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 skills/alchemiststudiosdotai/coderabbit-fix-flow-plugin/coderabbit-fix-flownpx skills add alchemiststudiosDOTai/coderabbit-fix-flow-plugin --skill coderabbit-fix-flowgit clone --depth 1 https://github.com/alchemiststudiosDOTai/coderabbit-fix-flow-pluginWhat 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 | $0.00054 | $0.00963 |
| Opus 5 | $0.00027 | $0.00481 |
| Sonnet 5 | $0.00011 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
coderabbit-fix-flow 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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeRabbit Fix Flow
Overview
This skill automates the workflow of processing CodeRabbit code review feedback by saving the review output to a timestamped document, then using MCP tools (sequential thinking and Exa context) to analyze and implement fixes with minimal code changes.
When to Use
Use this skill immediately after running coderabbit --plain or when you have CodeRabbit feedback that needs systematic processing. The skill handles type safety issues, code style violations, and other CodeRabbit-identified problems.
Workflow
Step 1: Execute CodeRabbit Review
Run the CodeRabbit review command in plain text mode:
coderabbit --plain
Step 2: Save Feedback Document
Save the CodeRabbit output to a timestamped QA document:
- Create file:
memory-bank/qa/coderabbit/cr-qa-{timestamp}.md - Include the full CodeRabbit output in the document
- Add YAML front matter with metadata:
--- title: "CodeRabbit QA Review - {timestamp}" link: "cr-qa-{timestamp}" type: "qa" tags: - code-review - coderabbit - type-safety created_at: "{timestamp}" updated_at: "{timestamp}" uuid: "{generate-uuid}" ---
Step 3: Analyze Issues with Sequential Thinking
Use the sequential thinking MCP tool to analyze all identified issues:
- Categorize issues by type (type safety, performance, style, security)
- Prioritize fixes (critical runtime issues first, then documentation)
- Plan minimal changes to achieve the fixes
- Identify dependencies between issues
Step 4: Get Best Practices Context
Use the Exa code context MCP tool to research current best practices for each issue type:
- For type issues: "TypeScript type guards runtime validation best practices"
- For Python type issues: "Python type annotations Optional None best practices"
- For performance: "Performance optimization best practices [language]"
- For security: "Security vulnerability fixes [language]"
Step 5: Implement Fixes Systematically
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.
- 2d ago First seen · 143 lines · 54 tokens per session scan A 72f0e25e9827
coderabbit-fix-flow is a skill published in the GitHub repository alchemiststudiosDOTai/coderabbit-fix-flow-plugin (4 stars, last pushed 10mo ago), licensed MIT. It adds 54 tokens to every session and 963 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…