (ruff) - 1.2s
[OK] type (mypy) - 3.4s
[OK] test (pytest) - 8.7s
[OK] build - 2.1s
[INFO] Pushing to origin/feature/auth...
[OK] Pushed successfully
[INFO] Creating pull request...
[OK] PR #42 created: https://github.com/user/repo/pull/42
Error Recovery
If CI fails, the system will:
- Diagnose the error type (dependency, lock file, stale artifacts, cache)
- Attempt automatic recovery for recoverable errors
- Report clearly if manual intervention is needed
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.
- 4d ago First seen · 96 lines · 0 tokens per session scan A 9bbfd611635e
prep-pr is a command published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 765 once invoked, about $0.0000 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 commands, from other repositories
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
commit
智能创建 git 提交，分析代码变更并生成符合项目规范的提交信息.
changelog
Summarize staged git changes into a concise changelog/commit message.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.