codoop-discover

A guided session for designing a new product or feature from the beginning. It uses several specialist viewpoints, such as product management, user experience, and architecture, to produce design and backlog documents.

In plain words
What is it for?
Exploring a new product or feature, clarifying its scope, defining expected behavior, and preparing technical architecture and backlog documentation.
Why use it?
It organizes early decisions and checks that the proposed requirements, behavior, and system design fit together before implementation.

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/codoop/codoop-flow/codoop-discover
Any agent
npx skills add Codoop/codoop-flow --skill codoop-discover
Clone the repo
git clone --depth 1 https://github.com/Codoop/codoop-flow

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,361 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 $0.00067 $0.04361
Opus 5 $0.00034 $0.02181
Sonnet 5 $0.00013 $0.00872
Haiku 4.5 $0.00007 $0.00436

Measured yesterday against content hash 98d65f40e8b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codoop-discover 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.

skills/codoop-discover/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Discovery & Design Loop

This skill guides the AI to act as an Orchestrator running a decentralized, multi-role collaborative pipeline to discover, validate, and architect products or features. It ensures strict avoidance of assumptions, leverages multi-perspective analysis, and produces production-grade BDD specifications and system architectures.

It is designed to be compatible with Codex, Claude Code, Cursor Desktop, and other coding agents that can read files and write project docs.

Project Paths

Read [project_paths] from codoop_flow.toml before designing implementation. If it is missing, run the sibling codoop-init skill first.

The keys describe the system project type; the values are the real directories and may use any existing name. Design code only for listed projects. Treat unlisted systems as external context or contracts, never implementation work.

Also read output_language. Use it for every user-facing message, question, summary, generated document, and delegated role prompt. "auto" or a missing field follows the user's current language. An explicit request for the current task overrides the config. Translate template headings and labels as needed; never switch languages merely because a source document or template uses one.

Read user_role too; a missing value means general. It changes only the live conversation: use normal professional terms inside the user's field, and explain cross-field topics in plain language. The user's current request for simpler or more professional language overrides it. Do not apply this profile to generated documents, code, reports, or delegated agent prompts; those remain precise and professional.

Sub-Agent Expert Roles

This skill invokes the following expert personas from the plugin Runtime (../../runtime/codoop-flow/agents/):

  • PM / Product Strategy: product-sprint-prioritizer.md
  • GTM & Pricing: sales-offer-lead-gen-strategist.md
  • UI Designer: design-ui-designer.md
  • Backend Architect: engineering-backend-architect.md (only when backend is configured)
  • Software Architect: engineering-software-architect.md
  • Alignment Auditor: alignment-agent.md

Read the full file on GitHub · 221 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 221 lines · 67 tokens per session scan A 98d65f40e8b1

Subscribe to this mod's changes

codoop-discover is a skill published in the GitHub repository Codoop/codoop-flow (5 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 4,361 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

agentflow

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

sickn33/agentic-awesome-skills · 52 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

backlog-grooming

Review Agiflow Planning tasks for readiness, prioritize approved work, group related tasks into work units, and promote ready tasks to Todo. Use when grooming a backlog, organizing planned tasks, creating work units, or deciding what should be executed next.

hashgraph-online/awesome-codex-plugins · 55 tokens

project-plan

Turn a product goal or feature request into a clear Agiflow project plan with small, testable tasks in Planning status. Use when starting a project, decomposing a feature, clarifying requirements, or converting an idea into an actionable backlog.

hashgraph-online/awesome-codex-plugins · 52 tokens

refine-task

Refine an existing Agiflow task into an unambiguous, testable specification without expanding its intended outcome. Use when a task is vague, lacks acceptance criteria, has unclear scope or dependencies, or is not ready for backlog grooming.

hashgraph-online/awesome-codex-plugins · 52 tokens

triage

Diagnose stalled, blocked, overloaded, or unhealthy Agiflow projects and recommend specific corrective actions. Use for project health checks, blocked work, conflicting priorities, obsolete tasks, overloaded assignees, or an unmanageable backlog.

hashgraph-online/awesome-codex-plugins · 49 tokens