Coding-agent integration guide

Codex, Claude Code, and OpenClaw integrations.

CortexPilot already fits into modern coding-agent workflows, but the truthful entrypoint is not “install our official plugin.” The truthful story today is: read-only MCP, repo-owned skills, API/client entrypoints, and Workflow Cases + Proof & Replay as the common operating record.

Use this page when you want the shortest honest answer to: “How do I actually use CortexPilot with Codex, Claude Code, or OpenClaw right now?”

The safe product positioning is workflow-aligned and read-only MCP-compatible. It is not an official OpenAI or Anthropic plugin surface. Keep plugin wording narrow: for CortexPilot, the default public story is still integrations + skills + MCP; for OpenClaw, plugin-ready wording only becomes safe when a real package or native manifest path is shipped and verified.

Open read-only MCP quickstart Open compatibility matrix Open builder quickstart Open skills quickstart Open repository README

Need the fastest proof-first walkthrough instead of the deeper integration map? Open use-case guide.

The shortest truthful compatibility map

Surface	Works today	How CortexPilot fits	What we must not claim
Codex	Yes	Command Tower, Workflow Cases, Proof & Replay, read-only MCP, repo-owned skills, and API/client entrypoints all fit Codex-style governed coding loops.	Do not call CortexPilot an official Codex plugin or an OpenAI-managed integration surface.
Claude Code	Yes	The same repo-owned surfaces work for Claude Code workflows: read-only inspection, case tracking, operator guidance, and package-level builder glue.	Do not imply an official Claude Code plugin, Anthropic-managed partnership, or hosted account integration.
OpenClaw	Bundle-compatible only when explicitly mapped	OpenClaw belongs in the adjacent coding-agent layer. CortexPilot can still provide read-only MCP, skill-pack guidance, and proof/case review surfaces around it without pretending the same first-class binding as Codex / Claude Code.	Do not present OpenClaw support as an official plugin, native OpenClaw plugin, or first-class product binding unless a real mapped bundle or native plugin ships and is tested.

What teams can actually adopt today

Command Tower as the single operator surface above coding-agent runs
Workflow Cases as the shared operating record that ties request, queue, verdict, and linked runs together
Proof & Replay as the review surface you use before trusting an outcome
read-only MCP when you want machine-readable inspection without mutation
frontend client + contract + shared UI substrate when you want repo-owned builder entrypoints
repo-local skills when you want coding agents to use the same operating playbook

Three copy-paste starting points

If your team wants something more concrete than “read the docs,” start with one of these repo-owned paths.

# 1) protocol-first: prove the read-only MCP surface is real
PYTHONPATH=apps/orchestrator/src python3 -m cortexpilot_orch.cli mcp-readonly-server

# 2) builder-first: prove the thin client + contract bootstrap path is real
node packages/frontend-api-client/examples/control_plane_starter.local.mjs \
  --base-url http://127.0.0.1:10000 \
  --role WORKER \
  --mutation-role TECH_LEAD \
  --preview-provider cliproxyapi \
  --preview-model gpt-5.4

# 3) proof-first: prove the public first-run loop is real
CORTEXPILOT_HOST_COMPAT=1 bash scripts/test_quick.sh --no-related

How to talk about this truthfully

Good wording

“CortexPilot works with Codex and Claude Code workflows through Workflow Cases, Proof & Replay, read-only MCP, repo-owned skills, and builder entrypoints.”

Bad wording

“CortexPilot already ships an official Codex / Claude Code / OpenClaw plugin.”

Good wording

“OpenClaw stays in the adjacent coding-agent layer and can use CortexPilot as a bundle-compatible review surface when the mapped path is explicitly shipped and tested.”

Bad wording

“OpenClaw is a first-class officially supported plugin surface inside CortexPilot today.”

FAQ

Is this an official Codex or Claude Code plugin page?

No. The truthful story today is workflow compatibility through Workflow Cases, Proof & Replay, read-only MCP, repo-owned skills, and builder entrypoints.

Where does OpenClaw fit today?

OpenClaw stays in the adjacent coding-agent layer. CortexPilot can still provide read-only MCP, proof and replay, and skill-pack guidance around it without claiming a first-class native plugin.

Should a new team start from MCP, builders, or skills?

Start from read-only MCP when the first need is protocol inspection, from builders or API when the first need is package-level integration, and from skills when the first need is repeatable operating playbooks.

Does this page mean CortexPilot is hosted or write-capable through MCP?

No. The current public MCP contract is read-only, and CortexPilot should not be described as a hosted operator product today.