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/kamiazya/scopes/code-rabbitgit clone --depth 1 https://github.com/kamiazya/scopesWhat 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 | $0.00000 | $0.00755 |
| Opus 5 | $0.00000 | $0.00378 |
| Sonnet 5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
code-rabbit 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 yesterday.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeRabbit Review Handler
Process CodeRabbit review comments with context-aware discretion.
Usage
/code-rabbit
Then paste one or more CodeRabbit comments.
Instructions
1. Initial Context
Inform the user:
I'll review the CodeRabbit comments with discretion, as CodeRabbit doesn't have access to the entire codebase and may not understand the full context.
For each comment, I'll:
- Evaluate if it's valid given our codebase context
- Accept suggestions that improve code quality
- Ignore suggestions that don't apply to our architecture
- Explain my reasoning for accept/ignore decisions
2. Process Comments
Single File Comments
If all comments relate to one file:
- Read the file for context
- Evaluate each suggestion
- Apply accepted changes in batch using MultiEdit
- Report which suggestions were accepted/ignored and why
Multiple File Comments
If comments span multiple files:
Launch parallel sub-agents using Task tool:
Task:
description: "CodeRabbit fixes for {filename}"
subagent_type: "general-purpose"
prompt: |
Review and apply CodeRabbit suggestions for {filename}.
Comments to evaluate:
{relevant_comments_for_this_file}
Instructions:
1. Read the file to understand context
2. For each suggestion:
- Evaluate validity given codebase patterns
- Accept if it improves quality/correctness
- Ignore if not applicable
3. Apply accepted changes using Edit/MultiEdit
4. Return summary:
- Accepted: {list with reasons}
- Ignored: {list with reasons}
- Changes made: {brief description}
Use discretion - CodeRabbit lacks full context.
3. Consolidate Results
After all sub-agents complete:
📋 CodeRabbit Review Summary
Files Processed: {count}
Accepted Suggestions:
{file}: {changes_made}
Ignored Suggestions:
{file}: {reason_ignored}
Overall: {X}/{Y} suggestions applied
4. Common Patterns to Ignore
- Style preferences that conflict with project conventions
- Generic best practices that don't apply to our specific use case
- Performance optimizations for code that isn't performance-critical
- Accessibility suggestions for internal tools
- Security warnings for already-validated patterns
- Import reorganization that would break our structure
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.
- yesterday First seen · 121 lines · 0 tokens per session scan A f21bfc73b0a5
code-rabbit is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 755 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 2026-08-31.
Other commands, from other repositories
review.v1
Review code changes: /review [commit|branch|PR].
diagnose-deeptrace
Run a ZDX deep trace diagnostics session — start, analyze, or clean up deep traces for a user's device.
troubleshoot-user
Cross-product troubleshooting of user connectivity across ZCC, ZDX, ZPA, and ZIA.
audit-ssl
Audit ZIA SSL inspection rules -- list rules by action (INSPECT, DONOTINSPECT, DONOTDECRYPT, BLOCK), identify bypasses, and assess risk.
create-access-rule
Create a ZPA access policy rule with v2 conditions for application access control.
investigate-incident
Investigate security incidents using Z-Insights analytics -- threats, firewall actions, shadow IT, and web traffic.