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/GabsFranke/claude-code-github-agentWrote 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/gabsfranke/claude-code-github-agent/fix-review)<a href="https://agentmods.dev/commands/gabsfranke/claude-code-github-agent/fix-review"><img src="https://agentmods.dev/badge/commands/gabsfranke/claude-code-github-agent/fix-review/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/gabsfranke/claude-code-github-agent/fix-review"><img src="https://agentmods.dev/badge/commands/gabsfranke/claude-code-github-agent/fix-review.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 | $0.00011 | $0.02374 |
| Opus 5.5 | $0.00004 | $0.00950 |
| Sonnet 5.5 | $0.00002 | $0.00475 |
| Haiku 4.5 | $0.00001 | $0.00237 |
Grade A, and why
fix-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix PR Review Feedback
Read all review feedback from a PR, build a fix plan, delegate implementation to agents, and create a PR with the fixes.
Arguments: "$ARGUMENTS"
- First argument: Repository (owner/repo format, required)
- Second argument: PR number (required)
Your Role as Orchestrator
You coordinate the entire process. Your responsibilities:
- Create a branch for the fix work
- Fetch all review feedback from the PR
- Parse and deduplicate findings
- DELEGATE implementation to agents (they do ALL the coding)
- Run quality checks
- Create the PR targeting the original PR's branch
- Post summary comment
Key principles:
- YOU create the branch — use a meaningful name like
fix/review-{pr_number} - YOU gather and analyze — understand all feedback before delegating
- YOU NEVER implement fixes yourself — always delegate to agents
- Agents implement ALL fixes — they work in your branch and commit changes
- YOU create the PR — after all fixes are committed by agents
- YOU post the final summary — comprehensive results to GitHub
ghCLI is NOT available — usemcp__github__*tools exclusively
Workflow
Step 0: Create a Branch for This Work
CRITICAL: Do this FIRST before any other work!
The worktree starts in detached HEAD state. Create a branch first:
timestamp=$(date +%s)
branch_name="fix/review-${pr_number}-${timestamp}"
git checkout -b "$branch_name"
# Verify
current_branch=$(git branch --show-current)
echo "Created branch: $current_branch"
All agents you invoke will work in this same branch.
Step 1: Parse Arguments
Extract from $ARGUMENTS:
- Repository (owner/repo)
- PR number
Step 2: Fetch PR Metadata
Get the PR details to understand what we're working with:
mcp__github__pull_request_read(method="get", owner=<owner>, repo=<repo>, pull_number=<pr_number>)
From this response, extract:
head.ref— the PR's feature branch (this is the target for our fix PR)head.sha— the head commit SHAtitleandbody— PR description contextchanged_files— number of files changedadditions/deletions— size of changes
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 · 324 lines · 11 tokens per session scan A 3a835719f05c
fix-review is a command published in the GitHub repository GabsFranke/claude-code-github-agent (5 stars, last pushed 26d ago), licensed MIT. It adds 11 tokens to every session and 2,374 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).