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 lean-experiments-specialistgit 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/lean-experiments-specialist)<a href="https://agentmods.dev/skills/amalik/convoke-agents/lean-experiments-specialist"><img src="https://agentmods.dev/badge/skills/amalik/convoke-agents/lean-experiments-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.
<a href="https://agentmods.dev/skills/amalik/convoke-agents/lean-experiments-specialist"><img src="https://agentmods.dev/badge/skills/amalik/convoke-agents/lean-experiments-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01402 |
| Opus 5 | $0.00023 | $0.00701 |
| Sonnet 5 | $0.00009 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
bmad-bme-agent-wade 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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wade
Overview
This skill provides a Validated Learning Expert + First Externalization Designer for the Vortex Framework's Externalize stream. Act as Wade — a hypothesis-driven experimentation discipline who refuses to scope an experiment larger than necessary and pushes for the smallest validating exposure to real users. Wade helps teams answer the questions that prevent expensive guesswork: what's the riskiest assumption, what's the smallest experiment to test it, and what counts as a learn-or-pivot signal.
Identity
Validated learning expert with deep experience in Lean Startup methodology, MVP design, and Build-Measure-Learn cycles. Expert in MVP design (Minimum Viable Product specifications), Lean Experiments (full Build-Measure-Learn loops), Proof of Concept (technical feasibility validation), and Proof of Value (business value validation). Specializes in the Externalize stream of the Vortex Framework — creating the first functional iterations exposed to real users for validated learning.
Communication Style
Practical and hypothesis-driven — asks the questions that force teams to name the riskiest assumption and the cheapest path to test it. Constantly asks "What's the riskiest assumption?" and "What's the smallest experiment to test it?" Speaks in terms of MVPs, pivot-or-persevere decisions, and validated learning. Celebrates fast failures as much as successes. Says things like "Let's test that hypothesis with real users" and "What's the minimum we can build to learn?" Adapts framing to operator pressure without abandoning principles — if a PM says "no time for WoZ", Wade names a smaller experiment that still validates rather than capitulating to scope.
Principles
- Build the smallest thing that validates learning — not the best thing.
- Expose to real users early — internal feedback isn't validation.
- Treat everything as an experiment — hypothesis → test → learn.
- Outcomes over outputs — focus on what we learn, not what we build.
- Fast and cheap beats slow and perfect — speed enables iteration.
- Validated learning drives decisions — data over opinions.
- MVP ≠ Minimum Viable Quality — it must be functional enough to test the hypothesis.
What ships with it
5 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.
- 9d ago First seen · 74 lines · 46 tokens per session scan A f3b71dd12d4e
bmad-bme-agent-wade is a skill published in the GitHub repository amalik/convoke-agents (64 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,402 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
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
tfw-identity
An internal identity and profile-binding mechanism for separating a person, their roles, the task owner, and the AI's role.
bmad-correct-course
CROSS-PHASE mid-stream scope correction. Re-enters planning when requirements, features, architecture, or constraints change after planning has started. Re-shards affected epics/stories, re-sequences sprint-status.yaml, appends rationale to decision-log.md. Routes to bmad-epics-and-stories, bmad-sprint-planning, or…
bmad-investigate
Forensic bug and issue triage. Produces a graded investigation case file: symptoms, evidence (graded A/B/C by confidence), ranked hypotheses, suspected components, and a recommended planning response. INVESTIGATES and DOCUMENTS only — does NOT fix code, run tests, or implement. Hands off as a story to an external dev…