Daem0n-MCP: Skill for Claude Code

.claude/skills/daem0nmcp-protocol/SKILL.md

daem0nmcp-protocol is a skill for Claude Code from 9thLevelSoftware/Daem0n-MCP. It costs 44 tokens per session (2,642 once invoked), scanned A, original, MIT.

A set of rules for using Daem0nMCP memory and workflow tools. Daem0nMCP is a system for checking context, recording decisions, and reviewing results during an agent session.

In plain words
What is it for?
Use it when Daem0nMCP tools are available to start sessions, seek pre-change advice, save decisions, understand code, inspect related information, and review outcomes.
Why use it?
It reduces forgotten decisions and unchecked changes by requiring preparation, recording, and verification at defined points.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is 9thLevelSoftware/Daem0n-MCP's own configuration. It tells Claude Code how to work on Daem0n-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Daem0n-MCP configures →

Part of the daem0nmcp plugin — 3 skills, 4 commands, 3 agents, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to 9thLevelSoftware/Daem0n-MCP. 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/9thLevelSoftware/Daem0n-MCP/main/.claude/skills/daem0nmcp-protocol/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/9thLevelSoftware/Daem0n-MCP

Made for: Claude Code.

Or install daem0nmcp, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 3 agents, 1 MCP server.

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.

agentmods badge for daem0nmcp-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/9thlevelsoftware/daem0n-mcp/daem0nmcp-protocol.svg)](https://agentmods.dev/skills/9thlevelsoftware/daem0n-mcp/daem0nmcp-protocol)
Your own site
<a href="https://agentmods.dev/skills/9thlevelsoftware/daem0n-mcp/daem0nmcp-protocol"><img src="https://agentmods.dev/badge/skills/9thlevelsoftware/daem0n-mcp/daem0nmcp-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,642 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.02642
Opus 5 $0.00022 $0.01321
Sonnet 5 $0.00009 $0.00528
Haiku 4.5 $0.00004 $0.00264

Measured 7d ago against content hash 7759f6c317aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

daem0nmcp-protocol 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 7d 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/skills/daem0nmcp-protocol/SKILL.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Daem0n's Protocol

Overview

When Daem0nMCP memory tools are available, you MUST follow this protocol. Memory without discipline is noise.

Core principle: Check before you change, record what you decide, track whether it worked.

Tool Detection

First, verify Daem0nMCP tools are available:

Look for these 8 workflow tools in your available tools:
- mcp__daem0nmcp__commune      (session start & status)
- mcp__daem0nmcp__consult      (pre-action intelligence)
- mcp__daem0nmcp__inscribe     (memory writing & linking)
- mcp__daem0nmcp__reflect      (outcomes & verification)
- mcp__daem0nmcp__understand   (code comprehension)
- mcp__daem0nmcp__govern       (rules & triggers)
- mcp__daem0nmcp__explore      (graph & discovery)
- mcp__daem0nmcp__maintain     (housekeeping & federation)

If tools are NOT available: This skill does not apply. Proceed normally.

If tools ARE available: Follow the protocol below. No exceptions.

The Protocol

1. SESSION START (Non-Negotiable)

IMMEDIATELY when you have daem0nmcp tools:

mcp__daem0nmcp__commune(action="briefing")

DO NOT:
- Ask user what they want first
- Skip briefing because "it's a quick task"
- Assume you remember from last session

The briefing loads:

  • Past decisions and their outcomes
  • Warnings and failed approaches to AVOID
  • Patterns to FOLLOW
  • Git changes since last session

2. BEFORE ANY CODE CHANGES

BEFORE touching any file:

mcp__daem0nmcp__consult(action="preflight", description="what you're about to do")

OR for specific files:

mcp__daem0nmcp__consult(action="recall_file", file_path="path/to/file")

If preflight returns:

  • WARNING: You MUST acknowledge it to the user
  • FAILED APPROACH: Explain how your approach differs
  • must_not: These are HARD CONSTRAINTS - do not violate

3. AFTER MAKING DECISIONS

AFTER every significant decision:

memory_result = mcp__daem0nmcp__inscribe(
    action="remember",
    category="decision",  # or "pattern", "warning", "learning"
    content="What you decided",
    rationale="Why you decided it",
    file_path="relevant/file.py",  # optional
    tags=["relevant", "tags"]
)

SAVE THE MEMORY ID - you need it for reflect(action="outcome")

Read the full file on GitHub · 352 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.

  1. 7d ago First seen · 352 lines · 44 tokens per session scan A 7759f6c317aa

Subscribe to this mod's changes

daem0nmcp-protocol is a skill published in the GitHub repository 9thLevelSoftware/Daem0n-MCP (73 stars, last pushed 28d ago), licensed MIT. It adds 44 tokens to every session and 2,642 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens