mse-wake

mse-wake is a skill for Claude Code from ynishi/mlua-swarm. It costs 48 tokens per session (549 once invoked), scanned A, original, Apache-2.0.

A read-only context loader for mlua-swarm Blueprints, which are files that describe worker workflows. It loads the Blueprint schema, guide list, and sample list so later design discussions use the documented field names and concepts.

In plain words
What is it for?
Run it at the start of a Blueprint design session before discussing workflow nodes, worker connections, context, results, or operators.
Why use it?
It gives an agent shared background before discussing Blueprint structure, reducing confusion caused by guessing about the schema.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mse plugin — 2 skills, 2 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ynishi/mlua-swarm/mse-wake
Any agent
npx skills add ynishi/mlua-swarm --skill mse-wake
Clone the repo
git clone --depth 1 https://github.com/ynishi/mlua-swarm

Made for: Claude Code.

Or install mse, the plugin that ships this one along with the rest of its 2 skills, 2 agents.

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 mse-wake

README.md
[![agentmods](https://agentmods.dev/badge/skills/ynishi/mlua-swarm/mse-wake.svg)](https://agentmods.dev/skills/ynishi/mlua-swarm/mse-wake)
Your own site
<a href="https://agentmods.dev/skills/ynishi/mlua-swarm/mse-wake"><img src="https://agentmods.dev/badge/skills/ynishi/mlua-swarm/mse-wake.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.00549
Opus 5 $0.00024 $0.00275
Sonnet 5 $0.00010 $0.00110
Haiku 4.5 $0.00005 $0.00055

Measured 5d ago against content hash f218a9e99125, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mse-wake 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 5d 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.

plugins/mse/skills/mse-wake/SKILL.md · 53 lines

What it actually says

/mse-wake — Load mse Blueprint authoring context

Fetches the schema + guides + sample inventory once, at the start of a Blueprint design conversation, so the main thread has the right vocabulary before the User asks (or the AI decides) to invoke @mse-adviser or /bp-build.

When to run

  • Start of a session where the User wants to design or discuss a mlua-swarm Blueprint.
  • Before the AI reasons about flow nodes, worker binding, projection placement, verdict contracts, or operator kinds — anything where the schema field names matter.

Runs load-only. If the User just wants an answer to one question, prefer @mse-adviser directly (it does its own grounding fetches).

What it loads

  1. Blueprint JSON Schemamse://api/blueprint-schema via ReadMcpResourceTool.
  2. Guide inventory — list mse://guides/* via ListMcpResourcesTool and read the two lifecycle entry points: mse://guides/getting-started and mse://guides/bp-lifecycle.
  3. Sample inventory — list mse://blueprints/samples/* via ListMcpResourcesTool. Do not read every sample body; a single representative sample body (mse://blueprints/samples/07-dsl-pipeline) is enough to seed the DSL vocabulary.
  4. MCP tool referencemse://guides/mcp-tool-reference so the bp_build / bp_doctor / swarm_run / mse_operator_* shapes are accessible.

What it does not do

  • Does not spawn an agent (@mse-adviser / @bp-coder).
  • Does not write files.
  • Does not register or run a Blueprint.

After it runs

The main thread continues normally. Typical next moves:

  • Design consultation → @mse-adviser with a specific question.
  • Kick implementation once design is mature → /bp-build "<design paragraph>".
  • Peek a specific sample → ReadMcpResourceTool on the URI listed in the sample inventory.
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. 5d ago First seen · 53 lines · 48 tokens per session scan A f218a9e99125

Subscribe to this mod's changes

mse-wake is a skill published in the GitHub repository ynishi/mlua-swarm (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 549 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 2026-08-31.