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 elevanaltd/debate-hall-mcp --skill debate-hall-autogit clone --depth 1 https://github.com/elevanaltd/debate-hall-mcpWrote 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/elevanaltd/debate-hall-mcp/debate-hall-auto)<a href="https://agentmods.dev/skills/elevanaltd/debate-hall-mcp/debate-hall-auto"><img src="https://agentmods.dev/badge/skills/elevanaltd/debate-hall-mcp/debate-hall-auto/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/elevanaltd/debate-hall-mcp/debate-hall-auto"><img src="https://agentmods.dev/badge/skills/elevanaltd/debate-hall-mcp/debate-hall-auto.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 | $0.00022 | $0.01045 |
| Opus 5 | $0.00011 | $0.00522 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
debate-hall-auto 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 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.
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.
What it actually says
===DEBATE_HALL_AUTO===
META: TYPE::SKILL[FOCUSED] VERSION::"1.0" PURPOSE::"Automated debate orchestration via run_debate and resolve_question" ROUTER::debate-hall
§1::TOOLS
RUN_DEBATE::[ PURPOSE::"Single-call automated Wind/Wall/Door debate", PARAMS::[ topic::REQUIRED[question_or_decision], tier::"fast"|"standard"|"premium"[default:standard], thread_id::OPTIONAL[auto_generated_if_omitted], compression_tier::"none"|"basic"|"aggressive"|"ultra", primer_tier::"none"|"literacy"|"standard"|"advanced" ], RETURNS::synthesis+turn_count+status ]
RESOLVE_QUESTION::[ PURPOSE::"Highest-level API - debate + decision record in one call", PARAMS::[topic::REQUIRED,tier::OPTIONAL,thread_id::OPTIONAL], RETURNS::DecisionRecord[thread_id,synthesis,rationale,validation,provenance] ]
RESUME_DEBATE::[ PURPOSE::"Continue PAUSED debates after provider timeouts", PARAMS::[thread_id::REQUIRED,tier::OPTIONAL], USE_WHEN::status="PAUSED" ]
SEARCH_DECISIONS::[ PURPOSE::"Find past decisions by topic", PARAMS::[query::REQUIRED,limit::10,min_score::0.0], RETURNS::ranked_results[thread_id,topic,synthesis,score] ]
§2::TIER_CONFIGURATIONS
FAST::[ COST::~$0.02, MODELS::[gemini-3-flash,gpt-5.1-codex-mini,claude-haiku-4.5], MAX_TURNS::6, CONSENSUS::false, USE_FOR::[exploration,low_stakes,rapid_iteration] ]
STANDARD::[ COST::~$0.30, MODELS::[gemini-3-pro,gpt-5.2-codex,claude-sonnet-4.5], MAX_TURNS::12, REFINEMENT_LOOPS::4, USE_FOR::[design_decisions,medium_complexity] ]
PREMIUM::[ COST::~$0.60, MODELS::[claude-opus-4.5,gpt-5.2-pro,gemini-3-pro], MAX_TURNS::16, REFINEMENT_LOOPS::5, CONSENSUS::true, USE_FOR::[production_decisions,high_stakes] ]
§2.1::AGENT_ROLES // Restored from monolith §5
TIER_1_BASIC::[ AGENTS::[wind-agent,wall-agent,door-agent], BEHAVIOR::[explores_obvious_paths,balanced_judgment,balanced_integration], MAPPED_TO::fast_tier ] TIER_2_SPECIALIST::[ PATHOS::[ideator[minimal_elegant],edge-optimizer[hidden_vectors]], ETHOS::[validator[cold_truth],critical-engineer[production_readiness]], LOGOS::[synthesizer[breakthrough_1+1=3],technical-architect[system_design]], MAPPED_TO::standard_and_premium_tiers ] MAPPING::specialists→cognition_role[PATHOS→Wind,ETHOS→Wall,LOGOS→Door]
§3::EXAMPLES
QUICK::run_debate("Redis vs Memcached for sessions?",tier:"fast") STANDARD::run_debate("API versioning strategy?",tier:"standard") PREMIUM::resolve_question("Migrate PostgreSQL to CockroachDB?",tier:"premium")
GRAVITY_HINTS::[ fast::[naming_conventions,ui_tweaks,tooling_choices], standard::[api_design,module_boundaries,testing_strategy], premium::[security_architecture,data_model,external_contracts] ]
§4::BEST_PRACTICES TIER_SELECTION::"Match tier to decision gravity" ESCALATION::"If fast insufficient, re-run with premium" THIRD_WAY::"Best debates synthesize what neither Wind nor Wall proposed alone"
===END===
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.
- 11d ago First seen · 109 lines · 22 tokens per session scan A ac2264091e43
debate-hall-auto is a skill published in the GitHub repository elevanaltd/debate-hall-mcp (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,045 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…