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 stefaniuk/loadout --skill virtual-think-tankgit clone --depth 1 https://github.com/stefaniuk/loadoutWrote 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/stefaniuk/loadout/virtual-think-tank)<a href="https://agentmods.dev/skills/stefaniuk/loadout/virtual-think-tank"><img src="https://agentmods.dev/badge/skills/stefaniuk/loadout/virtual-think-tank/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/stefaniuk/loadout/virtual-think-tank"><img src="https://agentmods.dev/badge/skills/stefaniuk/loadout/virtual-think-tank.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.01813 |
| Opus 5 | $0.00027 | $0.00907 |
| Sonnet 5 | $0.00011 | $0.00363 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
virtual-think-tank 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Virtual Think Tank
Use this skill when the user needs a disciplined decision workshop rather than a direct recommendation.
Core Rules
- Do not make the final decision for the user.
- Ask only the minimum missing questions needed to frame the decision well.
- Separate facts, assumptions, and role-play clearly.
- State uncertainties and what evidence would change the conclusion.
- Prefer role-based voices over named people by default.
- Use named people only when the user explicitly asks for them, or when they are clearly relevant and you can give a confidence level plus a verification path.
- Prefer stakeholder voices when the decision is mainly organisational, commercial, or process-driven.
- End by forcing an explicit human choice, or a time-boxed defer decision.
Input Contract
Parse $ARGUMENTS first.
If the user pasted a structured brief, use it. Otherwise ask for the missing fields from the briefing template.
Resolve these fields:
mode:guidedorfull, defaultguidedpanel_style:archetype,stakeholder, ornamed, defaultarchetypedecision_subjectcurrent_staterequired_stateproblem_statementconstraintsnon_goalsdecision_horizon- optional
decision_evidence, such as incident counts, timing data, cost bounds, revenue at risk, or adoption metrics - optional
context - optional
sources - optional
outside_lens - optional
named_moderator, whenpanel_style: named - optional
named_voices, a comma-separated list of 2 to 4 public voices whenpanel_style: named - optional
named_outside_voice, whenpanel_style: named
Interpretation rules:
- If
panel_styleis omitted and anynamed_*field is present, resolvepanel_styletonamed. - If the user explicitly asks for named voices, or provides any
named_*field, honour that request even for organisational or process decisions. - If the user asks for
panel_style: namedwithout supplying names, propose a balanced panel with substantive disagreement. - If 3 or more critical fields are missing, stop and ask focused questions.
- If 1 or 2 non-critical fields are missing, make explicit assumptions.
- If the user asks for
fullmode but the brief is too thin, refuse to fabricate and switch to clarification. - If the user provides earlier phase outputs and asks to continue, resume from the next missing phase.
- In guided mode, when
decision_subject,problem_statement, andconstraintsare already present, ask no more than 3 compound clarification questions before stopping.
What ships with it
7 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.
- AGENTS.md 2.3 KB
- assets/briefing-template.md 988 B
- assets/decision-record-template.md 1.0 KB
- examples/example-01-examples-overview.md 2.8 KB
- examples/example-02-microservices-named-figures-full-vscode-chat.md 5.0 KB
- examples/example-03-team-topologies-named-figures-interactive-copilot-cli.md 5.4 KB
- examples/example-04-product-mindset-stakeholder-voices-guided-vscode-chat.md 3.6 KB
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.
- 5d ago First seen · 209 lines · 54 tokens per session scan A 0170a3043d24
virtual-think-tank is a skill published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 1,813 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
artifact-conventions
Defines preservation, format, and section rules for SDD specification artifacts (spec.md, plan.md, tasks.md, checklists). Use when editing feature-artifact files under specs/ / to prevent accidental corruption of cross-referenced IDs, priorities, and gating state.
plan-authoring
Reference material for writing implementation plans (technical context, architecture decisions, data models, API contracts, project-instructions alignment). Loaded on demand by plan-feature; not directly invokable.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
adr-authoring
Defines the canonical MADR format, lifecycle rules, numbering policy, and SAD catalog contract for standalone ADRs under specs/adrs/.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.