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 rp1-run/rp1 --skill socratic-duel-rungit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/socratic-duel-run)<a href="https://agentmods.dev/skills/rp1-run/rp1/socratic-duel-run"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/socratic-duel-run/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/rp1-run/rp1/socratic-duel-run"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/socratic-duel-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.01827 |
| Opus 5 | $0.00012 | $0.00914 |
| Sonnet 5 | $0.00005 | $0.00365 |
| Haiku 4.5 | $0.00002 | $0.00183 |
Grade A, and why
socratic-duel-run 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Socratic Duel Run
§ROLE: Subagent-only Socratic Duel launcher.
§OBJ
- Resolve source path and effective topic once.
- Spawn exactly two
rp1-base:socratic-duel-participantagents with distinct participant names. - Emit only orchestration progress under deterministic units.
- Wait for participant-owned terminal closure.
- Report final debate artifact path and terminal outcome.
§BOUNDARY
- Launcher MUST NOT write the debate artifact.
- Launcher MUST NOT parse turn quality, decide consensus, append conclusions, claim/release locks, or close locks for participants.
- Launcher MAY read participant results and terminal metadata only to report path/outcome after participant-owned closure.
- Participant agents own all debate turns, artifact edits, lock ownership, terminal conclusions, and
--close-runoutcome emits. - MVP is same-harness orchestration; do not claim cross-harness participant spawning.
§CTX
- Use generated Workflow Bootstrap values:
RUN_ID,projectRoot,workRoot,codeRoot, resolved arguments. - Determine
CURRENT_HOST:claude-code,codex,gh-copilot,opencode,amp, elseunknown; defaultcodex. TARGET_PATH: required absolute readable.mdor.markdownsource path.TOPIC: optional. If blank, read the source document and use the first Markdown heading asEFFECTIVE_TOPIC, falling back to source filename stem.MODEL_ID: pass through unchanged; if unknown, keepunknown-model.
STATE-MACHINE
stateDiagram-v2
[*] --> preparing
preparing --> invalidated : invalid_input
preparing --> waiting_for_participant : agents_launched
waiting_for_participant --> debating : participants_active
waiting_for_participant --> closing : terminal_seen
waiting_for_participant --> invalidated : orchestration_failure
debating --> debating : participant_turn
debating --> closing : terminal_seen
debating --> invalidated : orchestration_failure
closing --> completed : accepted_or_dissent_or_timeout
closing --> invalidated : validation_failed
completed --> [*]
invalidated --> [*]
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.
- 12d ago First seen · 206 lines · 24 tokens per session scan A eb8150748ec1
socratic-duel-run is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 4d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,827 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.
Other skills, from other repositories
diffler
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.
learn
Use at the end of T3 work, after an incident/rollback, or when the user asks for a retro — turns what happened into recorded learnings that live in the repo (CHANGELOG entry, typed LEARNINGS.md entries, follow-up tasks, and — only with explicit user approval — new RULES).
code-documentation-code-explain
You are a code education expert specializing in explaining complex code through clear narratives, visual diagrams, and step-by-step breakdowns. Transform difficult concepts into understandable explanations.
writing-agents
How to write Codex reviewer skills — SKILL.md format, review process, severity/confidence, spawnagent dispatch patterns.
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.