harness-update

harness-update is a skill for Claude Code, Codex from Chachamaru127/codex-harness. It costs 53 tokens per session (907 once invoked), scanned A, original, MIT.

A workflow for updating an existing Harness project to a newer Harness version. Harness is the project setup and task workflow used by this add-on; the update includes version checks, backups, and non-destructive file changes.

In plain words
What is it for?
Use it to update Harness templates and configuration, fix outdated permission syntax, detect new skills, and optionally sync Codex files.
Why use it?
It reduces the risk of losing project settings or tasks during a template update. It also identifies breaking changes, changed skills, and files that need attention.

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/chachamaru127/codex-harness/harness-update
Any agent
npx skills add Chachamaru127/codex-harness --skill harness-update
Clone the repo
git clone --depth 1 https://github.com/Chachamaru127/codex-harness

Made for: Claude Code, 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 harness-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/chachamaru127/codex-harness/harness-update.svg)](https://agentmods.dev/skills/chachamaru127/codex-harness/harness-update)
Your own site
<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/harness-update"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/harness-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 907 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 5.1 $0.00053 $0.00907
Opus 5 $0.00026 $0.00453
Sonnet 5 $0.00011 $0.00181
Haiku 4.5 $0.00005 $0.00091

Measured 5d ago against content hash 34543b95226f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

harness-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 5d 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.

.codex/skills/harness-update/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Update Skill

Safely update projects with existing harness to the latest harness version. Version detection → Backup → Non-destructive update flow preserves existing settings and tasks while introducing latest features.

Quick Reference

  • "I want to update harness to the latest version"
  • "I want to add new features to existing project"
  • "I want to update config file format to latest version"
  • "I want to fix incorrect permission syntax"
  • "I was notified of template updates"

Deliverables

  • Version detection via .claude-code-harness-version
  • Template update detection and localization judgment
  • Identify files needing update
  • Auto-backup creation
  • Non-destructive settings/workflow file updates
  • No localization → overwrite / Localized → merge support
  • Skills diff detection - Auto-detect and propose new skills
  • Optional: Codex CLI sync (.codex/ + AGENTS.md)
  • Post-update verification

Execution Flow Overview

Phase Reference Description
Phase 1 references/version-detection.md Version detection and confirmation
Phase 1.5 references/breaking-changes.md Breaking changes detection and fix
Phase 2 references/backup-and-update.md Backup creation and file updates
Phase 3 references/verification.md Verification and completion

Phase Summary

Phase 1: Version Detection

  1. Check .claude-code-harness-version file
  2. Compare with plugin's latest version
  3. Run template-tracker.sh check for content-level updates
  4. Confirm update scope with user

If harness not installed: Suggest using /harness-init instead.

Phase 1.5: Breaking Changes Detection

Detect and fix existing settings issues:

  • Incorrect permission syntax (e.g., Bash(npm run *)Bash(npm run:*))
  • Deprecated settings (e.g., disableBypassPermissionsMode)
  • Old hook settings in project files (should use plugin hooks.json)

Read the full file on GitHub · 101 lines

Files

What ships with it

5 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. 5d ago First seen · 101 lines · 53 tokens per session scan A 34543b95226f

Subscribe to this mod's changes

harness-update is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 907 once invoked, about $0.0003 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.