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 agentmods add skills/lazyfroglol/harness_engineering/gpt2-codegolfnpx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolfgit clone --depth 1 https://github.com/lazyFrogLOL/Harness_EngineeringWrote 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/lazyfroglol/harness_engineering/gpt2-codegolf)<a href="https://agentmods.dev/skills/lazyfroglol/harness_engineering/gpt2-codegolf"><img src="https://agentmods.dev/badge/skills/lazyfroglol/harness_engineering/gpt2-codegolf.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 | $0.00067 | $0.01446 |
| Opus 5 | $0.00034 | $0.00723 |
| Sonnet 5 | $0.00013 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
gpt2-codegolf 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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 167 lines · 67 tokens per session scan A c76c9dc6c1e7
gpt2-codegolf is a skill published in the GitHub repository lazyFrogLOL/Harness_Engineering (126 stars, last pushed 3mo ago), with no licence file. It adds 67 tokens to every session and 1,446 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 2026-08-30.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
cua-driver
Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by elementindex, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to…
openloomi-memory
OpenLoomi Memory is the long-lived context layer of OpenLoomi — a tiered, locally-stored knowledge graph that grows on its own from your Connectors, chats, and Screen Capture. Memory is what makes Chat grounded and what Loop reads before it produces a Decision. It is always on your machine (local-first), always…
openloomi-setup
Run OpenLoomi one-time setup — auto-chains install → set Codex provider → launch → wait API → mint guest session token → ready in one call. Mirrors Claude's /openloomi:setup. Triggers: setup openloomi, install openloomi, install and run, 一键装好并跑起来, fix openloomi, finalize openloomi, installrequired, awaitinguseraction…
create-task
Create an end-to-end Continual Learning Bench task. Use when adding a new src/tasks/ benchmark task, including design interview, concrete Jinja prompt templates, JSON action contracts, observation templates, debug schedule, behavioral E2E tests, validation, smoke/debug runs with icl and iclnotepad, and README…
openloomi-api
OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…