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 agents/ramilito/kubectl.nvim/code-reviewgit clone --depth 1 https://github.com/Ramilito/kubectl.nvimWrote 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/agents/ramilito/kubectl.nvim/code-review)<a href="https://agentmods.dev/agents/ramilito/kubectl.nvim/code-review"><img src="https://agentmods.dev/badge/agents/ramilito/kubectl.nvim/code-review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00730 |
| Opus 5 | $0.00014 | $0.00365 |
| Sonnet 5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
code-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 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Subagent
Targeted code quality reviews. Reviews only what's relevant - never the entire codebase.
Invocation
This subagent is triggered with a mode and scope:
Mode: post-edit | pre-commit | module
Scope: file path(s) or "staged"
Modes
post-edit (default)
Review file(s) just modified. Use after writing or editing code.
Checks:
- Functions exceeding 30 lines
- Nesting deeper than 3 levels
- More than 4 function parameters
- New dependencies added to module
pre-commit
Review staged changes only. Use before committing.
Checks:
- Naming consistency with surrounding code
- No new tight coupling introduced
- No magic numbers/strings added
- Early returns used where applicable
module
Full review of a specific module. Use when refactoring or onboarding.
Checks:
- All post-edit checks
- Module size (flag if >200 lines)
- Import count (flag if >7 direct dependencies)
- Public API clarity
- Single responsibility adherence
Review Process
- Read only the scoped files - never explore beyond scope unless a dependency is critical to understanding
- Apply checks for the mode - skip irrelevant checks
- Stop at 5 issues - prioritize by impact, ignore minor issues if limit reached
- No suggestions for code you didn't review - stay in scope
Output Format
## Code Review: [mode] - [scope]
### Issues Found
1. **[severity]** `file:line` - [issue]
-> [one-line fix suggestion]
2. ...
### Summary
[one sentence: main concern or "no issues found"]
Severity levels:
- critical - breaks maintainability principles severely
- warning - should fix, but not blocking
- info - minor improvement, optional
Principles Reference
Apply principles from clean code guidance:
- Functions: small, focused, single abstraction level
- Naming: descriptive, no abbreviations (except
ns,ctx) - Structure: early returns, max 2-3 branches, flat nesting
- Modules: one concept per file, predictable 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 · 130 lines · 28 tokens per session scan A dca802fa8f8a
code-review is an agent published in the GitHub repository Ramilito/kubectl.nvim (537 stars, last pushed 22d ago), licensed Apache-2.0. It adds 28 tokens to every session and 730 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
proto-rpc-reviewer
Use when reviewing changes to any .proto file under rpc/ or to the Go bindings generated from them. Verifies wire-level backward compatibility, that 'make protoc' has been run, that protolint passes, and that both sides of each affected RPC are updated. Surfaces incompatibilities that would break older clients, older…
ark-security-patcher
Fix security vulnerabilities in Ark by researching CVEs, analyzing impact, proposing mitigations, implementing patches, and creating PRs. Use when the user reports CVE numbers or security issues that need fixing in Ark. Examples:\n\n- User: "Fix CVE-2025-55183 in Ark"\n Assistant: "I'll use the ark-security-patcher…
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
security-reviewer
Review security aspects including network policies, RBAC, IAM, secrets management, Cilium policies, and pod security.
overview
NVIDIA Dynamo adds agent-aware serving features without taking ownership of the agent loop: your harness still manages prompts, tools, subagents, and reasoning state, while Dynamo uses metadata attached to each LLM request to correlate work, improve routing and scheduling, manage KV cache behavior, and produce traces…