codex-update-compat

A Codex workflow for upgrading Codex in a repository and fixing compatibility problems caused by changes to its app-server interface. It covers source code, generated TypeScript types, event handling, and tests.

In plain words
What is it for?
Use it when updating versions, regenerating app-server types, repairing event mappings, and updating fixtures or snapshots.
Why use it?
It gives a structured way to address errors and changed behavior after updating Codex or its npm packages.

Skill for Claude CodeCodex

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 skills/agentprism/agentprism-workflows/codex-update-compat
Any agent
npx skills add agentprism/agentprism-workflows --skill codex-update-compat
Clone the repo
git clone --depth 1 https://github.com/agentprism/agentprism-workflows

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00086 $0.00556
Opus 5 $0.00043 $0.00278
Sonnet 5 $0.00017 $0.00111
Haiku 4.5 $0.00009 $0.00056

Measured 2d ago against content hash 96fec49880bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-update-compat 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 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.

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.

packages/codex-acp/.agents/skills/codex-update-compat/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Update Compat

Use this workflow to safely upgrade Codex and close update-induced regressions.

Workflow

  1. Inspect update scope before changing code. Run:
git log --oneline -n 5
git show --name-only --oneline -n 1

Focus first on package.json, package-lock.json, and generated src/app-server/** changes.

  1. Run typecheck and tests immediately. Run:
npm run typecheck
npm test

Treat type errors as the migration guide for required protocol changes.

  1. Fix runtime compatibility in source files. Typical hotspots:
  • src/CodexAcpClient.ts: thread start/resume params and initialize capabilities
  • src/AgentMode.ts: sandbox policy shape changes
  • src/CodexEventHandler.ts: new/changed server notifications
  • src/CodexAcpServer.ts: history replay for new ThreadItem variants
  • src/CodexToolCallMapper.ts: mapping new tool-like items to ACP events
  1. Fix test fixtures and snapshots. Update typed fixtures for new required fields instead of weakening types. Then update snapshots only after behavior is intentionally verified.

  2. Re-run targeted suites, then full checks. Run focused tests for touched behavior, then:

npm run typecheck
npm test

Non-Trivial Changes: Ask Before Finalizing

When migration requires behavior decisions (not only schema fixes), ask the user first. Examples:

  • Enabling/disabling experimental flags (persistExtendedHistory, experimentalApi)
  • User-visible messaging changes for new events (e.g., model reroute wording)
  • Converting integration tests to mocks or skipping env-dependent tests

Event Mapping Rule

Do not silently drop new event/item variants if they should be visible to users. Map them to ACP updates:

  • Tool-like operations -> tool_call / tool_call_update
  • Informational reasoning/infra events -> agent_thought_chunk (if user-meaningful)
  • Internal/noise events -> explicit no-op case (documented in switch)

References

For common break patterns and ready fixes, read:

  • references/codex-update-playbook.md

Read the full file on GitHub · 66 lines

Files

What ships with it

2 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.

  1. 2d ago First seen · 66 lines · 86 tokens per session scan A 96fec49880bc

Subscribe to this mod's changes

codex-update-compat is a skill published in the GitHub repository agentprism/agentprism-workflows (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 556 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

mcp-acp-bridge

Orchestrate multiple ACP agents (Gemini, Claude, etc.) using a stateful tool-based bridge. Use when you need to manage background generations, run agents in different directories, or track real-time tool logs across multiple connections.

theorionic/mcp-acp-bridge · 54 tokens

copilot-pr-review-loop

Drive a GitHub pull request through repeated rounds of Copilot code review until convergence. Use when the user asks to "request Copilot review", "run a Copilot review loop", iterate on Copilot feedback, or wants automated triage-and-respond on Copilot PR comments. Covers re-request mechanics, open-thread filtering…

microsoft/intelligent-terminal · 91 tokens

upstream-sync

Periodically sync new commits from microsoft/terminal into this manually-forked intelligent-terminal repo by cherry-picking commit-by-commit onto a dated sync branch, auto-skipping revert pairs and empty commits, auto-resolving known take-upstream files, and stopping cleanly on genuine conflicts. The agent (you…

microsoft/intelligent-terminal · 139 tokens

release-notes

Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…

microsoft/intelligent-terminal · 73 tokens

add-acp-agent-support

Add first-class support for an ACP-compatible agent CLI to Intelligent Terminal. Use when integrating a new built-in AI agent, ACP server command, authentication flow, model selection, interactive delegation, session hooks, onboarding, Settings, branding, GPO policy, documentation, tests, build, deployment, or live…

microsoft/intelligent-terminal · 72 tokens

opentag

Use when installing, pairing, operating, or troubleshooting OpenTag through the published CLI, self-hosted Control Plane, governed completion, supported collaboration platforms, or built-in coding agents.

amplifthq/opentag · 40 tokens