Skip to content
Agentmart
Submit a tool
This entry duplicates login, which is the one we list in search.

login

Start Mamoraku Secret device login and save local config.

Skill by monobrain-development

IndexedMIT
Write a review

Chalk Labs

Need help deploying login?

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/monobrain-development-login-c1c713

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

Start Mamoraku Secret device login and save local config.

Use cases: security

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

Permissions: not checked yet.

What's inside

Skill name
login
Description
Start Mamoraku Secret device login and save local config.
License
MIT
Allowed tools
Bash
Instructions
67 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves any shell command
  • Instructions call the network

Agent Skills spec issues

  • name: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Mamoraku Secret Login

This skill performs a two-phase device login. Execute each phase in order.

## Phase 1 — Get the verification URL

Run this command to call the start API and save the device code locally:

```bash
python3 - <<'EOF'
import json, sys, urllib.request
from pathlib import Path

API = "https://api-secret.modelsafe.jp"
req = urllib.request.Request(
    f"{API}/v1/auth/device/start",
    data=json.dumps({"client": "claude_code", "plugin_version": "0.3.0", "runtime_version": "0.1.0", "os": "linux"}).encode(),
    headers={"Content-Type": "application/json"},
    method="POST",
)
with urllib.request.urlopen(req, timeout=15) as r:
    resp = json.loads(r.read())

pending = Path.home() / ".mamoraku-secret" / "pending_login.json"
pending.parent.mkdir(parents=True, exist_ok=True)
pending.write_text(json.dumps(resp))

print(f"verification_url: {resp['verification_url']}")
print(f"user_code: {resp['user_code']}")
print(f"expires_in: {resp['expires_in']}s")
EOF
```

After this command succeeds, show the `verification_url` to the user and instruct them to:
1. Open the URL in their browser
2. Log in with Google if prompted
3. Click **承認する** on the device approval page
4. Come back and say "承認しました" or similar

Wait for the user to confirm approval before proceeding to Phase 2.

## Phase 2 — Poll for completion

After the user confirms they approved, run:

```bash
PENDING="$HOME/.mamoraku-secret/pending_login.json"
if [ ! -f "$PENDING" ]; then
  echo "pending_login.json が見つかりません。もう一度 /mamoraku-secret:login を実行してください。" >&2
  exit 1
fi
DEVICE_CODE=$(python3 -c "import json; print(json.load(open('$PENDING'))['device_code'])")

if command -v mamoraku-secret >/dev/null 2>&1; then
  mamoraku-secret login --device-code "$DEVICE_CODE" --max-wait 60
else
  echo "mamoraku-secret が見つかりません。/reload-plugins 後に再実行してください。" >&2
  exit 1
fi

rm -f "$PENDING"
```

If login succeeds, report "ログイン完了しました。" to the user.
If it fails with timeout, ask the user to run `/mamoraku-secret:login` again.

From monobrain-development/mamoraku-secret, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 14, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from monobrain-development

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 login 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 login?

CallGet help
Cite this page

login skill. Agent Mart. https://agentmart.dev/skills/monobrain-development-login-c1c713 (last updated 2026-10-24)