What is dev-competition?

A blind comparison process in which two agents independently build solutions to the same requirement and a third agent judges and combines the lessons. It requires three available agents and a requirement to evaluate.

Use it to compare two independent implementations and produce a judged result when three agents, a requirements file, and a workspace for the outputs are available.

Independent attempts reduce the chance that both implementations follow the same mistaken approach. A separate judge provides a structured comparison instead of letting one implementer assess its own work.

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/dev-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/dev-competition/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/dev-competition)

Your own site

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

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,175 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	$0.00030	$0.03175
Opus 5.5	$0.00012	$0.01270
Sonnet 5.5	$0.00006	$0.00635
Haiku 4.5	$0.00003	$0.00317

Measured 1mo ago against content hash 6df26dc7f3ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-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/dev-competition/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev-Competition Skill

Use mesh-comms-core first if direct peer notification has not already been proven. This skill depends on injection/direct notification, not passive comms.md polling.

Prerequisite: Three Agents Required

This skill requires at least three available agents (Implementer A, Implementer B, and Judge). If fewer than three agents are available, STOP and report:

CANNOT RUN dev-competition: only [N] agent(s) available, 3 required.
Available: [list agents]

Do not attempt a degraded single-implementer run.

Default roster: use Claude Code and Codex peers, including additional launched Claude/Codex peers when needed. Do not use Gemini CLI, Antigravity CLI, or Antigravity Desktop as an implementer or judge unless the human explicitly selects that peer.

Required Parameters

Parameter	Description
`competition_dir`	Directory where both implementations and the judgment will be created
`requirement_path`	Path to the spec file the Judge evaluates against

Both must be provided before the skill begins. If either is missing, STOP and ask for it.

Purpose

Enable two agents to independently implement the same requirement WITHOUT seeing each other's work, then have a third agent compare results and identify the best path forward. This pattern surfaces diverse approaches and prevents groupthink.

When to Use

When you want to explore multiple implementation approaches
When the "best" solution is unclear and comparison would help
When avoiding anchoring bias is important (no one drafts first)
When you want redundancy as a quality check

Roles

Lead (Orchestrator)

The agent (or human) who sets up and coordinates the competition. The Lead:

Creates the competition directory structure
Ensures requirement_path exists and is accessible
Assigns named agents to each role
Dispatches implementers and triggers judgment
Ensures blindness is maintained

Implementer A and Implementer B (Parallel, Blind)

Read the full file on GitHub · 372 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 · 372 lines · 30 tokens per session scan A 6df26dc7f3ad

Subscribe to this mod's changes

dev-competition is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,175 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

dev-competition next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dev-competitiondazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	30	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