ouroboros

A front layer for Claude Code that interviews you about a coding request and checks how specific the brief is before creating a work specification. It can withhold certain verification details from the worker's contract.

In plain words
What is it for?
Clarifying coding requests, scoring their vagueness, blocking specification generation unless forced through, and creating worker contracts with selected acceptance-test details omitted.
Why use it?
It helps expose vague requirements before coding begins. It also makes the worker focus on producing the requested outcome rather than simply copying a stated verification answer.

Plugin for Claude Code

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 plugins/q00/ouroboros/marketplace
Claude Code
/plugin marketplace add Q00/ouroboros
Clone the repo
git clone --depth 1 https://github.com/Q00/ouroboros

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

ouroboros 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 yesterday.

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.

.claude-plugin/marketplace.json · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "ouroboros",
  "description": "Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the worker's contract block, with no flag to put them back, so the worker is asked for the outcome rather than handed the assertion. Redaction of those values elsewhere is literal over five encodings, so a reshaped copy can still get through; that gap is tracked in a public issue.",
  "owner": {
    "name": "Q00",
    "email": "[email protected]"
  },
  "plugins": [
    {
      "name": "ouroboros",
      "description": "Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the worker's contract block, with no flag to put them back, so the worker is asked for the outcome rather than handed the assertion. Redaction of those values elsewhere is literal over five encodings, so a reshaped copy can still get through; that gap is tracked in a public issue.",
      "version": "0.51.17",
      "author": {
        "name": "Q00",
        "email": "[email protected]"
      },
      "source": "./",
      "category": "development",
      "homepage": "https://github.com/Q00/ouroboros",
      "repository": "https://github.com/Q00/ouroboros",
      "license": "MIT",
      "keywords": [
        "workflow",
        "requirements",
        "socratic",
        "interview",
        "seed",
        "evaluation",
        "agentic-loop",
        "loop-engineering"
      ],
      "tags": [
        "requirement-engin

Read the full file on GitHub · 41 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. yesterday First seen · 41 lines scan A dfe86c793fe0

Subscribe to this mod's changes

ouroboros is a plugin published in the GitHub repository Q00/ouroboros (5,730 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.