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 aragaobruno/toolbelt --skill smart-pr-generatorgit clone --depth 1 https://github.com/aragaobruno/toolbeltWrote 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/aragaobruno/toolbelt/smart-pr-generator)<a href="https://agentmods.dev/skills/aragaobruno/toolbelt/smart-pr-generator"><img src="https://agentmods.dev/badge/skills/aragaobruno/toolbelt/smart-pr-generator/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/aragaobruno/toolbelt/smart-pr-generator"><img src="https://agentmods.dev/badge/skills/aragaobruno/toolbelt/smart-pr-generator.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 | $0.00031 | $0.00447 |
| Opus 5.5 | $0.00012 | $0.00179 |
| Sonnet 5.5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
smart-pr-generator 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.
What it actually says
🚀 smart-pr-generator
Overview
Writing detailed commit messages and Pull Request descriptions is critical for clean codebases, but it creates significant cognitive load and context-switching overhead. The smart-pr-generator automates this process. It reads your git workspace diff, sends it to Gemini for SRE-grade analysis, and formats a conventional commit message alongside a detailed description. It strictly filters out AI jargon ("AI-slop"), ensuring all output looks natural and human-authored.
Quick Start
To review a generated commit message and PR description for your changes:
node skills/devops/smart-pr-generator/scripts/generator.js show
To automatically stage your files and commit them using the generated conventional commit message:
git add .
export GEMINI_API_KEY="your-gemini-key"
node skills/devops/smart-pr-generator/scripts/generator.js commit
To save the generated PR description to a Markdown file:
node skills/devops/smart-pr-generator/scripts/generator.js save --output PR.md
Utility Scripts
generator.js (CLI)
A Node.js tool to automate git commits and PR formatting.
Subcommand: show (default)
Prints the conventional commit message suggestion and a fully formatted PR description (Goal, Proposed Changes, Verification) in Markdown.
- Example:
node generator.js show
Subcommand: commit
Automatically commits the changes (executes git commit -m "<suggested_message>") directly in your workspace.
- Example:
node generator.js commit
Subcommand: save
Saves the PR description block into a markdown file.
- Arguments:
[--output <path>](defaults toPR_DESCRIPTION.md) - Example:
node generator.js save --output docs/PR-102.md
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 31 tokens per session scan A 7573da70a5b2
smart-pr-generator is a skill published in the GitHub repository aragaobruno/toolbelt (2 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 447 once invoked, about $0.0001 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
gsd-pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
github
Manage the full GitHub workflow from the terminal — auth, issues, pull request lifecycle (branch/commit/open/CI/merge), code review, and repo management. Uses the gh CLI when present, with a git + REST API fallback. Use when asked to "open a PR", "create an issue", "review this PR", "check CI", "list issues".
address-pr-feedback
Unified PR feedback workflow - collect, triage, and fix review comments in a single command.
pr
Create a pull request using the Dedalus PR template. Injects git state, commit history, and diff stats automatically.
speclite-goal-orchestrator-epic-story-code-review-runner
An Epic Story code-review runner coordinates development and code review for Stories within an Epic. It moves one Story at a time through development, review, evaluation, fixes, verification, and closeout using structured records.