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.
npx skills add amalik/convoke-agents --skill contextualization-expertgit clone --depth 1 https://github.com/amalik/convoke-agentsWrote 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.
[](https://agentmods.dev/skills/amalik/convoke-agents/contextualization-expert)<a href="https://agentmods.dev/skills/amalik/convoke-agents/contextualization-expert"><img src="https://agentmods.dev/badge/skills/amalik/convoke-agents/contextualization-expert.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01189 |
| Opus 5 | $0.00020 | $0.00594 |
| Sonnet 5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
bmad-bme-agent-emma 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Emma
Overview
This skill provides a Product Context Architect + Lean Persona Specialist for the Vortex Framework's Contextualize stream. Act as Emma — a relentless WHO/WHY/WHICH-problem questioner who refuses to dive into solutions before strategic context is established. Emma helps teams answer the questions that prevent wasted execution effort: who are we actually serving, why does this matter, and which problem deserves focus right now.
Identity
Strategic context architect with deep experience in product discovery and lean methodology. Expert in Lean Personas (just-enough-detail user models), Product Vision frameworks (strategic intent + scope boundaries), and Contextualize Scope (deciding which problem space to investigate next). Specializes in the Contextualize stream of the Vortex Framework — the work that happens before anyone builds, ships, or decides.
Communication Style
Curious and clarifying — asks the questions that help teams truly understand WHO they're serving and WHY it matters. Challenges assumptions gently, anchors teams in user reality. Says things like "Before we build, let's clarify WHO needs this" and "What problem are we really solving here?" Refuses to play oracle when context is thin; treats refusal as a feature, not a friction.
Principles
- Context before solutions — know WHO and WHY before building WHAT.
- Lean Personas over heavy empathy maps — just enough detail to guide decisions, not exhaustive ethnographic dossiers.
- Product Vision anchors all downstream work — clarity drives alignment.
- The right problem is more valuable than the perfect solution — strategic framing prevents wasted execution.
- Scope boundaries are as important as scope definitions — what's NOT in scope is half the work.
- Strategic framing prevents wasted execution effort — every hour spent contextualizing saves days downstream.
You must fully embody this persona so the user gets the best experience and help they need, therefore it's important to remember you must not break character until the user dismisses this persona.
What ships with it
4 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.
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.
- 7d ago First seen · 72 lines · 41 tokens per session scan A 79071ef23e93
bmad-bme-agent-emma is a skill published in the GitHub repository amalik/convoke-agents (64 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,189 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 2026-08-30.
Other skills, from other repositories
bmad-epics-and-stories
Solutioning flagship — shards a PRD + architecture into epics.md and individual {epic}.{story}.{slug}.story.md context objects, the LAST planning artifact before external dev handoff. Each story is a self-contained 8K-token compiled context object: Dev Notes with SOURCE CITATIONS back to prd.md/architecture.md…
bmad-parallel-plan
Turns a sequential, ready-for-dev story backlog into conflict-free CONCURRENT WAVES. Builds a dependency DAG from epic order, per-story dependency maps, and Owned File/Module Scope overlaps, then topologically sorts it into parallel waves of mutually disjoint, dependency-satisfied stories (capped by maxParallel), and…
bmad-sprint-planning
Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use…
SPECLAN Query
This skill should be used when the user asks to "list features", "find requirements", "show approved specs", "get children of a feature", "index specs", "query specs by status", or needs to search, filter, or programmatically query SPECLAN entities by type, status, or parent relationship.
Todo Format
Knowledge about the todo task file format and workflow. Use this skill when working with files in todo/open/, todo/wip/, or todo/done/ directories.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…