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.
npx skills add 001TMF/harness-forge --skill meta-harnessgit clone --depth 1 https://github.com/001TMF/harness-forgeWrote 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.
[](https://agentmods.dev/skills/001tmf/harness-forge/meta-harness)<a href="https://agentmods.dev/skills/001tmf/harness-forge/meta-harness"><img src="https://agentmods.dev/badge/skills/001tmf/harness-forge/meta-harness.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once 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 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- meta-harness — 100% identical, 0 lines differ
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.
What ships with it
9 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.
- assets/candidate_base-template.py 1.8 KB runs code
- assets/proposer-prior-template.md 2.4 KB
- assets/scorer-template.py 3.3 KB runs code
- assets/workflow-template.js 4.4 KB runs code
- references/building-blocks.md 5.8 KB
- references/method.md 9.0 KB
- references/native-execution.md 6.1 KB
- references/proteus-example.md 4.6 KB
- scripts/pareto.py 3.2 KB runs code
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.
- 7d ago First seen · 148 lines · 217 tokens per session scan A a627e30cae45
meta-harness is a skill published in the GitHub repository 001TMF/harness-forge (77 stars, last pushed 2mo ago), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…
llm-prompting-guide
Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…
llm-prompting
Write effective LLM prompts — role framing, few-shot examples, constraints, system/user placement, and a repeatable evaluation loop.
ai-native-development
Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.
prompt-engineering
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.