nanocoai/nanoclaw / .claude/skills/add-codex
add-codex
FlaggedUse Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
payload/container/agent-runner/src/provider-contracts/codex.ts
View on GitHubimport {
codexExecutionPolicySection,
codexInferenceSection,
codexMcpServersSection,
codexMemorySection,
codexRuntimeOwnership,
codexTone,
type CodexMemorySessionHook,
writeCodexConfigToml,
} from '../providers/codex-app-server.js';
import { registerProviderContract } from '../providers/provider-registry.js';
import { archiveProviderExchange } from './exchange-archive.js';
import {
type ProviderRuntimeContract,
type RuntimeAfterExchangeInput,
type RuntimeCallbackEffects,
type RuntimeConfigurationInputs,
} from './registry.js';
const provider = 'codex';
// Pinned literal, not the core's constant: a core seam bump must fail this
// payload's version check until the payload is refreshed to match.
const RUNTIME_SEAM_VERSION = 1;
// This module loading means core runs the contract's beforeQuery before every
// query, so the provider's own direct write must stand down — otherwise the
// files would be written twice per query.
codexRuntimeOwnership.contractOwnsRuntimeFiles = true;
// Keep the payload compatible with cores that predate the optional tone field.
export const codexRuntimeContract: ProviderRuntimeContract & {
configuration: { tone: typeof codexTone };
} = {
seamVersion: RUNTIME_SEAM_VERSION,
configuration: {
executionPolicy: { constant: codexExecutionPolicySection() },
inference: codexInferenceSection,
tone: codexTone,
// Codex's native memory stays off whatever hook core registers, so the
// section is a declared constant, not a function of the hook.
memory: { constant: codexMemorySection() },
mcpServers: codexMcpServersSection,
},
lifecycle: { beforeQuery: writeCodexRuntimeFiles },
history: { afterExchange: archiveCodexExchange },
textDelivery: 'result',
commands: { formatting: 'xml' },
};
// Two-step registration: providers/codex.ts registered the factory; this
// attaches the contract. Order-independent, and neither file imports the other.
registerProviderContract(provider, codexRuntimeContract);
function writeCodexRuntimeFiles(inputs: Partial<RuntimeConfigurationInputs>): void {
const hook = inputs.memory as CodexMemorySessionHook | undefined;
if (!hook) throw new Error('Codex provider requires a registered memory hook before query');
writeCodexConfigToml(inputs.mcpServers ?? {}, hook, codexInferenceSection(inputs.inference ?? {}));
}
function archiveCodexExchange({ exchange }: RuntimeAfterExchangeInput, fx: RuntimeCallbackEffects): string | null {
return archiveProviderExchange({
provider,
prompt: exchange.prompt,
result: exchange.result,
continuation: exchange.continuation,
status: exchange.status,
timestamp: new Date(fx.now()),
});
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |