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 skills/metedata/remarc/skillnpx skills add metedata/Remarc --skill skillgit 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 | $0.00041 | $0.02529 |
| Opus 5 | $0.00020 | $0.01264 |
| Sonnet 5 | $0.00008 | $0.00506 |
| Haiku 4.5 | $0.00004 | $0.00253 |
Grade A, and why
remarc 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remarc Comments
Remarc comments are contextual feedback attached to a session. Infer the user's intent from the whole request, not from one exact verb. People may say "check", "review", "handle", "go through", "fix these", "take this", "what's left", "triage", or many other variants.
Default to an addressing workflow when the user asks you to take responsibility for the comments. Use a read-only workflow when the user asks only to inspect, list, summarize, count, audit, or recommend without changing the underlying artifact or comment statuses.
Session Lifecycle
Remarc sessions are containers for contextual feedback. They may be created by the user from the Remarc app, created by chat through MCP, or created by an installed integration. Do not assume the session's origin.
Use remarc_create_session only when the user asks to start a Remarc session
mid-conversation. Claude Code and Codex must provide their real agent session
ID; do not invent one. OMP may omit the legacy session ID because its trusted
MCP process records origin: "omp", then the user can run /remarc-pair to
enable instant delivery. For existing work in any harness, list sessions first
and reuse the match when appropriate.
There is no exposed MCP tool to stop, close, or delete a session. If the user asks to stop a session, explain that MCP cannot do that directly and point them to the Remarc app's session controls or their configured integration cleanup.
Choose a Mode
Before changing any status, decide which mode the user requested:
- Read-only: Inspect, list, count, summarize, audit, or recommend. Do not change statuses.
- Addressing: Take responsibility for comments, update the artifact or produce the requested response, and move comments through the status lifecycle.
- Status-only: Change Remarc statuses exactly as requested without doing additional artifact work.
If the request is ambiguous and status changes would surprise the user, ask a brief clarifying question. If the user has clearly handed you the comments to work through, use addressing mode.
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 · 236 lines · 41 tokens per session scan A 2285fd642762
remarc is a skill published in the GitHub repository metedata/Remarc (66 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 2,529 once invoked, about $0.0002 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 skills, from other repositories
swift-fast-mcp
Generate a complete MCP server project in Swift using the FastMCP library. Use when asked to create a Swift MCP server, build an MCP tool server, or scaffold a Model Context Protocol project in Swift.
release-peekaboo
Peekaboo release: notarization, npm/GitHub release, appcast, verify, closeout.
scarf-template-author
Scaffold a new Scarf project OR enrich an existing one after a Scarf "Upgrade Project" — dashboard, optional configuration schema, optional cron job, AGENTS.md, and (via the scarf-miniapp-author skill) a starter mini-app — from a short conversational interview. Output is immediately usable locally and cleanly…
awesome-swift-macos-apps-docs
Use when adding, updating, or validating app entries in the awesome-swift-macos-apps repository, especially when maintaining both README.md and README.zh.md with concise one-sentence descriptions, correct category placement, and consistent bilingual formatting.
homekit
Control HomeKit smart home accessories and view home events via homeclaw-cli. Use when the user asks to control lights, locks, thermostats, fans, blinds, scenes, check device/sensor status, or view recent home activity/events. Examples: "turn off the stairs lights", "lock the front door", "what's the temperature"…
homeclaw
Control HomeKit smart home accessories via HomeClaw MCP tools. Also includes reference data for accessory categories, characteristics, and value formats. This skill should be used when the user wants to: Turn lights on or off, set brightness, or change color temperature Lock or unlock doors Set thermostat temperature…