project-discovery

project-discovery is a skill for Claude Code, Codex from pueraeternis/agentic-project-template. It costs 0 tokens per session (717 once invoked), scanned A, original, MIT.

A guided conversation that clarifies what a new project should build before anyone decides how to build it.

In plain words
What is it for?
Use it when starting a project, assessing an idea, defining a first version, or exploring requirements. It helps decide what belongs in the project before architecture or coding begins.
Why use it?
It turns incomplete ideas, goals, assumptions, and constraints into a shared understanding of the project and its scope.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when starting a project, assessing an idea, defining a first version, or exploring requirements. It helps decide what belongs in the project before architecture or coding begins.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pueraeternis/agentic-project-template/project-discovery
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.

Any agent
npx skills add pueraeternis/agentic-project-template --skill project-discovery
Clone the repo
git clone --depth 1 https://github.com/pueraeternis/agentic-project-template

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.

agentmods badge for project-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/pueraeternis/agentic-project-template/project-discovery.svg)](https://agentmods.dev/skills/pueraeternis/agentic-project-template/project-discovery)
Your own site
<a href="https://agentmods.dev/skills/pueraeternis/agentic-project-template/project-discovery"><img src="https://agentmods.dev/badge/skills/pueraeternis/agentic-project-template/project-discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 717 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00717
Opus 5 $0.00000 $0.00358
Sonnet 5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00072

Measured 8d ago against content hash 48498132e06e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-discovery 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 8d 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/project-discovery/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Discovery

Purpose

This skill guides a collaborative discovery process between the human and the AI agent.

Its objective is to establish a shared understanding of the project before architecture or implementation begins.

Project Discovery produces the foundation for all subsequent engineering work.


Lifecycle Stage

Idea
        ↓
Project Discovery
        ↓
Roadmap Creation

Project Discovery defines what should be built.

It intentionally avoids defining how it will be implemented.


Role

Primary role:

Discovery Agent


When to Use

Use this skill when:

  • starting a new project;
  • evaluating a new idea;
  • defining an MVP;
  • clarifying project scope;
  • exploring requirements.

Do not use this skill for:

  • architecture design;
  • engineering decisions;
  • implementation planning;
  • repository initialization;
  • production code.

Inputs

Discovery may begin with any amount of information.

Typical inputs include:

  • an initial idea;
  • business goals;
  • user discussions;
  • existing systems;
  • constraints;
  • assumptions;
  • desired outcomes.

Inputs may be incomplete.

A major purpose of this skill is discovering the missing information.


Outputs

Produce:

  • PROJECT.md

Optionally identify engineering assumptions that will later become inputs for ENGINEERING.md.

The discovery process should produce sufficient understanding for roadmap creation.


Procedure

Step 1 — Understand the Problem

Identify:

  • the problem;
  • target users;
  • expected value;
  • project motivation.

Focus entirely on understanding.


Step 2 — Build Shared Understanding

Work collaboratively.

The agent should:

  • ask clarifying questions;
  • challenge assumptions;
  • simplify ideas;
  • identify risks;
  • refine project boundaries.

Avoid technical implementation discussions.


Step 3 — Define the MVP

Identify the smallest version that delivers meaningful value.

Clearly distinguish:

  • MVP;
  • future capabilities.

Read the full file on GitHub · 230 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. 8d ago First seen · 230 lines · 0 tokens per session scan A 48498132e06e

Subscribe to this mod's changes

project-discovery is a skill published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 717 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.