A research workflow for an LLM Wiki, a collection of linked notes for AI-readable knowledge. It finds outside sources, records where they came from, and adds useful conclusions to the wiki.

Use it to investigate a defined topic, collect five to ten reliable sources, save their details, and update relevant wiki pages with linked notes.

It turns an open-ended information search into a documented process with source evidence and focused updates. It also prevents research from becoming a disconnected report.

research — Skill for Claude Code and Codex by jackwener: A research workflow for an LLM Wiki, a collection…

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.

agentmods

npx agentmods add skills/jackwener/llm-wiki/research

Any agent

npx skills add jackwener/llm-wiki --skill research

Clone the repo

git clone --depth 1 https://github.com/jackwener/llm-wiki

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jackwener/llm-wiki/research.svg)](https://agentmods.dev/skills/jackwener/llm-wiki/research)

Your own site

<a href="https://agentmods.dev/skills/jackwener/llm-wiki/research"><img src="https://agentmods.dev/badge/skills/jackwener/llm-wiki/research.svg" alt="Measured on agentmods" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 460 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00460
Opus 5	$0.00023	$0.00230
Sonnet 5	$0.00009	$0.00092
Haiku 4.5	$0.00005	$0.00046

Measured 5d ago against content hash e5e323765fbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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.

skills/research/SKILL.md · 58 lines

What it actually says

Research for an LLM Wiki

Research fills a scoped gap in the wiki, then preserves the evidence and its useful conclusions. It combines query, source collection, and ingestion.

Workflow

Read wiki-purpose.md and wiki-schema.md; decline or narrow requests outside the vault's scope.
Run the query workflow first to determine what is known and define a precise research question.
Gather 5–10 high-quality sources. Prefer primary materials, official documentation, papers, and authoritative recent analysis. Seek independent confirmation for important claims.

Save each collected source under sources/YYYY-MM-DD/ before analysis. Include provenance when creating a research note:

---
title: Source Title
url: https://original-url
author: Author Name
date: YYYY-MM-DD
retrieved: YYYY-MM-DD
type: article | paper | documentation | blog | video-transcript
---

Treat files in sources/ as immutable after saving.

Apply the ingest workflow to each source: update focused, attributable wiki pages and add wikilinks rather than compiling a detached report only.

Present a final report with this structure:

## Research Report: Topic
### Question
### Findings
### Sources Added
### Wiki Pages Created/Updated
### Remaining Gaps

Create a query-synthesis page only when the cross-source conclusion is genuinely new and well supported. Then append a research entry to wiki-log.md and run llm-wiki sync.

Guardrails

Keep the research question bounded; list tangents as follow-ups.
Attribute every material claim to saved sources or cited wiki pages.
Flag outdated evidence for fast-moving topics.
Never invent a source, citation, or conclusion.

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.

5d ago First seen · 58 lines · 46 tokens per session scan A e5e323765fbb

Subscribe to this mod's changes

research is a skill published in the GitHub repository jackwener/llm-wiki (100 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 460 once invoked, about $0.0002 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens