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-manualgit 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-manual)<a href="https://agentmods.dev/skills/elevanaltd/debate-hall-mcp/debate-hall-manual"><img src="https://agentmods.dev/badge/skills/elevanaltd/debate-hall-mcp/debate-hall-manual/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-manual"><img src="https://agentmods.dev/badge/skills/elevanaltd/debate-hall-mcp/debate-hall-manual.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 | $0.00019 | $0.00972 |
| Opus 5 | $0.00010 | $0.00486 |
| Sonnet 5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
debate-hall-manual 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_MANUAL===
META: TYPE::SKILL[FOCUSED] VERSION::"1.0" PURPOSE::"Manual turn-by-turn debate control" ROUTER::debate-hall
§1::WORKFLOW SEQUENCE::INIT→TURN→GET→CLOSE
§2::TOOLS
INIT_DEBATE::[ thread_id::REQUIRED[FORMAT:"YYYY-MM-DD-descriptor"], topic::REQUIRED, mode::"fixed"|"mediated"[default:fixed], max_turns::12[default], max_rounds::4[default], strict_cognition::false[default] ]
ADD_TURN::[ thread_id::REQUIRED, role::REQUIRED["Wind"|"Wall"|"Door"], content::REQUIRED, cognition::PATHOS|ETHOS|LOGOS[optional], agent_role::STRING[audit_trail], model::STRING[audit_trail] ]
GET_DEBATE::[ thread_id::REQUIRED, include_transcript::true[default], context_turns::INTEGER[optional_limit] ]
CLOSE_DEBATE::[ thread_id::REQUIRED, synthesis::REQUIRED[Door_final_text], output_format::"json"|"octave"|"both" ]
PICK_NEXT_SPEAKER::[ thread_id::REQUIRED, role::"Wind"|"Wall"|"Door", USE_IN::mediated_mode_only ]
§3::MODES
FIXED::[ SEQUENCE::Wind→Wall→Door→repeat, USE_FOR::[structured_decisions,guaranteed_coverage] ]
MEDIATED::[ SEQUENCE::pick_next_speaker_determines_order, USE_FOR::[dynamic_debates,breaking_deadlocks], WARNING::"Can bias outcomes if roles starved" ]
§4::EXAMPLE init_debate("2026-02-09-api-design","REST vs GraphQL?") add_turn(thread_id,"Wind","What if GraphQL? Single endpoint, client flexibility...") add_turn(thread_id,"Wall","Yes, but complexity. Team experience, caching challenges...") add_turn(thread_id,"Door","Therefore: REST for public API, GraphQL for internal dashboard...") close_debate(thread_id,synthesis,output_format:"octave")
§5::PARALLEL_AGENTS // Restored from monolith §4.1, §7.4, §11
DEFINITIONS::[ PARALLEL_THINKING::"Generate candidate turns concurrently off-server (multiple models/processes)", SEQUENTIAL_COMMIT::"Persist turns in strict order via add_turn (one committed head at a time)" ]
HARD_RULES::[ DOOR_NEVER_SYNTHESIZES_BEFORE_WIND_AND_WALL_COMMITTED, WALL_REALITY_TESTS_CONCRETE_WIND_OUTPUT, ONE_COMMIT_PER_THREAD_AT_A_TIME[avoid_lost_updates], RETRY_ON_STALE_STATE::get_debate→regenerate→add_turn ]
BARRIER_PROTOCOL::[ ROUND::Rk[ STEP_1::snapshot=get_debate(thread_id), STEP_2::spawn_parallel_drafts[Wind_draft,Wall_draft], STEP_3::serial_commit::add_turn(Wind)→add_turn(Wall), STEP_4::Door_reads_latest=get_debate(thread_id)→synthesize→add_turn(Door), STEP_5::repeat_or_close ] ]
BEST_PRACTICES::[ DEFAULT::parallel_draft_sequential_commit, DOOR_BARRIER::"Door must read latest state after Wind+Wall commits", WALL_FRAMEWORK_MODE::"If drafting early, write constraints then apply post-Wind" ]
DEPLOYMENT::REQUIRE::DEBATE_HALL_STATE_DIR_set_to_shared_location[avoid_split_brain]
===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 · 111 lines · 19 tokens per session scan A c7fea4ed50c5
debate-hall-manual is a skill published in the GitHub repository elevanaltd/debate-hall-mcp (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 972 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…