replicate

A verification method that asks several agents to implement the same software specification independently in separate workspaces, then compares their results.

In plain words
What is it for?
Use it to test the clarity of a specification before implementation. The output is a map of where independent implementations agree or diverge.
Why use it?
Agreement shows which parts of a specification are clear; differences reveal ambiguity, missing assumptions, or requirements that need clarification.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/sjarmak/agent-workflows/replicate
Any agent
npx skills add sjarmak/agent-workflows --skill replicate
Clone the repo
git clone --depth 1 https://github.com/sjarmak/agent-workflows

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02250
Opus 5 $0.00000 $0.01125
Sonnet 5 $0.00000 $0.00450
Haiku 4.5 $0.00000 $0.00225

Measured 2d ago against content hash 5e253342931e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

replicate 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 2d 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.

skills/replicate/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Independent Verification by Reimplementation. Spawns N agents in isolated worktrees to implement the SAME specification independently, with no knowledge of each other's code. Compares outputs to produce a convergence/divergence map that reveals where the spec is clear, where it is ambiguous, and what it fails to specify at all.

This is NOT prototyping. Agents implement the same spec, not different strategies. The value is in the convergence/divergence analysis, not in picking a winner. Where implementations converge, the spec is unambiguous. Where they diverge, the spec has gaps or hidden assumptions. The divergence map IS the output.

Arguments

$ARGUMENTS — format: [N] [path/to/spec.md or inline specification] where N is optional (default: 3, min 2, max 5)

Parse Arguments

Extract:

  • agent_count: optional leading integer (default 3, min 2, max 5)
  • spec_input: path to an existing specification file, or an inline specification string

If the spec input is missing or unclear, ask the user to provide a specification before proceeding. The spec should describe WHAT to build, not HOW — the whole point is to see how independent agents interpret the "how."

Phase 1: Frame the Specification

If a file path is given: read it and extract the full specification content.

If inline: parse the specification description.

Prepare a specification brief that includes:

  • What is being specified (the deliverable)
  • Functional requirements (what it must do)
  • Non-functional requirements (performance, compatibility, constraints)
  • Interface contracts (inputs, outputs, APIs if specified)
  • Explicit constraints (tech stack, file structure, naming conventions)
  • What the spec does NOT specify (note any obvious gaps without filling them — gaps are part of what we are measuring)

Present the specification brief to the user and confirm before proceeding. Do NOT fill in gaps or resolve ambiguities — present the spec as-is. If you notice potential ambiguities, note them privately but do not hint at them to the user or the agents. The agents must encounter ambiguities naturally.

Read the full file on GitHub · 222 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. 2d ago First seen · 222 lines · 0 tokens per session scan A 5e253342931e

Subscribe to this mod's changes

replicate is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,250 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

speckit.specify

Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.

caipe-io/ai-platform-engineering · 0 tokens

release-docs

Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…

caipe-io/ai-platform-engineering · 76 tokens

speckit.clarify

Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.

caipe-io/ai-platform-engineering · 0 tokens

local-integration-testing

Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.

caipe-io/ai-platform-engineering · 44 tokens

update-docs

Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…

caipe-io/ai-platform-engineering · 70 tokens

docker-compose-first-install

Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.

caipe-io/ai-platform-engineering · 60 tokens