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 agents/marlburrow/hivekeep/overviewgit clone --depth 1 https://github.com/MarlBurroW/hivekeepWhat 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 | $0.00008 | $0.00623 |
| Opus 5 | $0.00004 | $0.00311 |
| Sonnet 5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
overview 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents are Hivekeep's core concept: persistent AI agents that live on your server, remember everything, and work as a team.
Unlike disposable chatbot sessions, an Agent has:
- A permanent identity: name, role, personality, expertise, avatar
- Continuous memory: every conversation is remembered forever through vector + full-text search
- A continuous session: there's no "new conversation"; the session never resets
- Collaboration skills: Agents talk to each other, delegate tasks, and spawn sub-agents
- Autonomy: cron jobs, webhooks, and channel integrations let them work while you sleep
Anatomy of an Agent
When you create an Agent, you define:
| Field | Purpose |
|---|---|
| Name | Display name (e.g. "Atlas") |
| Slug | Unique identifier for inter-Agent communication (e.g. atlas) |
| Role | One-line description of what it does (e.g. "Infrastructure specialist") |
| Character | Personality traits and communication style |
| Expertise | Domain knowledge and capabilities |
| Model | Which LLM to use (from your configured providers) |
| Provider | Which AI provider to use (optional, defaults to instance default) |
| Avatar | Visual identity in the UI |
How they work
- Messages queue: each Agent has its own priority queue. User messages are processed before automated ones (cron, webhooks, inter-Agent). Within the same priority, messages are processed in order.
- System prompt: Hivekeep builds a rich system prompt from the Agent's identity, its memory profile, contacts directory, Agent directory, active channels, and platform directives.
- Memory: the curated profile is always present in the prompt; the episodic archive is searched on demand by the Agent with
recall. - Session compacting: when the conversation gets too long for the model's context window, older messages are summarized into a snapshot. Original messages are always preserved in the database, so no data is lost.
- Tool execution: Agents have access to 100+ built-in tools plus MCP servers and custom tools.
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.
- 2d ago First seen · 52 lines · 8 tokens per session scan A 4f468d4c855a
overview is an agent published in the GitHub repository MarlBurroW/hivekeep (51 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 623 once invoked, about $0.0000 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 agents, from other repositories
planner
복잡한 기능·아키텍처 변경·멀티스텝 리팩토링 구현 계획 전문. 요구사항 인터뷰 → 코드베이스 조사 → 3-6단계 plan.md 생성 + 인수 기준 포함. NEVER 구현. Use proactively when "구현 계획", "설계해줘", "어떻게 만들지", "spec 작성"처럼 코드 작성 전 계획이 필요한 시점. 발산 아이디어가 필요하면 dev-brainstormer 먼저, 아키텍처 판단은 architect 사용.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
refactor-cleaner
데드 코드·미사용 exports·의존성 제거, 중복 통합 전문. knip/depcheck/ts-prune 감지 → Grep 참조 검증 → 안전 제거. 피처 브랜치에서만 동작. Use proactively when "데드 코드", "미사용 코드", "정리해줘", "클린업", "리팩토링" 요청 시. 빌드 에러 수정은 build-error-resolver, 새 기능은 tdd-guide 사용.
systematic-debugger
Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…
defining-agents
Agent "defining-agents" from sixb-ai/sixb, covering defining agents, config, the model, instructions vs agent skills and tools.