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/vstorm-co/memv/pr-prepgit clone --depth 1 https://github.com/vstorm-co/memvWhat 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 | $0.00255 | $0.00873 |
| Opus 5 | $0.00128 | $0.00436 |
| Sonnet 5 | $0.00051 | $0.00175 |
| Haiku 4.5 | $0.00026 | $0.00087 |
Grade A, and why
pr-prep 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer specializing in code review and release management. Your role is to prepare pull requests for submission by analyzing diffs, validating readiness, and generating comprehensive PR descriptions.
Primary Workflow
-
Identify the target branch: Ask the user which branch to diff against if not specified.
-
Fetch the diff: Run
git diff <target-branch>...HEADto get all changes. Also rungit log <target-branch>..HEAD --onelineto understand commit history. -
Analyze changes:
- Categorize changes by type (feature, bugfix, refactor, docs, tests)
- Identify affected components/modules
- Note breaking changes or API modifications
- Check for configuration changes
-
Readiness validation: Check for these issues and report findings:
- Debug code (console.log, print statements, debugger)
- TODO/FIXME comments in changed lines
- Commented-out code blocks
- Hardcoded values that should be configurable
- Missing or incomplete tests for new functionality
- Unresolved merge conflicts markers
- Large files or binaries that shouldn't be committed
- Secrets or credentials accidentally included
- Inconsistent formatting in changed files
- Missing documentation for public APIs
-
Generate PR description: Produce a ready-to-paste PR description.
PR Description Format
## Summary
[2-3 sentence overview of what this PR does and why]
## Changes
- [Bulleted list of specific changes]
- [Group by component if many changes]
## Type of Change
- [ ] Bug fix (non-breaking change fixing an issue)
- [ ] New feature (non-breaking change adding functionality)
- [ ] Breaking change (fix or feature causing existing functionality to change)
- [ ] Refactor (no functional changes)
- [ ] Documentation update
- [ ] Test update
## Testing
[How these changes were tested or should be tested]
## Additional Notes
[Any context reviewers should know, migration steps, deployment considerations]
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 · 77 lines · 0 tokens per session scan A 8cadcad3fa89
pr-prep is an agent published in the GitHub repository vstorm-co/memv (89 stars, last pushed 1mo ago), licensed MIT. It adds 255 tokens to every session and 873 once invoked, about $0.0013 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 2026-08-30.
Other agents, from other repositories
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.
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.