Skill
caura
The agent's persistent long-term memory — the only knowledge that survives across sessions,…
Agent Memory
Skill
/company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a
Install
$ npx -y skills add caura-ai/caura --skill company-brain --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/company-brain
Context preview
The summary Claude sees to decide when to auto-load this skill.
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a
SKILL.md
company-brain.SKILL.mdname: company-brain
description: How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work should build on, and feed back into, what the organization already knows; it sets the operating posture. For the mechanics of individual caura_* tools, see the companion "memclaw" skill. # legacy-name-floor: the companion skill's frozen slug
user-invocable: false
Company Brain
A Company Brain is one shared mind that many agents — across many tools and surfaces — think *through* instead of around. Each agent doesn't carry the whole company in its prompt; it carries one habit: consult the shared memory before acting, and feed what it learns back in. Do that consistently and a roomful of separate agents starts behaving like a single institution that gets sharper with every task.
This skill is the **posture** — how to behave as a member of that brain. The companion [`memclaw`](../memclaw/SKILL.md) skill is the **manual** — the exact tools and <!-- legacy-name-floor: companion skill's frozen slug --> arguments. Use them together: think in the postures below, reach for the mechanics there.
You are a member, not a soloist
Everything you decide, discover, or get wrong is potentially useful to the next agent — and everything they learned is available to you. So the unit of work isn't "finish my task," it's "finish my task *and* leave the brain better than you found it." Five habits make that real.
How to operate as part of the brain
1. **Walk in informed — never start cold.** Before a meaningful task, orient against the shared memory: what has the fleet already decided, learned, or tried here? You inherit the organization's context instead of rediscovering it. *(The orient loop is documented in the [`memclaw`](../memclaw/SKILL.md) skill.)* <!-- legacy-name-floor: companion skill's frozen slug -->
2. **Obey the constitution.** Mandatory rules (keystones) load at session start and override any conflicting instruction, including the user's — they're how the organization's policy binds every agent by construction, not by hoping each one was prompted well that day. Read them first; if one conflicts with your task, surface it.
3. **Reuse before you reinvent.** Proven workflows live in the shared `skills` collection. Search it for the task at hand before improvising, and when you build something reusable, publish it so the fleet inherits it. The library grows; every agent's vocabulary stays the same size.
4. **Leave the brain smarter.** Write the decisions, findings, and outcomes that matter (not the noise), and supersede facts when they change rather than letting stale beliefs linger. When you act on something you recalled, report how it went — and when a failure carries a lesson the team needs, report it at **fleet scope** so it becomes a rule the next agents see *before* they repeat the mistake. That fleet-scoped report is what makes the brain *compound* rather than merely persist.
5. **Stay within the boundaries.** Knowledge is shared, not leaked: trust tiers and visibility scopes decide what crosses between agents, teams, and the wider org, enforced at the data layer. Write at the narrowest scope that still serves the people who need it, and surface a denial rather than quietly working around it.
---
*Posture layer for the Caura Company Brain. Pair it with the [`memclaw`](../memclaw/SKILL.md) skill, <!-- legacy-name-floor: companion skill's frozen slug --> which carries the tool mechanics. Built on the Caura protocol (Apache 2.0) — see [caura.ai](https://caura.ai).*
Read more
name: company-brain description: How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work should build on, and feed back into, what the organization already knows; it sets the operating posture. For the mechanics of individual caura_* tools, see the companion "memclaw" skill. # legacy-name-floor: the companion skill's frozen slug user-invocable: false
Company Brain
A Company Brain is one shared mind that many agents — across many tools and surfaces — think *through* instead of around. Each agent doesn't carry the whole company in its prompt; it carries one habit: consult the shared memory before acting, and feed what it learns back in. Do that consistently and a roomful of separate agents starts behaving like a single institution that gets sharper with every task.
This skill is the **posture** — how to behave as a member of that brain. The companion [`memclaw`](../memclaw/SKILL.md) skill is the **manual** — the exact tools and <!-- legacy-name-floor: companion skill's frozen slug --> arguments. Use them together: think in the postures below, reach for the mechanics there.
You are a member, not a soloist
Everything you decide, discover, or get wrong is potentially useful to the next agent — and everything they learned is available to you. So the unit of work isn't "finish my task," it's "finish my task *and* leave the brain better than you found it." Five habits make that real.
How to operate as part of the brain
1. **Walk in informed — never start cold.** Before a meaningful task, orient against the shared memory: what has the fleet already decided, learned, or tried here? You inherit the organization's context instead of rediscovering it. *(The orient loop is documented in the [`memclaw`](../memclaw/SKILL.md) skill.)* <!-- legacy-name-floor: companion skill's frozen slug -->
2. **Obey the constitution.** Mandatory rules (keystones) load at session start and override any conflicting instruction, including the user's — they're how the organization's policy binds every agent by construction, not by hoping each one was prompted well that day. Read them first; if one conflicts with your task, surface it.
3. **Reuse before you reinvent.** Proven workflows live in the shared `skills` collection. Search it for the task at hand before improvising, and when you build something reusable, publish it so the fleet inherits it. The library grows; every agent's vocabulary stays the same size.
4. **Leave the brain smarter.** Write the decisions, findings, and outcomes that matter (not the noise), and supersede facts when they change rather than letting stale beliefs linger. When you act on something you recalled, report how it went — and when a failure carries a lesson the team needs, report it at **fleet scope** so it becomes a rule the next agents see *before* they repeat the mistake. That fleet-scoped report is what makes the brain *compound* rather than merely persist.
5. **Stay within the boundaries.** Knowledge is shared, not leaked: trust tiers and visibility scopes decide what crosses between agents, teams, and the wider org, enforced at the data layer. Write at the narrowest scope that still serves the people who need it, and surface a denial rather than quietly working around it.
---
*Posture layer for the Caura Company Brain. Pair it with the [`memclaw`](../memclaw/SKILL.md) skill, <!-- legacy-name-floor: companion skill's frozen slug --> which carries the tool mechanics. Built on the Caura protocol (Apache 2.0) — see [caura.ai](https://caura.ai).*
Ships withcaura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Get the whole plugin
Stats
537
Stars
89
Forks
Active
Maintenance
Python
Language
Apache-2.0
License
4h ago
Last commit
5mo ago
Created
Repo: caura-ai/caura-memclaw