harness-refresh

harness-refresh is a skill for Claude Code, Codex from harnessworks/harness-starter-kit. It costs 36 tokens per session (212 once invoked), scanned A, original, MIT.

A review tool for finding old, duplicated, conflicting, or unused guidance in a repository’s AI-agent setup. It examines instructions, stored project knowledge, checks, and command wiring without changing files by default.

In plain words
What is it for?
Use it to classify harness material as worth keeping, updating, merging, archiving, deleting, or reviewing manually, then produce a maintenance report.
Why use it?
It shows where maintenance is needed so agents do not rely on obsolete advice or redundant records.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present.

Part of the agent-skills plugin — 6 skills shipped together

Good fit Use it to classify harness material as worth keeping, updating, merging, archiving…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/harnessworks/harness-starter-kit/harness-refresh
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.

Any agent
npx skills add harnessworks/harness-starter-kit --skill harness-refresh
Clone the repo
git clone --depth 1 https://github.com/harnessworks/harness-starter-kit

Made for: Claude Code, Codex.

Or install agent-skills, the plugin that ships this one along with the rest of its 6 skills.

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-refresh

README.md
[![agentmods](https://agentmods.dev/badge/skills/harnessworks/harness-starter-kit/harness-refresh.svg)](https://agentmods.dev/skills/harnessworks/harness-starter-kit/harness-refresh)
Your own site
<a href="https://agentmods.dev/skills/harnessworks/harness-starter-kit/harness-refresh"><img src="https://agentmods.dev/badge/skills/harnessworks/harness-starter-kit/harness-refresh.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 212 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 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 $0.00036 $0.00212
Opus 5 $0.00018 $0.00106
Sonnet 5 $0.00007 $0.00042
Haiku 4.5 $0.00004 $0.00021

Measured 7d ago against content hash 6adc7aac2892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

harness-refresh 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 7d 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.

agent-skills/skills/harness-refresh/SKILL.md · 29 lines

What it actually says

Harness Refresh

Review an existing target harness for maintenance needs.

Steps

  1. Read ../../references/package-contract.md.
  2. Read ../../references/refresh-workflow.md.
  3. If ./harness-starter-kit/commands/harness-refresh.md exists in the target, prefer that canonical workflow.
  4. Inspect current harness docs, rules, memory records, checks, and normal command wiring.
  5. Classify findings as keep, update, merge, archive/delete candidate, or manual review.
  6. Run lightweight checks when available.
  7. Produce the Harness Refresh Report.

Boundaries

  • Do not delete, archive, move, rename, format, or stage files unless the user explicitly approves the specific files.
  • Report recommendations by default.
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. 7d ago First seen · 29 lines · 36 tokens per session scan A 6adc7aac2892

Subscribe to this mod's changes

harness-refresh is a skill published in the GitHub repository harnessworks/harness-starter-kit (113 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 212 once invoked, about $0.0002 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 2026-08-30.