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 agentmods add skills/markdonish/round-table-workspace/debatenpx skills add MarkDonish/round-table-workspace --skill debategit clone --depth 1 https://github.com/MarkDonish/round-table-workspaceWrote 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/markdonish/round-table-workspace/debate)<a href="https://agentmods.dev/skills/markdonish/round-table-workspace/debate"><img src="https://agentmods.dev/badge/skills/markdonish/round-table-workspace/debate.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 | $0.00035 | $0.01275 |
| Opus 5 | $0.00017 | $0.00638 |
| Sonnet 5 | $0.00007 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
debate 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debate Project Skill Adapter
This is the Claude Code project-skill entry for /debate.
It is an adapter, not the canonical implementation source. The canonical /debate sources remain:
AGENTS.mddocs/protocol-spec.md.codex/skills/debate-roundtable-skill/SKILL.md.codex/skills/debate-roundtable-skill/runtime/README.mddocs/debate-runtime-bridge.mddocs/host-adapter-architecture.mddocs/debate-skill-architecture.mddocs/agent-role-map.mddocs/reviewer-protocol.mddocs/decision-quality-rubric.mddocs/red-flags.mddocs/room-to-debate-handoff.mdschemas/debate-session.schema.jsonschemas/debate-result.schema.jsonschemas/room-to-debate-handoff.schema.jsonprompts/debate-roundtable.mdprompts/debate-reviewer.mdprompts/debate-followup.md
If this file conflicts with those sources, follow those sources and report the mismatch.
Self-Contained Path Resolution & Fallback
This skill adapter is 100% self-contained and portable:
- Primary path resolution uses repo-relative paths (e.g.
docs/...,prompts/...,schemas/...). - Canonical absolute path fallback: When running outside the repository root or in global host contexts, resolve all referenced files against
/Users/markdonish/round-table-workspace/(e.g./Users/markdonish/round-table-workspace/docs/protocol-spec.md). - All protocols, schemas, and prompt specifications are fully contained within this repository.
Trigger Boundary
Use this skill only for explicit debate mode:
/debate <topic>/debate --with ... <topic>/debate --without ... <topic>/debate --quick <topic>- a valid
/roomhandoff packet accepted by the checked-in packet preflight
Do not use this skill for ordinary chat, /room exploration before upgrade, or single-agent advice.
Operating Rules
- Treat
/debateas a round-table dispatcher and reviewer workflow, not as a personality. - Do not let participants modify runtime state directly.
- Keep
/roomhandoff one-way through the packet contract. - Do not consume historical
reports/as current handoff input. - Do not use old Windows paths as runtime entry points.
- Separate facts, inferences, uncertainty, and recommendations.
- Do not fabricate reviewer approval. If review fails, return a blocked or follow-up state.
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.
- 3d ago First seen · 129 lines · 35 tokens per session scan A c3dcc5e424e5
debate is a skill published in the GitHub repository MarkDonish/round-table-workspace (2 stars, last pushed 20d ago), licensed MIT. It adds 35 tokens to every session and 1,275 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 2026-08-31.
Other skills, from other repositories
loop-execution
Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.
brainstorming
Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.
executing-plans
Use when executing an implementation plan linearly with explicit human checkpoints between batches of tasks.
pr-reviewing
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.
writing-plans
Use after design approval to create a dated executable workflow file with bite-sized tasks, exact file paths, and loop/gate definitions.
document-review
Optional utility for reviewing existing docs, external specs, hand-authored notes, or non-HOTL documents. HOTL design docs and workflows get structural lint + AI review; other documents get AI-only review with a generic rubric.