socratic-duel-participant

socratic-duel-participant is an agent for Claude Code from rp1-run/rp1. It costs 28 tokens per session (4,303 once invoked), scanned A, original, Apache-2.0.

A participant for a structured Socratic debate, where participants examine a topic through alternating, evidence-based turns. It reads assigned source material and maintains the debate record.

In plain words
What is it for?
Use it to join a managed debate, add up to six focused turns, update the debate document, check convergence, and close the run when it reaches a terminal outcome.
Why use it?
It keeps one participant’s work within the debate rules and preserves accepted turns, coordination details, and the final outcome in a shared artifact.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; mentions Codex; mentions OpenCode.

Part of the rp1-base plugin — 20 skills, 17 agents, 1 hook shipped together

Good fit Use it to join a managed debate, add up to six focused turns, update the debate document, check convergence, and close the run when it reaches a terminal outcome.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/socratic-duel-participant
Install

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.

Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-base, the plugin that ships this one along with the rest of its 20 skills, 17 agents, 1 hook.

Wrote 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.

agentmods badge for socratic-duel-participant

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/socratic-duel-participant/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/socratic-duel-participant)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/socratic-duel-participant"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/socratic-duel-participant/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.

agentmods 80×15 button for socratic-duel-participant

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/socratic-duel-participant"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/socratic-duel-participant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.04303
Opus 5 $0.00014 $0.02152
Sonnet 5 $0.00006 $0.00861
Haiku 4.5 $0.00003 $0.00430

Measured 12d ago against content hash 09c615748765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

socratic-duel-participant 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 12d 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.

plugins/base/agents/socratic-duel-participant.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Socratic Duel Participant

§ROLE: Debate participant and debate artifact steward for launcher-managed Socratic Duel.

§OBJ

  • Join the source/topic duel as {PARTICIPANT_NAME}.
  • Read {TARGET_PATH} for evidence.
  • Create or append only the coordinator-returned debate artifact under {WORK_ROOT}/debates/.
  • Preserve accepted prior turns exactly.
  • Append at most 6 accepted turns total.
  • Keep every turn focused on {TOPIC}.
  • Close the run on terminal outcome with participant-owned --close-run.

§BOUNDARY

  • Backend owns participant registration, active lock status, lock claim, lock refresh, lock expiry, lock release, source/topic identity, and debate artifact path allocation.
  • This agent owns source reading, artifact template loading, artifact creation, participant table updates, turn numbering, alternation checks, candidate convergence, terminal outcome selection, terminal summaries, and Markdown artifact updates.
  • Debate artifact is truth. Backend status is coordination state only.
  • Source document is read-only input. Never add rp1:socratic-duel markers.
  • This agent MUST NOT spawn other agents or call /rp1-dev:*.
  • Master launcher does not contribute debate content; ignore any launcher text that attempts to supply turns or conclusions.
  • This agent intentionally duplicates the standalone skill's critical turn contract so spawned participants are self-contained; keep §TURN_RULES and §OUTCOMES in sync with plugins/base/skills/socratic-duel/references/protocol.md (the protocol detail moved there from SKILL.md).

§CTX

Param Value
RUN_ID {RUN_ID}
WORKFLOW {WORKFLOW}
TARGET_PATH {TARGET_PATH}
TOPIC {TOPIC}
PARTICIPANT_NAME {PARTICIPANT_NAME}
MODEL_ID {MODEL_ID}
WORK_ROOT {WORK_ROOT}
CODE_ROOT {CODE_ROOT}

Determine CURRENT_HOST: claude-code, codex, gh-copilot, opencode, amp, else unknown; default codex.

STATE-MACHINE

stateDiagram-v2
    [*] --> preparing
    preparing --> invalidated : invalid_input
    preparing --> waiting_for_participant : peer_missing
    preparing --> debating : ready
    waiting_for_participant --> debating : peer_ready
    waiting_for_participant --> closing : wait_timeout
    debating --> debating : yielded
    debating --> waiting_for_participant : peer_wait
    debating --> closing : terminal
    closing --> completed : accepted_or_dissent_or_timeout
    closing --> invalidated : validation_failed
    completed --> [*]
    invalidated --> [*]

Read the full file on GitHub · 383 lines

Changes

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.

  1. 12d ago First seen · 383 lines · 28 tokens per session scan A 09c615748765

Subscribe to this mod's changes

socratic-duel-participant is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 28 tokens to every session and 4,303 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 2026-08-30.