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/kenn-io/roborev/indexgit clone --depth 1 https://github.com/kenn-io/roborevWhat 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 | $0.00007 | $0.04339 |
| Opus 5 | $0.00003 | $0.02169 |
| Sonnet 5 | $0.00001 | $0.00868 |
| Haiku 4.5 | $0.00001 | $0.00434 |
Grade C, and why
index scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| Gemini | `agy` or `gemini` | `curl -fsSL https://antigravity.google/cli/install.sh \| bash` (preferred) or `npm install -g @google/gemini-cli` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Gemini | `agy` or `gemini` | `curl -fsSL https://antigravity.google/cli/install.sh \| bash` (preferred) or `npm install -g @google/gemini-cli` | How it starts
The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roborev supports multiple AI coding agents and auto-detects which ones are installed.
Supported Agents
| Agent | CLI Command | Install |
|---|---|---|
| Codex | codex |
npm install -g @openai/codex |
| Claude Code | claude |
npm install -g @anthropic-ai/claude-code |
| Gemini | agy or gemini |
curl -fsSL https://antigravity.google/cli/install.sh | bash (preferred) or npm install -g @google/gemini-cli |
| Copilot | copilot |
npm install -g @github/copilot |
| Cursor | agent |
See cursor.com/cli |
| OpenCode | opencode |
npm install -g opencode-ai@latest (anomalyco/opencode) |
| Droid | droid |
See factory.ai |
| Kilo | kilo |
npm install -g @kilocode/cli |
| Kiro | kiro-cli |
See kiro.dev |
| Pi | pi |
npm install -g @mariozechner/pi-coding-agent |
| Grok Build | grok |
curl -fsSL https://x.ai/cli/install.sh | bash (x.ai/cli) |
Auto-Detection
roborev auto-detects installed agents and falls back in this order:
- Codex
- Claude Code
- Gemini
- Copilot
- OpenCode
- Cursor
- Kiro
- Kilo
- Droid
- Pi
- Grok Build
The first available agent is used unless you specify one explicitly.
Specifying an Agent
Per-Command
roborev review --agent claude-code <sha>
roborev run --agent codex "Explain this code"
roborev refine --agent gemini
Per-Repository
# .roborev.toml
agent = "claude-code"
Global Default
# ~/.roborev/config.toml
default_agent = "codex"
Model Selection
You can override the default model for any agent using the --model / -m
flag:
roborev review --model gpt-4.1 <sha>
roborev refine --model claude-sonnet-4-20250514
Model Format by Agent
| Agent | Model Format | Example |
|---|---|---|
| Codex | OpenAI model name | gpt-4.1, o3-mini |
| Claude Code | Anthropic model name | claude-sonnet-4-20250514, claude-opus-4-20250514 |
| Gemini | Google model name | gemini-2.5-pro, gemini-2.5-flash |
| Copilot | OpenAI model name | gpt-4.1 |
| Cursor | Model name | claude-sonnet-4-20250514, gpt-4.1 |
| OpenCode | provider/model |
anthropic/claude-sonnet-4-20250514, openai/gpt-4.1 |
| Droid | Factory model name | (see Factory.ai docs) |
| Kilo | provider/model |
anthropic/claude-sonnet-4-20250514, openai/gpt-4.1 |
| Kiro | Model name | (see Kiro docs) |
| Pi | Model name | claude-sonnet-4-20250514, gpt-4.1 |
| Grok Build | xAI model ID | grok-4.5 (see x.ai/cli) |
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 · 431 lines · 7 tokens per session scan C d66c55efbfc2
index is an agent published in the GitHub repository kenn-io/roborev (1,685 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 4,339 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
kimi
Kimi CLI is Moonshot's coding agent. In CCR it is CLI only and always uses Only opened from CCR.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…