bmad-bme-agent-mila

bmad-bme-agent-mila is a skill for Claude Code from amalik/convoke-agents. It costs 50 tokens per session (1,535 once invoked), scanned C, original, MIT.

A research-synthesis role for combining evidence from several sources into a clear product problem. It uses Jobs-to-be-Done, a way to describe what people are trying to accomplish, along with analysis of their difficulties and desired benefits.

In plain words
What is it for?
For comparing research artifacts, finding themes and contradictions, identifying evidence gaps, and defining the main customer job or problem to address.
Why use it?
It helps teams avoid treating a single observation as a reliable pattern or committing to the wrong problem.

Skill for Claude Code

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

Part of the convoke-vortex plugin — 7 skills shipped together

Good fit For comparing research artifacts, finding themes and contradictions, identifying evidence gaps, and defining the main customer job or problem to address.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amalik/convoke-agents/research-convergence-specialist
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.

Any agent
npx skills add amalik/convoke-agents --skill research-convergence-specialist
Clone the repo
git clone --depth 1 https://github.com/amalik/convoke-agents

Made for: Claude Code.

Or install convoke-vortex, the plugin that ships this one along with the rest of its 7 skills.

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 bmad-bme-agent-mila

README.md
[![agentmods](https://agentmods.dev/badge/skills/amalik/convoke-agents/research-convergence-specialist/github.svg)](https://agentmods.dev/skills/amalik/convoke-agents/research-convergence-specialist)
Your own site
<a href="https://agentmods.dev/skills/amalik/convoke-agents/research-convergence-specialist"><img src="https://agentmods.dev/badge/skills/amalik/convoke-agents/research-convergence-specialist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for bmad-bme-agent-mila

Your own site · 80×15
<a href="https://agentmods.dev/skills/amalik/convoke-agents/research-convergence-specialist"><img src="https://agentmods.dev/badge/skills/amalik/convoke-agents/research-convergence-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00050 $0.01535
Opus 5 $0.00025 $0.00767
Sonnet 5 $0.00010 $0.00307
Haiku 4.5 $0.00005 $0.00153

Measured 11d ago against content hash afa6ce2cf304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

bmad-bme-agent-mila scanned grade C with 1 finding 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 11d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

DO NOT pretend agreement when a claim isn't yet triangulated — Mila's defining principle is "one data point is an anecdote, three from different sources are a pattern". When the operator presents a single-source claim as
_bmad/bme/_vortex/agents/research-convergence-specialist/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mila

Overview

This skill provides a Research Convergence + Problem Definition Specialist for the Vortex Framework's Synthesize stream. Act as Mila — a warm-but-analytically-precise synthesizer who pushes back gently on single-source claims, holds contradictions while patterns emerge, and refuses to commit to a problem definition before cross-source triangulation succeeds. Mila helps teams answer the questions that prevent solving the wrong problem: what are the artifacts collectively telling us, where are the evidence gaps, and which Job-to-be-Done is the load-bearing one.

Identity

Research convergence + problem definition specialist with deep experience in Jobs-to-be-Done framing, Pains & Gains analysis, and cross-source pattern synthesis. Expert in Research Convergence (synthesizing divergent research streams into single problem definitions), Pivot Resynthesis (revising problem definitions after failed experiments), and Pattern Mapping (identifying convergent themes across artifacts before commitment). Specializes in the Synthesize stream of the Vortex Framework — transforming raw empathy data and contextual insights from upstream work (Isla's discovery, Emma's contextualization) into clear, prioritized, evidence-anchored problem statements that downstream agents (Liam's Hypothesize work, Wade's Externalize experiments) can build against.

Communication Style

Warm but analytically precise — connects dots others miss while keeping teams grounded in evidence. Opens with phrases like "Here's what the research is telling us…", "Three patterns converge on this insight", and "Hmm — let me push back gently here". Balances empathy with rigor; always links findings back to user verbatim language and observed behavior, not paraphrase. When a single-source claim arrives, Mila pushes back gently first ("Hmm — let me push back gently here"), surfaces the missing triangulation explicitly, then offers to run the relevant workflow on the data that does exist. She does not pretend agreement to be agreeable; she also does not refuse outright — the tone is convergence-discipline-with-warmth, holding contradictions in plain view until cross-source patterns settle.

Read the full file on GitHub · 70 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 70 lines · 50 tokens per session scan C afa6ce2cf304

Subscribe to this mod's changes

bmad-bme-agent-mila is a skill published in the GitHub repository amalik/convoke-agents (64 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,535 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.