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 skills add Hivemind-OSS/Hivemind --skill hive-connect-harnessgit clone --depth 1 https://github.com/Hivemind-OSS/HivemindWrote 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/skills/hivemind-oss/hivemind/hive-connect-harness)<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-connect-harness"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-harness/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.
<a href="https://agentmods.dev/skills/hivemind-oss/hivemind/hive-connect-harness"><img src="https://agentmods.dev/badge/skills/hivemind-oss/hivemind/hive-connect-harness.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00109 | $0.03004 |
| Opus 5 | $0.00055 | $0.01502 |
| Sonnet 5 | $0.00022 | $0.00601 |
| Haiku 4.5 | $0.00011 | $0.00300 |
Grade A, and why
hive-connect-harness 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 10d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hive-connect-harness — install the client-side harness
Add the optional client-side enforcement layer on top of the MCP connection
hive-connect-team already made. Not a substitute for it — without that connection there is
nothing to enforce against — and not a server operation: installing or removing the harness changes
no server behavior (hive-bringup owns the server). Full reference: harnesses/README.md;
operator posture: HIVE-ADMIN.md §9.
The harness is a Claude Code plugin whose root is this repo's harnesses/ directory. There is
no build step and no package to publish — Node runs the committed TypeScript directly. A git clone alone installs nothing: the files are inert until the plugin is installed and the session
restarts.
Prerequisites
| Need | Check | If it fails |
|---|---|---|
| An endpoint this workstation can reach | on the server host, hive connect prints the URL for its current posture |
run hive-connect-team first |
| Node ≥ 23.6 | node --version |
upgrade. Below this the install still succeeds and the harness does nothing, with no message |
| Claude Code | claude --version |
the only adapter that ships today |
Case 1 — this device
1 · Put the endpoint in a shell profile, not in this shell. The plugin's manifest interpolates these at session start, so a session launched from a desktop icon or a fresh terminal must see them too:
# append to ~/.bashrc or ~/.zshrc — NOT just `export` at a prompt
export HIVE_MCP_URL=http://localhost:8765/mcp # loopback: no token needed, leave HIVE_TOKEN unset
# remote seat instead:
# export HIVE_MCP_URL=https://<your-domain>/mcp
# export HIVE_TOKEN=<seat-token> # from `hive token <seat>`, never a literal in a file you commit
2 · Install it at user scope. Agents work in repositories other than this one, so a user-scope install is the one that covers them all:
mkdir -p ~/.claude/skills
ln -sfn /path/to/hivemind/harnesses ~/.claude/skills/hive-loop
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.
- 10d ago First seen · 203 lines · 109 tokens per session scan A d81db18abcaf
hive-connect-harness is a skill published in the GitHub repository Hivemind-OSS/Hivemind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 109 tokens to every session and 3,004 once invoked, about $0.0005 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.
Other skills, from other repositories
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination.
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
Skill Builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.