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/devswha/oh-my-gajae-code/multi-harness-researchnpx skills add devswha/oh-my-gajae-code --skill multi-harness-researchgit clone --depth 1 https://github.com/devswha/oh-my-gajae-codeWrote 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/devswha/oh-my-gajae-code/multi-harness-research)<a href="https://agentmods.dev/skills/devswha/oh-my-gajae-code/multi-harness-research"><img src="https://agentmods.dev/badge/skills/devswha/oh-my-gajae-code/multi-harness-research.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 | $0.00068 | $0.01989 |
| Opus 5 | $0.00034 | $0.00994 |
| Sonnet 5 | $0.00014 | $0.00398 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
multi-harness-research 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-harness research
This is an explicit, read-only research surface. It directly orchestrates four independent
harnesses; it does not create a GJC team, task, goal, session, worktree, or worker model.
Locked intent
artifact:research-docs— publish four fixed-position lane documents and a factualsummary.md; failed lanes keep a fixed placeholder and ledger entry.surface:explicit-command— only an explicitmulti-harness-researchskill request or/omg:multi-harnessinvocation may run it.integration:four-harnesses— run exactly the four lanes below, in order.constraint:read-only— workers can inspect the canonical target only; only the project-external XDG artifact directory is writable.constraint:same-task— every lane receives byte-identical normalized task bytes plus the same safety/output suffix, recorded by one SHA-256 digest.constraint:single-suite— all active files and runtime ownership useoh-my-gajae-code; no additional marketplace plugin is involved.
Activation and task confirmation
An explicit argument is the canonical task. Without one, preview a one-sentence goal, the research questions, and expected output; obtain confirmation before running. Do not infer a task from ordinary conversation, start a background run, or silently split one request into multiple tasks.
Use the direct multi-harness-research.mjs runner installed by the native user-scope
installer. Execution requires its trusted mode-0600 binding and private runtime snapshot at
~/.gjc/agent/runtimes/multi-harness-research/. A project-scope installation or a
project-local runner never authorizes execution. Missing, malformed, changed, or unsafe runtime
state fails closed; do not install, update, migrate, set up, or log in on the user's behalf.
Fixed lanes and isolation
The runner fans the one normalized task to exactly these lanes in this order; it never adds a fifth model, substitutes a selector, retries through a fallback provider, or asks for a winner, majority, vote, consensus, ranking, recommendation, or final verdict.
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.
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.
- 6d ago First seen · 132 lines · 68 tokens per session scan A 777f1beecda3
multi-harness-research is a skill published in the GitHub repository devswha/oh-my-gajae-code (34 stars, last pushed 17d ago), licensed MIT. It adds 68 tokens to every session and 1,989 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…