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.
npx agentmods add instructions/mindsdb/mindshub/claude-mdgit clone --depth 1 https://github.com/mindsdb/mindshubWrote 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/instructions/mindsdb/mindshub/claude-md)<a href="https://agentmods.dev/instructions/mindsdb/mindshub/claude-md"><img src="https://agentmods.dev/badge/instructions/mindsdb/mindshub/claude-md.svg" alt="Measured on agentmods" 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 | $0.01908 | $0.01908 |
| Opus 5 | $0.00954 | $0.00954 |
| Sonnet 5 | $0.00382 | $0.00382 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
mindshub CLAUDE.md 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 4d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minds Platform
Submodules
This repo has 4 submodules:
| Path | Repo | Tracking |
|---|---|---|
frontend |
mindsdb/cowork |
tag-pinned |
backend/core_api |
mindsdb/cowork-server |
tag-pinned |
backend/core_agent |
mindsdb/anton |
tag-pinned |
backend/data-vault |
mindsdb/data-vault |
main branch |
Clone (fresh)
git clone --recurse-submodules https://github.com/mindsdb/minds-platform
Initialize after cloning without submodules
git submodule update --init --recursive
Pull — sync to what the parent repo pins (default)
git submodule update --recursive
Pull — advance all submodules to latest main
Only do this if you intend to develop across all repos. You'll need to commit the updated pointers in the parent repo afterward.
git submodule foreach 'git checkout main && git pull origin main'
Make changes and push inside a submodule
- Go into the submodule and get on a real branch first (all submodules start in detached HEAD):
cd backend/data-vault # or whichever submodule
git checkout main # or: git checkout -b your-feature-branch
- Make your changes, commit, and push:
git add .
git commit -m "your message"
git push origin main
- Back in the parent repo, stage and commit the updated submodule pointer:
cd ../..
git add backend/data-vault
git commit -m "bump data-vault to latest"
git push
The parent repo stores a commit SHA pointer to each submodule, not the code itself. Always push from inside the submodule first, then update the pointer in the parent.
Working on module branches (multi-developer)
The superproject pins each submodule to a commit. To let everyone develop on
their own module branches without fighting over pins or drowning in git status
noise, the workflow is:
1. .gitmodules sets ignore = all on every submodule. Day-to-day branch
work in a submodule never shows up as a superproject change — git status in the
parent stays clean no matter what branch each module is on. (This is the only
setting that silences "new commits in <module>"; ignore = dirty does not.)
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.
- 4d ago First seen · 181 lines · 1,908 tokens per session scan A b25241e93530
mindshub CLAUDE.md is an instructions file published in the GitHub repository mindsdb/mindshub (39,680 stars, last pushed 13d ago), licensed MIT. It adds 1,908 tokens to every session, about $0.0095 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.
Other instructions, from other repositories
eigent AGENTS.md
AGENTS.md instructions for eigent-ai/eigent, covering eigent agent instructions, ui work, product terminology and validation.
markifact-mcp GEMINI.md
Instructions for markifact/markifact-mcp, covering markifact, the 8 tools, discover → inspect → run, connection vs account and reporting workflow.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则（最高优先级）, 架构 architecture and 命令 commands.
cowork-to-code-bridge CLAUDE.md
Instructions for abhinaykrupa/cowork-to-code-bridge, covering claude.md — cowork-to-code-bridge, first connection — read this and core functions (in coworktocodebridge/client.py).
job-hunt-skills AGENTS.md
Instructions for Remotivated/job-hunt-skills, covering job hunt skills repository guidance, before editing workflows, required checks and compatibility.
myPKA CLAUDE.md
Claude Code instructions for myICOR/myPKA, covering claude.md, first run check (read this before doing anything else), identity (mandatory — applies every session), source of truth and specialist dispatch (claude code specific).