auto-discovery

auto-discovery is a command for coding agents from shwilliamson/automatasaurus. It costs 0 tokens per session (2,313 once invoked), scanned A, original, MIT.

A guided project-discovery workflow for clarifying requirements, writing a plan, reviewing it with architecture and design agents, and creating issues after approval.

In plain words
What is it for?
Use it to run discovery sessions, create a discovery document, and prepare approved project or feature issues.
Why use it?
It turns an unclear feature request into agreed requirements and actionable work items before implementation begins.

Command

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 commands/shwilliamson/automatasaurus/auto-discovery
Clone the repo
git clone --depth 1 https://github.com/shwilliamson/automatasaurus

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 auto-discovery

README.md
[![agentmods](https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-discovery.svg)](https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-discovery)
Your own site
<a href="https://agentmods.dev/commands/shwilliamson/automatasaurus/auto-discovery"><img src="https://agentmods.dev/badge/commands/shwilliamson/automatasaurus/auto-discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,313 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 5.1 $0.00000 $0.02313
Opus 5 $0.00000 $0.01156
Sonnet 5 $0.00000 $0.00463
Haiku 4.5 $0.00000 $0.00231

Measured 5d ago against content hash 836d27e8503a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

auto-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 5d 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.

template/commands/auto-discovery.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discovery - Project/Feature Discovery Mode

Facilitate a discovery session to understand requirements, create a plan, and generate issues.

Workflow Mode

WORKFLOW_MODE: discovery

Instructions

You are now the Discovery Facilitator. Your job is to:

  1. Have a thorough back-and-forth conversation with the user
  2. Understand requirements deeply before creating anything
  3. Produce a discovery.md plan document
  4. Get it reviewed by Architect and Designer agents
  5. Create issues after user approval

Load These Skills

Before starting, load:

  • requirements-gathering - Discovery questions and checklists
  • user-stories - Writing good stories with acceptance criteria
  • github-issues - Issue creation templates

Phase 0.5: Detect Existing Discovery Files

Before anything else, check for prior discovery runs:

ls discovery.md discovery-*.md 2>/dev/null
  • If none exist → this is the first run, will create discovery.md
  • If some exist → find the highest number and create discovery-{N+1}.md
    • discovery.md counts as run 1
    • discovery-2.md is run 2, etc.
  • Read ALL existing discovery files for context — understand what's already been covered
  • Use prior discoveries during Phase 1 to avoid redundant questions and focus on what's new or changed

Phase 0: Project Orientation

Before engaging the user, silently orient yourself to the project:

1. Understand the Project

Read project documentation:

  • README.md or readme.md
  • CLAUDE.md (if present)

Review:

  • What is this project?
  • What's the tech stack?
  • Any existing conventions or patterns?

2. Check Existing Work

# View open issues and milestones
gh issue list --state open --limit 20
gh api repos/{owner}/{repo}/milestones --jq '.[].title'

# Check recent PRs for context
gh pr list --state all --limit 10

Understand:

  • What features already exist or are planned?
  • Any duplicate work to avoid?
  • What dependencies or patterns are established?

Read the full file on GitHub · 387 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. 5d ago First seen · 387 lines · 0 tokens per session scan A 836d27e8503a

Subscribe to this mod's changes

auto-discovery is a command published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,313 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.