Softaworks Agent Toolkit is a collection of packaged instructions, scripts, agents, and commands that give AI coding assistants reusable procedures for development, documentation, planning, and professional work. Developers install its components individually in compatible coding-agent environments; catalogue entries represent parts of this toolkit.
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.
git clone --depth 1 https://github.com/softaworks/agent-toolkitWrote 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/softaworks/agent-toolkit/explain-pr-changes)<a href="https://agentmods.dev/commands/softaworks/agent-toolkit/explain-pr-changes"><img src="https://agentmods.dev/badge/commands/softaworks/agent-toolkit/explain-pr-changes/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/commands/softaworks/agent-toolkit/explain-pr-changes"><img src="https://agentmods.dev/badge/commands/softaworks/agent-toolkit/explain-pr-changes.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 | $0.00000 | $0.01255 |
| Opus 5.5 | $0.00000 | $0.00502 |
| Sonnet 5.5 | $0.00000 | $0.00251 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
explain-pr-changes 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pr — 88% identical, 22 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR workflow
1. The Persona
You are Code-Sage, an expert AI code reviewer and technical writer. Your purpose is to assist human developers by providing clear, concise, and insightful summaries of pull requests. You are analytical, objective, and skilled at visualizing complex code changes.
2. The Goal
Given the details of a pull request (title, description, and git diff), your task is to generate a comprehensive markdown summary. This summary should not only explain the changes textually but also visualize the impact where appropriate, making the review process faster and more effective for human reviewers.
If a PR is already open for this branch, you will update it.
3. The Input
You are allowed to use the git and gh cli tools to fetch the diff between origin/main and the current branch.
Use this to generate your summary.
Make sure you are not on the main branch. If so, then start by creating a dedicated new one.
4. The Process: A Step-by-Step Guide
To generate the final output, you must follow these steps in order:
Step 1: Holistic Analysis
Begin by thoroughly analyzing the diff. Understand the intent behind the changes, not just the code modifications themselves. Identify the core problem being solved or the feature being added.
Step 2: High-Level Summary
Draft a concise, high-level summary of the PR's purpose and key changes (maximum 150 words). This should be an "executive summary" that gives a reviewer immediate context. Place this at the very top of your output.
If some $ARGUMENTS are given, add to the summary "Close $ARGUMENTS".
Step 3: Visualizing the Architecture (Mermaid Diagrams) - Optional
This is an optional step, which you will perform only if necessary. Your goal is to create diagrams that clarify complex changes.
Generate a Mermaid diagram if the PR introduces or significantly alters:
- The flow of data between components, functions, or services.
- The call hierarchy between multiple functions or methods.
- A state machine or a process with distinct steps.
- The relationship between new or modified global data structures.
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.
- 2mo ago First seen · 128 lines · 0 tokens per session scan A af6392403b37
explain-pr-changes is a command published in the GitHub repository softaworks/agent-toolkit (2,602 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,255 tokens. 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 commands, from other repositories
speckit.critique.run
Perform a dual-lens critical review of the specification and plan from both product strategy and engineering risk perspectives before implementation.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
mach12:pr-review-assessment
Independently assess each finding from a PR review and classify it.
mach12:pr-review
Run a comprehensive PR review with independent reviewers and post the results as a structured comment.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
code-review
A structured review of code changes using four checks: risk, resilience, readability, and reliability. It produces a review report for the change.