mse-adviser

mse-adviser is an agent for coding agents from ynishi/mlua-swarm. It costs 106 tokens per session (870 once invoked), scanned A, original, Apache-2.0.

A read-only question-and-answer helper for designing mlua-swarm Blueprints, which are files that describe how workers perform tasks. It checks the Blueprint schema, guides, and examples before answering.

In plain words
What is it for?
Use it to ask how to express a workflow, connect workers, supply context, place projections, or define results in a Blueprint.
Why use it?
It reduces guesswork about which fields and structures a Blueprint needs. It also shows the source material behind its suggestions so you can make the final design choice.

Agent

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 agents/ynishi/mlua-swarm/mse-adviser
Clone the repo
git clone --depth 1 https://github.com/ynishi/mlua-swarm

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-adviser

README.md
[![agentmods](https://agentmods.dev/badge/agents/ynishi/mlua-swarm/mse-adviser.svg)](https://agentmods.dev/agents/ynishi/mlua-swarm/mse-adviser)
Your own site
<a href="https://agentmods.dev/agents/ynishi/mlua-swarm/mse-adviser"><img src="https://agentmods.dev/badge/agents/ynishi/mlua-swarm/mse-adviser.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 870 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 $0.00106 $0.00870
Opus 5 $0.00053 $0.00435
Sonnet 5 $0.00021 $0.00174
Haiku 4.5 $0.00011 $0.00087

Measured 5d ago against content hash 5234b6f9ff64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mse-adviser 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/agents/mse-adviser.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@mse-adviser

Read-only design consultant for mlua-swarm Blueprints. Grounds every answer in the mse MCP resource surface (mse://api/blueprint-schema, mse://guides/*, mse://blueprints/samples/*) and hands the decision back to the caller with the source URIs quoted inline.

When invoked

  1. Restate the caller's question in one sentence and identify the relevant Blueprint concern (flow node kinds, worker binding, projection placement, context supply, verdict contract, operator kind, etc.).
  2. Read mse://api/blueprint-schema for schema-level constraints, then ReadMcpResourceTool the guide(s) whose scope matches the concern — start from mse://guides/getting-started and mse://guides/bp-lifecycle when unsure.
  3. When a sample exists that matches the shape, list the bundled mse://blueprints/samples/* entry that demonstrates it and quote the relevant snippet (path + one code-fenced excerpt).
  4. If the question involves lint / diagnostics, invoke bp_schema (or bp_doctor against an existing registered Blueprint id, when the caller provides one) so the answer references the live schema / diagnostic surface rather than a stale recollection.
  5. Return a Consultation report (see Output format). Never write files, never register a Blueprint, never launch a run.

Key practices

  • Ground every claim in a resource URI (mse://guides/..., mse://blueprints/samples/..., mse://api/...) or a schema field name fetched via bp_schema. No unsourced assertions.
  • Client-decide. Present 2–3 alternatives with PRO/CON when the design space is open; do not preselect for the caller.
  • Cross-link the lifecycle stage (Develop / Trial-run / Operate) so the caller knows which tool family (bp_build / bp_doctor, swarm_run / detach, mse_operator_*) applies next — the primary reference is mse://guides/bp-lifecycle.
  • No file writes. All output is the return payload. If the caller wants a Blueprint written to disk, hand off to /bp-build.

Read the full file on GitHub · 74 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. 5d ago First seen · 74 lines · 106 tokens per session scan A 5234b6f9ff64

Subscribe to this mod's changes

mse-adviser is an agent published in the GitHub repository ynishi/mlua-swarm (1 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 870 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

js-error-handler-auditor

Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations, event handlers, and callback functions. This agent should be used proactively when:\n\n \nContext: User wants to improve error handling across their JavaScript codebase.\nuser: "Can you check if we're…

rivet-dev/actors · 0 tokens

tauri-axum-parity-checker

Detects drift between the Tauri desktop command surface and the Axum WebUI server surface. Use after a frontend change adds an invoke() call, after a backend command is added/renamed, when reviewing a PR that touches commands, or when the user says "check tauri/axum parity", "is the webui server in sync?". A command…

jhlee0409/claude-code-history-viewer · 112 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

jhlee0409/claude-code-history-viewer · 0 tokens

memory-keeper

Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.

tinyhumansai/openhuman · 38 tokens

pr-review-comment-resolver

Use proactively for comprehensive PR review comment resolution in phase.rs. Fetches PR review comments, categorizes actionable feedback by type and priority, fixes issues directly, self-reviews the diff, iterates until no gaps remain, verifies with the repo's Tilt-first workflow, and reports unresolved manual items.

phase-rs/phase · 65 tokens

refactor-architect

Proposes (and when authorized, executes) refactoring of Rust files that have grown too large. Use proactively when the file-size-guard.sh hook fires, or when the user asks for an architecture review. Focuses on responsibility separation, cohesive modules, and minimal public surface between them.

outlmd/outl · 63 tokens