codex-unified: Skill for Codex

.codex/skills/update-v8-version/SKILL.md

update-v8-version is a skill for Codex from MikeManifold/codex-unified. It costs 86 tokens per session (836 once invoked), scanned A, a copy of update-v8-version, Apache-2.0.

A maintenance guide for updating the pinned V8 and rusty_v8 versions used by Codex. V8 is the JavaScript engine, and rusty_v8 provides Rust bindings for it.

In plain words
What is it for?
Use it to update V8 pins, refresh related artifacts and checksums, run local checks, and investigate failed V8 canary or artifact builds.
Why use it?
It organizes the version bump across dependency files, checksums, build files, tests, and the release-candidate validation process.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

This is MikeManifold/codex-unified's own configuration. It tells Codex how to work on codex-unified itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-unified configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .github/scripts/rusty_v8_bazel.py update-module-bazel.

Reuse

Borrowing it

Nothing to install: this file belongs to MikeManifold/codex-unified. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MikeManifold/codex-unified/main/.codex/skills/update-v8-version/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MikeManifold/codex-unified

Made for: Codex.

Wrote 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.

agentmods badge for update-v8-version

README.md
[![agentmods](https://agentmods.dev/badge/skills/mikemanifold/codex-unified/update-v8-version.svg)](https://agentmods.dev/skills/mikemanifold/codex-unified/update-v8-version)
Your own site
<a href="https://agentmods.dev/skills/mikemanifold/codex-unified/update-v8-version"><img src="https://agentmods.dev/badge/skills/mikemanifold/codex-unified/update-v8-version.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00086 $0.00836
Opus 5 $0.00043 $0.00418
Sonnet 5 $0.00017 $0.00167
Haiku 4.5 $0.00009 $0.00084

Measured 8d ago against content hash c3d4037f1d7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

update-v8-version 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.

Origin

This is a copy

100% identical to update-v8-version — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.codex/skills/update-v8-version/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update V8 Version

Core Workflow

  1. Read third_party/v8/README.md and follow its version-bump sequence. Treat that document as the release-process source of truth.

  2. Inspect and update the concrete repo surfaces that carry the pin:

    • codex-rs/Cargo.toml
    • codex-rs/Cargo.lock
    • MODULE.bazel
    • third_party/v8/BUILD.bazel
    • third_party/v8/README.md
    • the matching third_party/v8/rusty_v8_<version>.sha256 manifest when the remaining prebuilt inputs change
  3. Keep the existing checksum helpers in the loop:

    python3 .github/scripts/rusty_v8_bazel.py update-module-bazel
    python3 .github/scripts/rusty_v8_bazel.py check-module-bazel
    python3 -m unittest discover -s .github/scripts -p test_rusty_v8_bazel.py
    
  4. Validate the release-candidate path before broadening the work:

    • Prefer checking the v8-canary CI result for the candidate branch or PR when one exists, using GitHub check tooling or gh as appropriate.
    • If CI is unavailable or the user asked for a local-only check, run the closest local validation that is practical for the changed surface and say explicitly that it is a local substitute, not the full hosted canary.
  5. If the canary path passes, stop there. Summarize the result and encourage the user to commit the candidate changes or proceed with the release flow they requested. Do not publish tags, releases, or pushes unless the user asked.

Failure Path

Enter this path only when the canary or local build path fails.

  1. Capture the failing target, workflow job, and first actionable error.
  2. Compare the currently pinned version with the target version at the relevant upstream tag or SHA. Inspect both:
    • denoland/rusty_v8
    • upstream V8 source at the target Bazel-pinned version
  3. Track build-relevant deltas rather than broad source churn:
    • generated binding layout changes
    • archive or asset naming changes
    • GN/Bazel target changes
    • custom libc++ / libc++abi / llvm-libc inputs
    • sandbox or pointer-compression feature relationships
    • patch hunks in patches/ that no longer apply or no longer match upstream
  4. Trace each failing delta back into Codex's build graph:
    • MODULE.bazel
    • third_party/v8/BUILD.bazel
    • .github/scripts/rusty_v8_bazel.py
    • .github/workflows/v8-canary.yml
    • .github/workflows/rusty-v8-release.yml
  5. Update only the pieces required to restore the target version's build and artifact contract. Keep patch explanations and doc changes close to the affected files.
  6. Re-run the focused validation. If it becomes green, return to the normal workflow and stop with a concise summary plus the remaining release step.

Read the full file on GitHub · 73 lines

Files

What ships with it

1 file 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. 8d ago First seen · 73 lines · 86 tokens per session scan A c3d4037f1d7c

Subscribe to this mod's changes

update-v8-version is a skill published in the GitHub repository MikeManifold/codex-unified (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 86 tokens to every session and 836 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to update-v8-version, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

zhayujie/CowAgent · 41 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

debug-with-langwatch

Root-cause production errors and misbehaving agent runs with LangWatch. Finds errored traces, inspects spans, checks monitor and evaluator scores, then narrows to a root cause. Use when something is failing or misbehaving in production (errors, bad answers, latency spikes).

langwatch/langwatch · 63 tokens

eval-triage

Investigate failing experiments and evaluations with LangWatch. Triage a failing experiment run to the exact rows and evaluator scores that regressed, then to a root cause. Use when an experiment fails, scores drop, or evaluations regress.

langwatch/langwatch · 51 tokens