local-research-db

local-research-db is a skill for Claude Code, Codex from jbdamask/McBrain. It costs 86 tokens per session (2,694 once invoked), scanned A, original, MIT.

A local JSONL-based tracker for research tasks in a McBrain knowledge base. JSONL is a text format where each line stores one JSON record, making it suitable for a simple research backlog.

In plain words
What is it for?
Use it to initialize or extend a local research backlog, add topics to a McBrain vault, and prepare tasks for automated research.
Why use it?
It gives research topics a consistent queue that can later be processed and marked complete by a research runner.

Skill for Claude CodeCodex

Part of the mcbrain plugin — 4 skills, 1 command, 1 MCP server shipped together

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/jbdamask/mcbrain/local-research-db
Any agent
npx skills add jbdamask/McBrain --skill local-research-db
Clone the repo
git clone --depth 1 https://github.com/jbdamask/McBrain

Made for: Claude Code, Codex.

Or install mcbrain, the plugin that ships this one along with the rest of its 4 skills, 1 command, 1 MCP server.

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.

agentmods badge for local-research-db

README.md
[![agentmods](https://agentmods.dev/badge/skills/jbdamask/mcbrain/local-research-db.svg)](https://agentmods.dev/skills/jbdamask/mcbrain/local-research-db)
Your own site
<a href="https://agentmods.dev/skills/jbdamask/mcbrain/local-research-db"><img src="https://agentmods.dev/badge/skills/jbdamask/mcbrain/local-research-db.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,694 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.02694
Opus 5 $0.00043 $0.01347
Sonnet 5 $0.00017 $0.00539
Haiku 4.5 $0.00009 $0.00269

Measured 5d ago against content hash 16313d2882d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

local-research-db 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.

plugins/mcbrain/skills/local-research-db/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Research DB

Initialize (or extend) a local research-task tracker for a McBrain vault. The tracker is a single JSONL file at <vault>/raw/research_tasks/tasks.jsonl — one JSON object per line, all topics in one file, topic-as-a-field (not a folder). The companion skill local-research-runner drains "To do" rows from this file, runs research subagents, writes findings to raw/notes/, and flips rows to "Done".

When to Use

  • User says "set up a local research tracker", "register a research topic in my vault", "spin up a JSONL backlog for X".
  • User has run mcbrain-setup and chose Local as the research-tracker backend, and now wants to add an additional topic.

Prerequisites

  • The vault must be a McBrain vault — registered in ~/.mcbrain/registry.json and visible via the mcbrain MCP's list_vaults tool. The skill writes into the vault at its absolute path from the registry.
  • Python 3 must be available on the user's host (used by local-research-runner, not by this skill — but worth surfacing so the user knows the runner will work).
  • No external installations, no extra MCP connectors, no tokens.

Inputs to Collect

  1. Research topic — free-form string (e.g. "CRISPR base editing", "AI evals literature"). Used to derive the topic slug and to label tracker rows. If the user did not supply one, ask.
  2. Associated McBrain vault — see Identifying the McBrain vault below. Resolve this before writing anything.

That's the entire input set. There is no parent page, no database name, no schema choice.

Identifying the McBrain vault

McBrain vaults are registered in ~/.mcbrain/registry.json ({"vaults": [{"name", "path", "created"}]}). To pick the right one:

  1. List the registered vaults. In Claude Desktop / Cowork, call the mcbrain MCP's list_vaults tool. In Claude Code, read ~/.mcbrain/registry.json directly.
  2. Zero matches. No vault is registered. Tell the user the tracker can't be set up because there is no vault to write into. Stop.
  3. One match. Use it. Mention the choice in your confirmation message ("I'll register this tracker with mcbrain-ai-science.") so the user can correct you if it's wrong.
  4. Multiple matches. Try to infer from the research topic by simple substring/keyword overlap with the vault names — e.g. topic "AI evals literature" → mcbrain-ai-science is a much better match than mcbrain-finance. Only auto-pick when one candidate is an obvious winner; otherwise ask:

Read the full file on GitHub · 149 lines

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.

  1. 5d ago First seen · 149 lines · 86 tokens per session scan A 16313d2882d3

Subscribe to this mod's changes

local-research-db is a skill published in the GitHub repository jbdamask/McBrain (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 2,694 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.

Related

Other skills, from other repositories

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