meta-harness

meta-harness is a skill for Claude Code, Codex from gabrielmoreira/agent-skills-mirror. It costs 217 tokens per session (2,181 once invoked), scanned A, a copy of meta-harness, MIT.

A method for testing different parts of an AI agent's supporting system while keeping the underlying model fixed. This supporting system, called a harness, decides what the agent remembers, retrieves, summarizes, and receives in its prompts.

In plain words
What is it for?
Use it to run optimization loops over agent scaffolding and keep the best trade-offs. It is intended for harness-optimization tasks, including memory-summary experiments.
Why use it?
It helps compare changes to memory, retrieval, prompts, and tool selection using a cheap repeatable score. The goal is to find better quality, lower cost, or a useful balance of both.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to run optimization loops over agent scaffolding and keep the best trade-offs. It is intended for harness-optimization tasks, including memory-summary experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gabrielmoreira/agent-skills-mirror/meta-harness
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 gabrielmoreira/agent-skills-mirror --skill meta-harness
Clone the repo
git clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirror

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 meta-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/meta-harness/github.svg)](https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/meta-harness)
Your own site
<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/meta-harness"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/meta-harness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meta-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/meta-harness"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/meta-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 217 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,181 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 $0.00217 $0.02181
Opus 5 $0.00109 $0.01091
Sonnet 5 $0.00043 $0.00436
Haiku 4.5 $0.00022 $0.00218

Measured 12d ago against content hash a627e30cae45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meta-harness 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (assets/candidate_base-template.py, assets/scorer-template.py, assets/workflow-template.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 meta-harness — 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.

mirrors/repos/001TMF@harness-forge/skills/meta-harness/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Harness (native)

What this is

Meta-Harness optimizes the harness, not the model. The harness is the code around a fixed base model that decides what to store, retrieve, compress, and show while the model works. You hold the model frozen and search over that scaffolding: propose candidate variants, score each on a cheap deterministic eval, keep a Pareto frontier (quality up, cost down), and iterate. The proposer is an LLM agent writing code; the inner loop is a cheap scorer.

The Stanford repo (stanford-iris-lab/meta-harness) ships a Python driver — claude_wrapper.py (~720 lines) + meta_harness.py (~540 lines) — that reimplements an agent runtime to drive a headless Claude: spawn a session, parse stream-json, track tool calls, log everything, loop. You already are that runtime. So you run the same loop with native tools (Agent, Workflow, /loop) and keep only the irreducible domain logic — a $0 scorer. The orchestration was never the hard part; your harness provides it.

This skill is the method, reusable for any harness-optimization task. A fully worked example (optimizing proteus's campaign-memory summarizer) lives at ~/mh-proteus/ and is walked through in references/proteus-example.md.

When to use this

Strong fit when several of these hold (full criteria in references/method.md):

  • The base model is fixed and the opportunity is better retrieval / memory / context / prompting / tool scaffolding. (This is the whole premise — if the gain must come from the model weights, this is the wrong tool: do RL/fine-tuning instead.)
  • There are repeated episodes / tasks, not a one-off.
  • There is a cheap, deterministic eval with a real success signal — or you can build one.
  • The search set is large enough to expose failure modes, small enough to iterate.
  • There are recurring error patterns a harness could fix systematically.

Poor fit: no stable eval loop, or purely subjective quality with no measurable criterion.

Read the full file on GitHub · 148 lines

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. 12d ago First seen · 148 lines · 217 tokens per session scan A a627e30cae45

Subscribe to this mod's changes

meta-harness is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 217 tokens to every session and 2,181 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to meta-harness, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens