Borrowing it
Nothing to install: this file belongs to draekien-industries/membank. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/draekien-industries/membank/main/.claude/skills/harness-research/SKILL.mdgit clone --depth 1 https://github.com/draekien-industries/membankWrote 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/draekien-industries/membank/harness-research)<a href="https://agentmods.dev/skills/draekien-industries/membank/harness-research"><img src="https://agentmods.dev/badge/skills/draekien-industries/membank/harness-research/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.
<a href="https://agentmods.dev/skills/draekien-industries/membank/harness-research"><img src="https://agentmods.dev/badge/skills/draekien-industries/membank/harness-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00088 | $0.01030 |
| Opus 5 | $0.00044 | $0.00515 |
| Sonnet 5 | $0.00018 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A harness research task produces a library of spec-level reference files — one file per item (hook, tool, API endpoint), one directory per harness, nested under a topic subdirectory. The goal is exhaustive accuracy: every field name, every trigger condition, every edge case documented, not summarised.
Phase 1 — Scope
Resolve these four questions before spawning any agents. Each has a default; only ask when the user's request contradicts the default or leaves it genuinely ambiguous:
- Harnesses — which harnesses to cover (e.g. codex, copilot, opencode, and any others). Default: all harnesses referenced in the project's harness docs.
- Topic — what system or feature to document (e.g. hooks, tools, MCP integration). No default — must be explicit.
- Output root — where to write the files. Default:
docs/in the project root. - Granularity — one file per item (hook, tool, command) vs. one file per category. Default: one file per item.
If the topic was provided as part of the invocation, skip asking and proceed directly to decomposition.
Phase 2 — Decompose
Create one research angle per harness. State for each:
- Harness name
- One-sentence scope (what to find about the topic for this harness)
- Likely primary sources (official docs site, GitHub repo, changelog)
Present all angles to the user and confirm before spawning researchers.
Phase 3 — Research
Spawn one researcher per harness in parallel. All run simultaneously.
Brief each researcher with:
- Their harness and topic
- The primary sources identified in decomposition
- The quality bar: spec-level and exhaustive — every item the harness exposes, every field, every edge case, every semantic meaning of exit codes or return values. Not summaries.
- Return format: structured raw data with one heading per item, sub-headings for: Trigger, Input Shape, Output Shape, Exit Codes / Response Codes, Config Example, Notes. No prose paragraphs.
- If the harness does not support the topic at all: document that explicitly and describe what alternatives (if any) exist.
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.
- 12d ago First seen · 75 lines · 88 tokens per session scan A bcdb9862373e
harness-research is a skill published in the GitHub repository draekien-industries/membank (2 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 1,030 once invoked, about $0.0004 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 2026-08-31.
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…