A command for adding a thought, source, or pasted content to a MindBase project, a workspace for organizing research and notes.

Use it to add file paths, web pages, PDFs, raw text, document IDs, or short thoughts, with optional daily or concept categorization.

It lets you send one contribution to a chosen project without changing the project currently selected in the configuration.

contribute — Command for Claude Code by frankchu91

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/commands/frankchu91/mindbase-llm-wiki/contribute.svg)](https://agentmods.dev/commands/frankchu91/mindbase-llm-wiki/contribute)

Your own site

<a href="https://agentmods.dev/commands/frankchu91/mindbase-llm-wiki/contribute"><img src="https://agentmods.dev/badge/commands/frankchu91/mindbase-llm-wiki/contribute.svg" alt="Measured on agentmods" height="20"></a>

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 738 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	$0.00053	$0.00738
Opus 5	$0.00026	$0.00369
Sonnet 5	$0.00011	$0.00148
Haiku 4.5	$0.00005	$0.00074

Measured 7d ago against content hash 9eee15befb23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

contribute 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 7d 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/commands/contribute.md · 41 lines

What it actually says

Contribute content to a MindBase project.

Arguments: $ARGUMENTS

Parse in order (flags may appear anywhere, but text is what remains):

--project <id> or -p <id> — target project id. If omitted, uses config.json currentProjectId.
--mode <m> — daily | concept | daily+concept | (default: auto).
Remaining text = the body to contribute (file path, URL, raw paste, or short thought).

Important: -p / --project does NOT change the current project — it only routes THIS single contribution. Use /mb:load <id> to change current project persistently.

Resolve input type (in order):

File path ending in .pdf, .md, .txt: call mindbase_ingest_file({ path, projectId? }) FIRST — it archives the original into sources/raw/ and returns the extracted text. Then continue with the returned text (discuss takeaways → contribute). .html files: use Read.
URL pointing directly at a file (ends in .pdf, or an arXiv /pdf/ link): call mindbase_ingest_file({ path: url }) — it downloads, archives, and extracts. Other URLs (HTML pages): use WebFetch.
Raw doc id (raw:<id>): use mindbase_read_wiki_page or similar.
Pasted long text: ingest scale.
Short user thought (≤ 200 chars, time-anchored "today I…"): capture scale.
If empty: ask user what to add.

Calibrate output volume:

Short thought → call mindbase_contribute({ text, mode, projectId? }) ONCE. 1 action. Only include projectId in the call if user passed -p/--project.
Substantive source → dispatch the contributor sub-agent via the Task tool. Pass both the source body and the resolved projectId (if any) in the sub-agent brief so it threads projectId through every MCP call.

Routing prefix override (highest priority): if text starts with daily: or concept: or daily+concept:, strip the prefix and pass the remaining text + mode through verbatim to mindbase_contribute.

Examples:

/mb:contribute "wiki v2 refactor 上线了" → current project, mode=auto
/mb:contribute -p ai-agents "GPT-5 rumored 2026-Q4" → ai-agents, current project unchanged
/mb:contribute --project insurance --mode concept "policy X: 覆盖 flood" → insurance, concept mode
/mb:contribute /Downloads/paper.pdf → current, auto (contributor sub-agent)
/mb:contribute -p ai-agents /Downloads/paper.pdf → ai-agents, contributor sub-agent

After success, report:

✓ Contributed to <projectId>/sources/contributors/<you>/<today>.md

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.

7d ago First seen · 41 lines · 53 tokens per session scan A 9eee15befb23

Subscribe to this mod's changes

contribute is a command published in the GitHub repository frankchu91/mindbase-llm-wiki (95 stars, last pushed 13d ago), licensed MIT. It adds 53 tokens to every session and 738 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.

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

contribute

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

wiki-query

wiki-req

wiki-ingest

wiki-record

wiki-retro

wiki-discover