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/bityoungjae/marketplace/prgit clone --depth 1 https://github.com/BitYoungjae/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/bityoungjae/marketplace/pr)<a href="https://agentmods.dev/commands/bityoungjae/marketplace/pr"><img src="https://agentmods.dev/badge/commands/bityoungjae/marketplace/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 5.1 | $0.00014 | $0.02740 |
| Opus 5 | $0.00007 | $0.01370 |
| Sonnet 5 | $0.00003 | $0.00548 |
| Haiku 4.5 | $0.00001 | $0.00274 |
Grade A, and why
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 6d 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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gitkkal pr
Creates or updates a Pull Request. Auto-detects existing PR for current branch.
The PR body must be readable by non-developers (product managers, designers, business stakeholders). Anyone should be able to grasp the purpose and impact of the change without opening the diff.
Critical Rules
- NEVER include
Co-Authored-Bylines in PR body - NEVER use
git push --force - NEVER modify already merged PRs
- NEVER create PR from main/master branch
- ALWAYS use HEREDOC for PR body
Usage
/gitkkal:pr # Create or update (auto-detected)
/gitkkal:pr emphasize refactoring # With hint
Prerequisites
1. Load Configuration
git rev-parse --show-toplevel # Find project root
Read {project_root}/.gitkkal/config.json. If not exists, use defaults and display once:
"Using default settings. Run /gitkkal:init to customize."
2. Verify GitHub CLI
gh auth status
If not installed: "GitHub CLI is required. Install from https://cli.github.com"
If not authenticated: "Run gh auth login to authenticate."
Mode Detection
gh pr view --json number,state 2>/dev/null
- Succeeds + state is
OPEN→ Update Mode - Fails or state is
CLOSED/MERGED→ Creation Mode
PR Creation Mode
1. Check Branch Status
git branch --show-current
git remote show origin | grep 'HEAD branch'
git status -sb
git log origin/$(git branch --show-current)..HEAD --oneline 2>/dev/null || echo "no-remote"
If on main/master → Error: "Cannot create PR from main branch. Create a new branch first."
2. Gather Change Information
Run in parallel:
git log main..HEAD --oneline # Commit history with messages
git diff main...HEAD --stat # File-level change summary
IMPORTANT: Analyze ALL commits from base branch, not just the latest.
3. Understand Semantic Intent
Use staged analysis to avoid reading unnecessarily large diffs.
Step 1: Analyze commit messages + --stat first. Most PRs have descriptive commit messages that reveal intent; --stat shows scope.
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.
- 6d ago First seen · 331 lines · 14 tokens per session scan A 8183bee45671
pr is a command published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 2,740 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 commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.