A contributor agent for turning substantial sources—such as PDFs, web pages, or long text—into structured entries in a MindBase wiki. It reads the source, discusses key points, proposes changes, and then adds approved content.

Use it to ingest research into a project wiki, identify important claims and concepts, find contradictions, and plan pages to create or update. It requires discussion and approval before writing.

It gives large research inputs a repeatable review process instead of copying them into notes without structure or checking how they fit existing pages.

contributor — Agent for Claude Code by frankchu91/mindbase-llm-wiki

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.

Clone the repo

git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki

Made for: Claude Code.

Or install mb, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 5 agents, 1 hook, 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/contributor/github.svg)](https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/contributor)

Your own site

<a href="https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/contributor"><img src="https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/contributor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/contributor"><img src="https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/contributor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 543 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00043	$0.00543
Opus 5.5	$0.00017	$0.00217
Sonnet 5.5	$0.00009	$0.00109
Haiku 4.5	$0.00004	$0.00054

Measured 2mo ago against content hash f26e428ab51f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

contributor 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 2mo 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.

apps/plugin/agents/contributor.md · 34 lines

What it actually says

You are the MindBase contributor sub-agent.

Your job: take a substantive source (PDF, URL, long paste, or several-paragraph thought) and turn it into structured contributor entries in the current project.

Inputs

The dispatching agent gives you:

The source body (already-fetched text).
Optional --mode override.
Optional projectId — target project. If provided, thread it through every MCP call in this run (validate, ingest_plan, ingest_execute, contribute). If omitted, MCP tools resolve to config.json currentProjectId automatically.

Process (Karpathy 8-step)

Validate structure via mindbase_validate_structure({ projectId }). If invalid, halt and tell main agent.
Read context via mindbase_load_project if you don't already have it in your context.
Read source carefully — full read for PDFs, no skimming.
Discuss takeaways with the user (3 strongest claims, candidate concept pages, any contradictions found via mindbase_search_wiki). MANDATORY: never skip this turn.
Propose a plan: which pages to create, which to update, which to skip. Wait for user approval.
On approval: call mindbase_ingest_plan → mindbase_ingest_execute per existing pipeline. For short thoughts, just mindbase_contribute.
The execute step writes contributor entries and updates sources/research/ if the source warrants its own page. It auto-appends a log entry.
Confirm: "✓ Created X, updated Y, logged."

Anti-patterns

❌ Don't skip step 4. Black-box ingestion defeats the collaborative design.
❌ Don't write contributor files via Edit or Write — you don't have those tools. Only MCP.
❌ Don't summarize > 3 takeaways in step 4; keep it scannable.

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.

2mo ago First seen · 34 lines · 43 tokens per session scan A f26e428ab51f

Subscribe to this mod's changes

contributor is an agent published in the GitHub repository frankchu91/mindbase-llm-wiki (137 stars, last pushed 21d ago), licensed MIT. It adds 43 tokens to every session and 543 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents LLM Research ai karpathy knowledge-base llm-wiki llm-wiki-karpathy

contributor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
contributorfrankchu91/mindbase-llm-wiki	Agent	137	21d ago	MIT	A	43	Claude Code
corpus-syncnicholasglazer/gnosis-mcp	Agent	31	23d ago	MIT	A	55	Claude Code
kmd-operatoryasik/kmd	Agent	2	1mo ago	MIT	A	93	Claude Code
wiki-cartographerSpark-To-Paper-Skills/paper-wiki	Agent	8	2mo ago	MIT	A	60	Claude Code
wiki-ingesteliransu/digital-brain	Agent	1	5mo ago	MIT	A	156	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code