agentmods.dev

codex-update

A command that installs or updates a specific tagged version of the upstream OpenAI Codex plugin for Claude Code.

In plain words
What is it for?
Use it to install a pinned release, choose an installation directory, update the recorded hash, or output installation details as JSON.
Why use it?
It checks the downloaded files against a SHA-256 fingerprint and installs them atomically, reducing the risk of using altered files or a partial update.

Command

4 4mo ago A scan 17 tokens original Apache-2.0
View the source file dysfunc/ai-plugins-cc
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 commands/dysfunc/ai-plugins-cc/codex-update
Clone the repo
git clone --depth 1 https://github.com/dysfunc/ai-plugins-cc
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 380 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 $0.00017 $0.00380
Opus 5 $0.00009 $0.00190
Sonnet 5 $0.00003 $0.00076
Haiku 4.5 $0.00002 $0.00038

Measured yesterday against content hash 37e57ed6a524, 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 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 yesterday.

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.

plugins/ai/commands/codex-update.md · 26 lines

What it actually says

Run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/ai-companion.mjs" codex-update $ARGUMENTS

Behavior:

  • Downloads https://codeload.github.com/openai/codex-plugin-cc/tar.gz/refs/tags/<tag>.
  • Verifies the SHA-256 against ai-plugins-cc.upstream.pinnedSha in @ai-plugins-cc/codex-adapter's package.json if pinned. Refuses to install on mismatch.
  • Atomic-renames the extracted tree into the managed cache (default: ~/.cache/ai-plugins-cc/codex-plugin-cc/).
  • Subsequent invocations of /ai:review --provider=codex and friends discover this install automatically.

Flags:

  • --tag=vX.Y.Z — override the pinned tag. Use only when you've reviewed the upstream changes and intend to lift the pin afterwards.
  • --pin — after install, write the observed SHA back into @ai-plugins-cc/codex-adapter's package.json so subsequent installs hash-verify against it. Maintainer flag only: refuses to write to a node_modules copy and surfaces the SHA so it can be pasted manually instead.
  • --into=PATH — override the install directory.
  • --json — emit the full result as JSON.

Output the install summary verbatim so the user sees the resolved tag, SHA, target path, and whether the pin was written.

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. yesterday First seen · 26 lines · 17 tokens per session scan A 37e57ed6a524

Subscribe to this mod's changes

codex-update is a command published in the GitHub repository dysfunc/ai-plugins-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 380 once invoked, about $0.0001 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.

Git and workflowclaudeclaude-codeclaude-code-plugincodexgeminigrok
Related

Other commands, from other repositories

ask

Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic — ask the council, council review…

hex/claude-council · 189 tokens

result

Fetch, list, or cancel background council jobs started with --async.

hex/claude-council · 13 tokens

status

Check connectivity and configuration status of all council providers.

hex/claude-council · 9 tokens

grok-files

List, prune, or gc Grok (xAI) uploaded files. Cleanup for bridge-owned uploads only.

antonbabenko/deliberation · 26 tokens

help

Show how to use deliberation here - what each command does, when to reach for it, and real prompts you can paste right now. Read-only.

antonbabenko/deliberation · 33 tokens

setup

Configure deliberation with Codex (GPT), Gemini, Grok, and OpenRouter MCP servers.

antonbabenko/deliberation · 21 tokens