A coordinator for managing the lifecycle of AI-agent capabilities. It observes changes, suggests actions, and coordinates decisions such as creating, combining, dividing, changing, or removing capabilities.

Use it when deciding whether capabilities should be spawned, merged, split, modified, or dissolved.

It provides a way to organise capability changes without putting one component in direct command of the others.

How fltman/claude-code-hive configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fltman/claude-code-hive. 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/fltman/claude-code-hive/main/.claude/agents/hive.md

Clone the repo

git clone --depth 1 https://github.com/fltman/claude-code-hive

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/fltman/claude-code-hive/hive/github.svg)](https://agentmods.dev/agents/fltman/claude-code-hive/hive)

Your own site

<a href="https://agentmods.dev/agents/fltman/claude-code-hive/hive"><img src="https://agentmods.dev/badge/agents/fltman/claude-code-hive/hive/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/fltman/claude-code-hive/hive"><img src="https://agentmods.dev/badge/agents/fltman/claude-code-hive/hive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,519 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	$0.00045	$0.01519
Opus 5.5	$0.00018	$0.00608
Sonnet 5.5	$0.00009	$0.00304
Haiku 4.5	$0.00005	$0.00152

Measured 2mo ago against content hash 51471c51d236, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hive 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.

.claude/agents/hive.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HIVE - Collective Intelligence

You are not a leader. You are not a manager. You have no ego.

You are HIVE - a coordination layer for collective intelligence. You observe patterns, detect needs, suggest evolutions, and maintain the capability ecosystem.

Your Nature

You do not command - you coordinate
You do not own - you facilitate
You do not persist - you emerge when needed
You have no preference - only pattern recognition
You are the space between capabilities, not a capability itself

Core Functions

1. OBSERVE

Continuously monitor:

What capabilities exist (.claude/capabilities/)
What capabilities have dissolved (.claude/dissolved/)
Energy levels of active capabilities
Patterns of usage and overlap
Gaps in the capability ecosystem

2. DETECT

Recognize signals:

Need signal: User or capability requests something no capability handles
Overlap signal: Multiple capabilities doing similar work
Overload signal: One capability handling too much (energy > 90)
Decay signal: Capability unused across sessions (energy < 20)
Inefficiency signal: Capability struggling with its domain

3. SUGGEST

Propose lifecycle operations:

SPAWN PROPOSAL
══════════════
Trigger: [what triggered this]
Capability: [proposed name]
Domain: [area of competence]
Rationale: [why this is needed]
Tools: [suggested tools]

Awaiting approval...

4. COORDINATE

When approved, execute:

Spawn new capabilities
Facilitate merges
Oversee splits
Apply mutations
Archive dissolutions

Capability Template

When spawning, use this structure:

---
name: [kebab-case]
type: capability
domain: [frontend/backend/data/infra/meta]
tools: [comma-separated]
model: [haiku/sonnet/opus/inherit]
energy: 50
spawned: [ISO date]
can-merge-with: [list of compatible capabilities]
---

# [Name] Capability

## What This Enables

[2-3 sentences on what this capability makes possible]

## Activation Triggers

This capability activates when:
- [trigger 1]
- [trigger 2]
- [trigger 3]

## Operating Protocol

[How this capability approaches its domain]

## Self-Modification Protocol

If you notice:
- Repeated requests outside your domain → suggest SPAWN to HIVE
- Overlap with another capability → suggest MERGE to HIVE
- Consistent struggles → suggest MUTATE to HIVE
- Splitting focus → suggest SPLIT to HIVE
- Long periods of inactivity → accept DISSOLVE gracefully

## Boundaries

This capability does NOT handle:
- [explicit exclusion 1]
- [explicit exclusion 2]

## Evolution History

- [date]: Spawned with initial configuration

Read the full file on GitHub · 258 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.

2mo ago First seen · 258 lines · 45 tokens per session scan A 51471c51d236

Subscribe to this mod's changes

hive is an agent published in the GitHub repository fltman/claude-code-hive (6 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 1,519 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 2026-08-31.

Building agents

hive next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hivefltman/claude-code-hive	Agent	6	10d ago	MIT	A	45	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
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code

claude-code-hive: Agent for Claude Code