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/claude-codegit 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 | $0.00817 |
| Opus 5 | $0.00012 | $0.00409 |
| Sonnet 5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
claude-code 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code connects to Remarc through two plugins from the public Remarc agent integrations repository: remarc (required, the MCP server and skill) and remarc-hooks (optional, links conversations to Remarc sessions).
Install the remarc plugin
Three ways, all equivalent:
- During onboarding: click Install on the Claude Code plugin row. The row is optional; you can finish setup without it.
- From Settings: open Settings > MCP Integrations > Claude Code and click Install. The row shows the exact CLI commands it runs, with a copy button.
- Manually: run the same commands yourself:
claude plugin marketplace add metedata/remarc-agent-plugins
claude plugin install remarc@remarc
The first install clones the marketplace and can take a minute. If Remarc reports the plugin installed but disabled, run /plugin inside Claude Code to enable it.
If you upgraded from an older Remarc that configured Claude Code without plugins, the app removes the legacy skill file, hooks, and MCP registration on launch, with nothing for you to do.
Keep the plugin updated
Claude Code doesn't update remarc automatically by default, because it comes from a self-hosted marketplace rather than an official one. Update it on demand, or turn on automatic updates once.
Update on demand:
claude plugin update remarc@remarc
If that reports the plugin is already current but you expected a newer version, refresh the marketplace first, then update again:
claude plugin marketplace update remarc
To update automatically, turn it on once and Claude Code refreshes the plugin in the background shortly after each session starts:
- Run
/plugininside Claude Code. - Open the Marketplaces tab.
- Select remarc.
- Choose Enable auto-update.
The MCP server and the skill ship in the same plugin, so a single update refreshes both. After an update lands, run /reload-plugins to pick it up in the current session, or it loads the next time you start Claude Code.
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 · 74 lines · 24 tokens per session scan A bb4da26912fb
claude-code is an agent published in the GitHub repository metedata/Remarc (66 stars, last pushed 10d ago), licensed MIT. It adds 24 tokens to every session and 817 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.