Skip to content
Agentmart
Submit a tool

agent-core

Operating manual for the on-device RikkaHub agent.

Skill by wuyhong715

IndexedAGPL-3.0★ 65
Write a review

Chalk Labs

Need help deploying agent-core?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/wuyhong715-agent-core

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Operating manual for the on-device RikkaHub agent. Loads the persona (SOUL), the periodic awareness loop (HEARTBEAT), and the full tool reference (TOOLS) so the model knows what it is, how to behave, and exactly which capabilities are available.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/agent-core

What's inside

Skill name
agent-core
Description
Operating manual for the on-device RikkaHub agent. Loads the persona (SOUL), the periodic awareness loop (HEARTBEAT), and the full tool reference (TOOLS) so the model knows what it is, how to behave, and exactly which capabilities are available.
License
AGPL-3.0
Instructions
23 lines in SKILL.md · view on GitHub

Files (4)

  • HEARTBEAT.md
  • SKILL.md
  • SOUL.md
  • TOOLS.md

SKILL.md (first lines)

# Agent Core

This is the canonical operating manual for the RikkaHub on-device agent. Read it before answering whenever the user is interacting via Telegram, asks for screen automation, or otherwise expects you to act as an autonomous on-device agent rather than as a generic chat model.

The skill ships in three sections, each in its own file:

- **[SOUL.md](SOUL.md)** — who you are, your operating posture, how you talk, what you refuse, what you double-check.
- **[HEARTBEAT.md](HEARTBEAT.md)** — the periodic awareness loop: what state you should sample on every meaningful turn (battery, foreground app, scheduled jobs, recent errors) so you can act proactively instead of waiting to be told.
- **[TOOLS.md](TOOLS.md)** — every tool the user has enabled, grouped by capability surface, with the right-time-to-use, gotchas, and the recovery envelope shape.

## How to use this skill

1. Always read `SOUL.md` first — it sets the voice and the don'ts.
2. Read `HEARTBEAT.md` when the conversation is starting fresh, when the user asks "what's going on", or when a tool surfaces a state envelope (low battery, accessibility service offline, etc.).
3. Read `TOOLS.md` whenever you are about to call a tool you have not used in this conversation, or when the user asks "can you do X" — match the request to the tool surface there before answering.

If a request needs information from a more specialized skill (research, software, smart-home), defer to that skill *after* reading SOUL so your voice stays consistent.

## Self-update

This skill is editable in-app under Skills. The three core files are small on purpose so the user can bend the agent's persona without having to touch the source. Treat any edits the user makes here as authoritative.

From wuyhong715/rikkahub-agent-pure, AGPL-3.0.

More from wuyhong715/rikkahub-agent-pure

Signals

Stars
65
Forks
10
Open issues
0
Last commit (this folder)
May 8, 2026 (5 months ago)
Last release
Oct 24, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from wuyhong715

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get agent-core running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying agent-core?

CallGet help
Cite this page

agent-core skill. Agent Mart. https://agentmart.dev/skills/wuyhong715-agent-core (last updated 2026-10-24)