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 skills add muanlin/agent-collaboration-orchestrator --skill trae-codex-workspacegit clone --depth 1 https://github.com/muanlin/agent-collaboration-orchestratorWrote 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.
[](https://agentmods.dev/skills/muanlin/agent-collaboration-orchestrator/trae-codex-workspace)<a href="https://agentmods.dev/skills/muanlin/agent-collaboration-orchestrator/trae-codex-workspace"><img src="https://agentmods.dev/badge/skills/muanlin/agent-collaboration-orchestrator/trae-codex-workspace/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.
<a href="https://agentmods.dev/skills/muanlin/agent-collaboration-orchestrator/trae-codex-workspace"><img src="https://agentmods.dev/badge/skills/muanlin/agent-collaboration-orchestrator/trae-codex-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00102 | $0.02138 |
| Opus 5 | $0.00051 | $0.01069 |
| Sonnet 5 | $0.00020 | $0.00428 |
| Haiku 4.5 | $0.00010 | $0.00214 |
Grade A, and why
trae-codex-workspace 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 8d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TRAE Codex Workspace
Use this skill inside TRAE. TRAE is the primary operator. Codex is the delegated executor for difficult coding subtasks through the MCP bridge.
Workspace Rule
Recommend creating one shared workspace before starting collaboration:
codex_trae_workspace/
project-a/
project-b/
agent-collaboration-orchestrator/
Keep collaborative development projects inside codex_trae_workspace. When calling MCP tools, set projectRoot to the specific project directory, not the workspace root, unless creating a brand-new project.
Cross-Device Rule
TRAE desktop and mobile can both operate this workflow:
- Mobile can start a project or submit a task.
- Mobile can view a compact dashboard with
get_mobile_dashboard. - Mobile can check progress with
get_task_status. - Mobile can inspect logs with
get_task_log. - Mobile can adjust direction with
request_revision. - Mobile can stop work with
cancel_task. - Mobile can review generated files with
list_artifacts. - Mobile can review bridge-generated permission requests with
list_permission_requestsand approve/reject them withresolve_permission_request. - Desktop is preferred for detailed diff review, local testing, and resolving conflicts.
Always keep task titles clear so mobile task lists are readable.
Core Workflow
- Read the user request and identify the project directory in
codex_trae_workspace. - If the project does not exist, create or ask to create a new project folder under
codex_trae_workspace. - TRAE performs the first rough pass:
- scan project structure
- identify stack and conventions
- produce implementation plan
- split simple work and difficult work
- TRAE completes simple work directly.
- TRAE delegates difficult work with
submit_task. - Track progress with
get_mobile_dashboardorget_task_status. - Inspect executor details with
get_task_log. - View prompt/report/generated artifacts with
list_artifactsandget_result_report. - Adjust work with
request_revisionwhen requirements change or Codex output is incomplete. - Stop work with
cancel_taskwhen the user cancels or the delegated scope is wrong. - If Codex failed due to permission or sandbox restrictions, use
list_permission_requestsand ask the user whether to approve a retry.
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.
- 8d ago First seen · 296 lines · 102 tokens per session scan A e5845a024807
trae-codex-workspace is a skill published in the GitHub repository muanlin/agent-collaboration-orchestrator (0 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 2,138 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.