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/metedata/remarc/overviewgit clone --depth 1 https://github.com/metedata/RemarcWhat 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 | $0.00024 | $0.00499 |
| Opus 5 | $0.00012 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
overview 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remarc hands your comments to AI coding agents over MCP (Model Context Protocol): leave comments as you review, then tell the agent to work through them. The agent reads each comment with its context (the quoted selection, source app, screenshot image paths, and web element details like CSS selectors and component file paths), moves it through the status lifecycle, and ends with a resolution summary you can read on the card.
Supported agents
Remarc connects to agents through three delivery models; each page below covers one setup path.
| Agent | Delivery | Setup |
|---|---|---|
| Claude Code | Plugin | Claude Code |
| Codex | Plugin | Codex |
| OMP | Plugin | OMP |
| Cursor | App-managed | Cursor |
| Claude Desktop | Manual config | Claude Desktop & MCP clients |
| Any MCP client | Manual config | Claude Desktop & MCP clients |
Claude Code, Codex, and OMP install plugins from Remarc's public agent integrations repository. The app configures Cursor itself, driven by an Enable toggle. Claude Desktop and other MCP clients (OpenCode, Continue, Windsurf, and anything that takes JSON config) use copyable snippets from Settings > MCP Integrations.
Whatever the path, every connected agent gets the same seven tools; the MCP tools reference lists them. Tools that do not speak MCP can still receive comments through webhooks.
Sessions and connection status
Comments live in sessions, and sessions can pair with agent conversations. Sessions created by an agent carry its origin badge (Claude Code, Codex, or OMP) so you can tell who created what.
The popover footer has an MCP button with a status dot: green when connected, orange when a dependency is missing, red when not connected. Click it for details and a copyable sample prompt.
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 · 30 lines · 24 tokens per session scan A e32a0d90d56d
overview is an agent published in the GitHub repository metedata/Remarc (66 stars, last pushed 11d ago), licensed MIT. It adds 24 tokens to every session and 499 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 2026-08-30.
Other agents, from other repositories
swift-mcp-expert
Expert assistance for building MCP servers in Swift with the FastMCP library. Use proactively when authoring @Tool / @MCPResource / @MCPPrompt types, configuring the FastMCP builder, defining @Generable schemas, or debugging FastMCP server issues.
tooling-runner
Haiku runner for TMDb build/test commands — executes exactly one make target (or its xcode-tools MCP equivalent), writes the full output to a .build/last-.log file, and returns only a concise pass/fail + failures-as-file:line summary. Spawned by the /build, /build-for-testing, /test, and /integration-test skills; not…
task-agents
The primary agent workflow — inference setup resolution, the automation switch, evidence-first execution, tool policy, and the proposal/confirmation loop.
Native SwiftUI Builder
Builds complex custom SwiftUI views using standard SwiftUI components with TTBaseUIKit design tokens (XView/XSize/XFont). Does NOT use TTBaseSUI wrapper components.
kmp-architect
KMP architecture expert. Designs shared module structures, expect/actual patterns, navigation, and DI for Kotlin Multiplatform projects.
ios-reviewer
Expert iOS code reviewer. Reviews Swift code for quality, SwiftUI patterns, Combine/concurrency usage, and Apple best practices. Use PROACTIVELY after writing iOS code. MUST BE USED for all iOS changes.