An installation guide for connecting Remarc, a tool that reads coding-session comments, to Codex through a plugin. It covers installing, checking, and manually removing that connection.

Use it when installing or repairing the Remarc plugin for Codex, verifying it with a test session lookup, or finding old Remarc settings in Codex configuration.

It helps set up the integration and identify older configuration that may remain from previous versions.

codex — Agent by metedata

Install

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.

agentmods

npx agentmods add agents/metedata/remarc/codex

Clone the repo

git clone --depth 1 https://github.com/metedata/Remarc

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 410 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00027	$0.00410
Opus 5	$0.00014	$0.00205
Sonnet 5	$0.00005	$0.00082
Haiku 4.5	$0.00003	$0.00041

Measured 2d ago against content hash 26e08b27b059, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

If you used Remarc with Codex before the plugin existed, older builds wrote an `[mcp_servers.remarc]` table into `~/.codex/config.toml`. Remove that table by hand; the plugin replaces it.

docs-site/src/content/docs/agents/codex.md · 33 lines

What it actually says

Codex reads Remarc comments through a plugin installed from the public Remarc agent integrations repository. The plugin gives Codex the same MCP (Model Context Protocol) tools and skill as every other agent; the MCP tools reference lists them.

Install the plugin

Open Settings > MCP Integrations > Codex and click Install. The button reads Repair when the plugin is already installed but needs fixing. The row shows the exact CLI commands it runs, with a copy button. To run them yourself:

codex plugin marketplace add metedata/remarc-agent-plugins
codex plugin marketplace upgrade remarc
codex plugin add remarc@remarc

If the Codex CLI is not installed, the Install button says so; install Codex first or run the commands in a terminal.

To verify the install, ask Codex to call remarc_list_sessions. If your sessions come back, the plugin is working.

Remove the plugin

The Codex integration is install-only: Remarc never removes anything from your Codex configuration. To get rid of the plugin, remove it in Codex yourself.

:::caution If you used Remarc with Codex before the plugin existed, older builds wrote an [mcp_servers.remarc] table into ~/.codex/config.toml. Remove that table by hand; the plugin replaces it. :::

Comment delivery

Comments filed to a Codex session arrive when the agent next reads them; Codex sessions cannot be woken instantly the way Claude Code sessions can. Sessions created by Codex carry a Codex origin badge in the session picker.

Changes

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 · 33 lines · 27 tokens per session scan B 26e08b27b059

Subscribe to this mod's changes

codex is an agent published in the GitHub repository metedata/Remarc (66 stars, last pushed 11d ago), licensed MIT. It adds 27 tokens to every session and 410 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Testing Writing and docs ai-agents developer-tools macos model-context-protocol screen-annotation swift

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.

mehmetbaykar/swift-fast-mcp · 69 tokens

agentsb-roadmap

AgentSB is the repo-local maintenance agent app for SwiftASB. Its job is to help maintainers keep Codex CLI schema review, SwiftASB public API boundaries, docs, probes, and routine repo upkeep moving without turning uncertain upstream changes into silent source edits.

gaelic-ghost/SwiftASB · 0 tokens

codex-direct-read-plan

AgentSB may use direct local Codex reads as an experimental maintainer lane for faster reports and for prototyping the future SwiftASB direct-thread-storage feature. This lane is private, read-only by default, and version-gated. The destination feature is tracked in ../maintainers/codex-direct-thread-storage-plan.md.