What is peer-superset?

A two-agent review process in which agents critique an artifact independently, compare their work, and produce one combined set of findings and revision requests.

Use it to review sprint specifications, runbooks, deployment plans, safety reviews, architecture proposals, and incident retrospectives.

It reduces the chance that one reviewer misses an important problem. It is intended for high-stakes documents, not ordinary edits or implementation 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/peer-superset/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/peer-superset/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/peer-superset)

Your own site

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

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,490 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	$0.00074	$0.02490
Opus 5.5	$0.00030	$0.00996
Sonnet 5.5	$0.00015	$0.00498
Haiku 4.5	$0.00007	$0.00249

Measured 12d ago against content hash 1daf191420b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

peer-superset 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.

.agent/skills/peer-superset/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Peer Superset

Compatibility: two live agents with direct comms, preferably Codex 5.5 and Claude Opus 5.5.

Purpose

Use this skill when a matter deserves two strong independent analyses before consensus.

The pattern is:

Codex and Claude independently perform deep review and redteam.
They do not read each other's original work until both original artifacts exist.
They exchange originals.
Codex drafts a consensus superset.
Claude challenges, adds, downgrades, or corrects.
Codex integrates the final consensus.
Claude confirms [DONE] or files material objections.

The output is a single agreed artifact with the strongest combined analysis and an enumerated set of revision requests.

When To Use

Use for:

sprint specs
skills
runbooks
deployment plans
safety reviews
architecture proposals
incident retrospectives
high-stakes docs where independent redteam matters

Do not use for:

ordinary small edits
tasks where one reviewer is enough
loose brainstorming without a concrete matter or artifact
implementation work; this skill produces review/synthesis artifacts, not patches

Required Inputs

All inputs come from the prompt.

matter: what is being reviewed
context: why it matters and what success means
artifacts: file paths, commands, URLs, or evidence to inspect
output_dir: directory for all peer-superset artifacts

Recommended:

codex_session: default ps-codex-reviewer or another Codex 5.5 session
claude_session: default ps-claude-reviewer or another Claude Opus 5.5 session
final_output: default {output_dir}/consensus-final.md
max_turns: default 4 consensus exchanges after independent originals
controller: human or agent responsible for phase advancement
timeout_policy: default original 30 minutes, synthesis 20 minutes, response 20 minutes, final confirmation 15 minutes

Transport Requirement

Use mesh-comms-core before relying on this workflow.

Direct-send is mandatory. comms.md is only the ledger.

Read the full file on GitHub · 378 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.

12d ago Changed 1daf191420b7
1mo ago First seen · 378 lines · 74 tokens per session scan A 134f41450789

Subscribe to this mod's changes

peer-superset is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 74 tokens to every session and 2,490 once invoked, about $0.0003 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

peer-superset next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
peer-supersetdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	74	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	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
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

interlateral_agents: Skill for Claude Code