Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

M0

BSecurity

Use when the user says 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', or 'where is my memory stored', or when the M0 daemon or MCP wiring needs attention.

477 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsrustbashapibackend

Works with

apimcp

Security Analysis

B88/100
criticalSends environment variables or credentials to an external URL

Pro scans all 3 files and shows the line behind each finding

Scanned 10/7/2026

$npx -y skills add coco-research/coco --skill m0 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of M0?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for M0
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/coco-research-coco-coco/badge)](https://www.skillsdirectory.com/skills/coco-research-coco-coco)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: m0
description: "Use when the user says 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', or 'where is my memory stored', or when the M0 daemon or MCP wiring needs attention."
---

# /m0 — Cross-Tool Agent Memory

M0 keeps one local *operational thread* per project: what was done, what was
verified, what is next. Any tool can write to it and read it back, so a session
that starts cold can continue work another tool began.

The live M0 is the Rust daemon `coco-m0d`, serving `127.0.0.1:8000` under the
launchd job `com.coco.m0-backend`. The write path is `/m0-remember`, the read
path is `/m0-recall`, and the session handoff flow is `/m0-handoff`.

The token is read from ~/.coco/m0-token on each call; never print it.

## Quick Reference

```bash
M0="${COCO_M0_URL:-http://127.0.0.1:8000}"     # daemon base URL

# Is it up? (health needs no token)
curl -s "$M0/api/health"

# Is the launchd job loaded?
launchctl list | grep com.coco.m0-backend

# Everything else needs the token, for example the recent thread:
curl -s -H "Authorization: Bearer $(cat ~/.coco/m0-token)" \
  "$M0/api/brain/thread?project=my-project&limit=5"
```

There is no offline path: if the daemon is down, say so and stop; do not write anywhere else.

## Sub-commands

### /m0 status — is memory working

```bash
M0="${COCO_M0_URL:-http://127.0.0.1:8000}"
curl -s "$M0/api/health"
launchctl list | grep com.coco.m0-backend
```

Report to the user, in this order:

1. **Daemon** — reachable at `$M0` or not.
2. **launchd** — whether the job `com.coco.m0-backend` is loaded and running.

If either is missing, tell the user and stop. Do not work around it.

### /m0 start — you do not start it

The daemon runs under launchd; if it is down, tell the user and stop (restarts
and deploys are the owner's).

### /m0 mcp — the MCP tool

The daemon's MCP binary `coco-platform-mcp` exposes one tool, `m0`, with modes
`recall`, `context`, `wip`, `handoff`, and `remember`. Call it directly — it is
the lowest-friction way to make memory habitual.

### /m0 verify — prove it works

```bash
curl -s "$M0/api/health"
```

A healthy response means the daemon is serving. Quote the output rather than
summarising it.

### /m0 privacy — what leaves the machine

Nothing. The daemon binds to loopback, there are no outbound calls in the
request path and no telemetry. Text fields are capped at 400 characters and
redacted by the daemon before storage.

## When to reach for this

- **Use `/m0-recall`** at the start of a session, or when picking up work started
  elsewhere, before asking the user to repeat context.
- **Use `/m0-remember`** after a step lands, a decision is made, or something is
  verified.
- **Use `/m0-handoff`** before context is compacted or a session ends.
- **Use `/m0` (this skill)** for the plumbing: daemon, token, wiring.

M0 answers "where were we and what is next". For deeper knowledge-graph
retrieval see the comparison with the cognee bundle in `systems/m0/README.md`
before choosing.

Attribution

coco-researchcoco-research
View sourceSee grades on GitHubMore from coco-research →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →