What is traecnclaw-mcp?

A focused set of MCP tools for controlling TraeCN through its standard input/output connection. TraeCN is the external workspace and agent interface these tools operate.

Sending or stopping work, selecting a workspace, model, mode, or conversation, inspecting or changing Trae settings, managing conversations, and handling exceptional questions or approval requests.

It organizes common TraeCN actions and leaves queueing, waiting, recovery, and related process handling to the gateway.

How Luckycat133/traecnclaw-mcp-skill configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Luckycat133/traecnclaw-mcp-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Luckycat133/traecnclaw-mcp-skill/main/.codex/skills/traecnclaw-mcp/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Luckycat133/traecnclaw-mcp-skill

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/luckycat133/traecnclaw-mcp-skill/traecnclaw-mcp/github.svg)](https://agentmods.dev/skills/luckycat133/traecnclaw-mcp-skill/traecnclaw-mcp)

Your own site

<a href="https://agentmods.dev/skills/luckycat133/traecnclaw-mcp-skill/traecnclaw-mcp"><img src="https://agentmods.dev/badge/skills/luckycat133/traecnclaw-mcp-skill/traecnclaw-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/luckycat133/traecnclaw-mcp-skill/traecnclaw-mcp"><img src="https://agentmods.dev/badge/skills/luckycat133/traecnclaw-mcp-skill/traecnclaw-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00091	$0.01590
Opus 5.5	$0.00036	$0.00636
Sonnet 5.5	$0.00018	$0.00318
Haiku 4.5	$0.00009	$0.00159

Measured 1mo ago against content hash 03cf64671a91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

traecnclaw-mcp 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 1mo ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/mcp-stdio-smoke.test.js, scripts/setup-mcp.js, scripts/setup-mcp.test.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.codex/skills/traecnclaw-mcp/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TRAECNclaw MCP

Compose focused tools around user intent. Do not call preflight, wait, poll, event acknowledgement, recovery, cleanup, proof, process, or generic command operations from the agent loop; the gateway owns those mechanics.

Setup

Install the matching TRAECNclaw server from its source checkout or release server archive. The launcher checks the repository, an installed traecnclaw package, then traecnclaw-mcp on PATH; it never executes a JavaScript path selected by an environment variable.
Run npm run doctor in a source checkout. Then run npm run --silent setup:mcp from the checkout, or node scripts/setup-mcp.js from this Skill directory, to validate the server and print a resolved client entry. Use --output FILE to create a new mode-0600 file atomically; the command never overwrites an existing file. The JSON templates under assets remain manual fallbacks.
Start the gateway with npm run start:gateway, then reconnect the MCP client.
Use mock mode only for development; never cite mock output as live TraeCN evidence.

Choose only necessary context

Call traecn_open_workspace only when the requested folder is not already open.
Call traecn_list_models when the available choices matter; then call traecn_select_model once.
Call traecn_select_mode only when the task requires a different Solo/IDE mode.
Call traecn_list_conversations to read the current mode and stable conversation IDs.
Use traecn_create_conversation, traecn_select_conversation, or traecn_delete_conversation for exactly one conversation operation.

These tools change TraeCN context. Never repeat workspace paths in the model message.

Send and track work

Call traecn_send_message with the exact message and, when concurrency makes the target ambiguous, an explicit conversationId. Clients without the Tasks extension receive the accepted taskId and status. When the host declares io.modelcontextprotocol/tasks on the request, the same call returns that durable gateway identity as resultType: "task".

Read the full file on GitHub · 131 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 131 lines · 91 tokens per session scan A 03cf64671a91

Subscribe to this mod's changes

traecnclaw-mcp is a skill published in the GitHub repository Luckycat133/traecnclaw-mcp-skill (0 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 1,590 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.

Building agents agent mcp npm skill trae

edgeone skill scanner

A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.

Tencent/AI-Infra-Guard · 148 tokens

babysit

Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.

kirodotdev/KiroCrew · 45 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

project-wiki

A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.

GeminiLight/MindOS · 63 tokens

mindos-zh

A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.

GeminiLight/MindOS · 490 tokens

mindos

MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…

GeminiLight/MindOS · 136 tokens

traecnclaw-mcp-skill: Skill for Codex