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 skills add VersoXBT/claude-initial-setup --skill pr-standardsgit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWrote 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/skills/versoxbt/claude-initial-setup/pr-standards)<a href="https://agentmods.dev/skills/versoxbt/claude-initial-setup/pr-standards"><img src="https://agentmods.dev/badge/skills/versoxbt/claude-initial-setup/pr-standards/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/skills/versoxbt/claude-initial-setup/pr-standards"><img src="https://agentmods.dev/badge/skills/versoxbt/claude-initial-setup/pr-standards.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 | $0.00062 | $0.01688 |
| Opus 5.5 | $0.00025 | $0.00675 |
| Sonnet 5.5 | $0.00012 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
pr-standards 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 1mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Standards
Define and enforce PR best practices to keep reviews fast, thorough, and productive. Small PRs with clear descriptions get reviewed faster and have fewer bugs.
When to Use
- Creating a pull request
- Setting up PR templates for a repository
- Establishing team review guidelines
- Configuring branch protection rules
- Discussing why PRs are too large or reviews are slow
Core Patterns
PR Size Limits
Keep PRs small and focused. Target under 400 lines of meaningful changes.
Size Guidelines:
XS (1-50 lines) - Typo fix, config change, one-liner bug fix
S (51-200 lines) - Small feature, focused bug fix, single-file refactor
M (201-400 lines) - Standard feature, multi-file change
L (401-800 lines) - Large feature (split if possible)
XL (800+ lines) - Too large. Must be split into smaller PRs.
Lines counted: Additions + deletions in application code.
Excluded from count: Lock files, generated code, snapshots, migrations.
Strategies for splitting large PRs:
1. Layer-by-layer: Database schema -> Backend API -> Frontend UI
2. Feature flags: Merge incomplete features behind flags
3. Refactor-then-feature: Separate refactoring PR from feature PR
4. Vertical slices: One complete user story per PR
PR Description Template
<!-- .github/pull_request_template.md -->
## Summary
<!-- What does this PR do and why? 1-3 bullet points. -->
## Changes
<!-- List the key changes made. Group by area if helpful. -->
## Testing
<!-- How was this tested? Include commands to reproduce. -->
- [ ] Unit tests added/updated
- [ ] Manual testing performed
- [ ] Edge cases covered
## Screenshots
<!-- If UI changes, include before/after screenshots. -->
## Related
<!-- Link to issue, Jira ticket, or previous PR. -->
Closes #
## Checklist
- [ ] Self-review completed
- [ ] No console.log or debug statements
- [ ] No hardcoded secrets
- [ ] Tests pass locally
- [ ] Documentation updated (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.
- 1mo ago First seen · 224 lines · 62 tokens per session scan A 7b00c10a8a21
pr-standards is a skill published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 1,688 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
pr-review-merge
Drive a single pull request to merge-ready across all six criteria (sync, CI, inline comments, conversation, threads, bot re-review of the head commit), then smart-merge it. Source-agnostic library skill invoked by the /tm, /issues, /fix-pr, and /fix-develop commands and by marathon teammates. TRIGGER when a command…
fix-pr
Autonomous PR fixing loop - iterates on CI failures and review comments until green.
pr-describe
Write a pull-request title and body from the current branch's commits and diff against the base branch. Invoke when the user asks to open a PR, draft a PR description, or summarize a branch.
seal
Ships a feature — simplify pass, certify, commit, PR, CI monitoring, review loop, merge. Use when a feature branch is verified and ready to ship.