A workflow for having several coding agents solve the same task independently, then having judges compare their submissions and choose a winner.

Use it for coding challenges, design alternatives, or other tasks where separate attempts should be evaluated against shared criteria.

It removes the need to rely on one approach when multiple solutions are possible. Independent work can provide alternatives, while judging gives the submissions a structured comparison.

How dazzaji/interlateral_agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dazzaji/interlateral_agents/main/.agent/skills/competition/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dazzaji/interlateral_agents

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/competition/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/competition)

Your own site

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/competition"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/competition/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/competition"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/competition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,401 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.01401
Opus 5.5	$0.00007	$0.00560
Sonnet 5.5	$0.00004	$0.00280
Haiku 4.5	$0.00002	$0.00140

Measured 1mo ago against content hash b0d149436506, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

competition 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 1mo 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.

.agent/skills/competition/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Competition

Purpose

Multiple agents independently create solutions to the same challenge. Judges evaluate the submissions blind (if possible) and select a winner. Encourages diverse approaches and best-idea-wins culture.

Use mesh-comms-core first if direct competitor notification has not already been proven. comms.md is the ledger, not the wake-up path.

Default roster: use Claude Code and Codex peers. Do not use Gemini CLI, Antigravity CLI, or Antigravity Desktop as competitors or judges unless the human prompt explicitly names that peer.

Roles

Role	Description
`COMPETITOR`	Creates an independent solution to the challenge
`JUDGE`	Evaluates submissions against criteria, selects winner

Competitors work in isolation. Judges deliberate together.

Protocol

PHASE 1: CHALLENGE
- Challenge announced with clear criteria
- Competitors acknowledge and begin work

PHASE 2: PARALLEL WORK
- Competitors work independently (no collaboration)
- Each submits with [ENTRY]

PHASE 3: JUDGING
- Judges review all entries
- Score against criteria
- Deliberate on winner

PHASE 4: DECISION
- Judges announce winner with [WINNER]
- Provide feedback on all entries
- Optional: Synthesize best elements from all entries

Challenge Format

[CHALLENGE]
TASK: [What competitors must create]
CRITERIA:
1. [Criterion 1] - [Weight]
2. [Criterion 2] - [Weight]
3. [Criterion 3] - [Weight]
DEADLINE: [Turn count]

Entry Format

[ENTRY - COMPETITOR]
SUBMISSION: [The work product]
APPROACH: [Brief explanation of strategy]

Judging Format

[SCORE - JUDGE]
ENTRY: [Competitor name]
Criterion 1: [Score/10]
Criterion 2: [Score/10]
Criterion 3: [Score/10]
TOTAL: [Sum]
NOTES: [Qualitative feedback]

Winner Format

[WINNER]
SELECTED: [Competitor name]
REASON: [Why this entry won]
SYNTHESIS: [Optional: Best ideas from all entries to combine]

Inputs

All inputs come from the prompt.

Optional:

output: File path for winning entry
work: File containing challenge details
max_turns: Override default (40)

Read the full file on GitHub · 211 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.

1mo ago First seen · 211 lines · 18 tokens per session scan A b0d149436506

Subscribe to this mod's changes

competition is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,401 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-03.

Building agents

competition next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
competitiondazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	18	Claude Code, Codex
imagegenopenai/codex	Skill	133k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

interlateral_agents: Skill for Claude Code