agent-hivemind: Command for Claude Code

.claude/commands/hivesink-push.md

hivesink-push is a command for Claude Code from lancejames221b/agent-hivemind. It costs 14 tokens per session (1,888 once invoked), scanned E, original, MIT.

A command that uploads local hAIveMind skills, documentation, and configuration files to a shared central vault over HTTP through Tailscale, a private network connection.

In plain words
What is it for?
Use it to push skills, docs, configs, or all supported files to the vault. Use dry-run mode to inspect what would be uploaded.
Why use it?
It helps keep files on the local machine and the central vault in sync without setting up SSH keys, and it can preview changes first.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is lancejames221b/agent-hivemind's own configuration. It tells Claude Code how to work on agent-hivemind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-hivemind configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ls -la ./.mcp.json ./config/*.json 2>/dev/null || echo " No config files found".

Reuse

Borrowing it

Nothing to install: this file belongs to lancejames221b/agent-hivemind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lancejames221b/agent-hivemind/master/.claude/commands/hivesink-push.md
Clone the repo
git clone --depth 1 https://github.com/lancejames221b/agent-hivemind

Made for: Claude Code.

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 hivesink-push

README.md
[![agentmods](https://agentmods.dev/badge/commands/lancejames221b/agent-hivemind/hivesink-push.svg)](https://agentmods.dev/commands/lancejames221b/agent-hivemind/hivesink-push)
Your own site
<a href="https://agentmods.dev/commands/lancejames221b/agent-hivemind/hivesink-push"><img src="https://agentmods.dev/badge/commands/lancejames221b/agent-hivemind/hivesink-push.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,888 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 4 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.01888
Opus 5 $0.00007 $0.00944
Sonnet 5 $0.00003 $0.00378
Haiku 4.5 $0.00001 $0.00189

Measured 7d ago against content hash 106219f7059f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade E, and why

hivesink-push scanned grade E with 4 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s -X POST --data-binary @"$file" \

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt-get install curl

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://lance-dev:8900/vault/list | python3 -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://lance-dev:8900/vault/list | python3 -m json.tool
.claude/commands/hivesink-push.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hivesink-push - Sync to hAIveMind Vault

Purpose

Push skills, docs, and configs from your local machine to the central hAIveMind vault on lance-dev. Uses HTTP via Tailscale for cross-machine synchronization (no SSH key setup required).

Syntax

hivesink-push [options]

Options

  • --dry-run - Preview what would be pushed without making changes
  • --skills - Push only skill files (commands/*.md)
  • --docs - Push only docs (CLAUDE.md, etc.)
  • --configs - Push only config files
  • --all - Push everything (default behavior)

Central Vault Location

The hAIveMind vault is accessible via HTTP at lance-dev:8900:

  • http://lance-dev:8900/vault/upload/skills/ - Upload skill files
  • http://lance-dev:8900/vault/upload/docs/ - Upload documentation
  • http://lance-dev:8900/vault/upload/configs/ - Upload config files

Execution Instructions

When this command is invoked, execute the following commands based on options:

Check Current Vault State (--dry-run)

Preview what's in the vault and what would be pushed:

echo "=== Current Vault Contents ==="
curl -s http://lance-dev:8900/vault/list | python3 -m json.tool

echo ""
echo "=== Local Files to Push ==="
echo "Skills:"
ls -la ~/.claude/commands/*.md 2>/dev/null || echo "  No skill files found"
echo "Configs:"
ls -la ./.mcp.json ./config/*.json 2>/dev/null || echo "  No config files found"
echo "Docs:"
ls -la ./CLAUDE.md ./AGENT.md 2>/dev/null || echo "  No doc files found"

Push Everything (default or --all)

Upload all local files to vault:

MACHINE_NAME=$(hostname)

echo "=== Pushing Skills ==="
for file in ~/.claude/commands/*.md; do
    if [ -f "$file" ]; then
        filename=$(basename "$file")
        curl -s -X POST --data-binary @"$file" \
            -H "X-Source-Machine: $MACHINE_NAME" \
            "http://lance-dev:8900/vault/upload/skills/$filename" && \
            echo "✅ Uploaded: $filename"
    fi
done

echo ""
echo "=== Pushing Configs ==="
if [ -f "./.mcp.json" ]; then
    curl -s -X POST --data-binary @"./.mcp.json" \
        -H "X-Source-Machine: $MACHINE_NAME" \
        "http://lance-dev:8900/vault/upload/configs/.mcp.json" && \
        echo "✅ Uploaded: .mcp.json"
fi

for file in ./config/*.json; do
    if [ -f "$file" ]; then
        filename=$(basename "$file")
        curl -s -X POST --data-binary @"$file" \
            -H "X-Source-Machine: $MACHINE_NAME" \
            "http://lance-dev:8900/vault/upload/configs/$filename" && \
            echo "✅ Uploaded: $filename"
    fi
done

echo ""
echo "=== Pushing Docs ==="
for doc in CLAUDE.md AGENT.md; do
    if [ -f "./$doc" ]; then
        curl -s -X POST --data-binary @"./$doc" \
            -H "X-Source-Machine: $MACHINE_NAME" \
            "http://lance-dev:8900/vault/upload/docs/$doc" && \
            echo "✅ Uploaded: $doc"
    fi
done

echo ""
echo "✅ Push complete"

Read the full file on GitHub · 231 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. 7d ago First seen · 231 lines · 0 tokens per session scan E 106219f7059f

Subscribe to this mod's changes

hivesink-push is a command published in the GitHub repository lancejames221b/agent-hivemind (7 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,888 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it E with 4 findings (sends data to an external url, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.