paul:discover

paul:discover is a command for coding agents from ChristopherKahler/paul. It costs 12 tokens per session (348 once invoked), scanned A, original, MIT.

A command workflow for researching technical choices before planning a project phase. It produces a recommendation, supporting research, and a discovery document for standard or deep investigations.

In plain words
What is it for?
Use it to compare technical options, verify findings, record a recommendation, and prepare the project for a planning step.
Why use it?
It reduces uncertainty about libraries, architecture, and integration approaches before implementation planning 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/christopherkahler/paul/discover
Clone the repo
git clone --depth 1 https://github.com/ChristopherKahler/paul

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 paul:discover

README.md
[![agentmods](https://agentmods.dev/badge/commands/christopherkahler/paul/discover.svg)](https://agentmods.dev/commands/christopherkahler/paul/discover)
Your own site
<a href="https://agentmods.dev/commands/christopherkahler/paul/discover"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 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 $0.00012 $0.00348
Opus 5 $0.00006 $0.00174
Sonnet 5 $0.00002 $0.00070
Haiku 4.5 $0.00001 $0.00035

Measured 4d ago against content hash 85a83d1d270f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paul: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 4d 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.

src/commands/discover.md · 49 lines

What it actually says

When to use: Before planning a phase with technical unknowns (library selection, architecture decisions, integration approaches).

Distinct from /paul:research: Research is for gathering documentation/information. Discover is for making technical decisions.

<execution_context> @/.claude/paul-framework/workflows/discovery.md @/.claude/paul-framework/templates/DISCOVERY.md </execution_context>

@.paul/STATE.md @.paul/ROADMAP.md

The workflow implements:

  1. Determine depth level (quick/standard/deep)
  2. Identify unknowns for the phase
  3. Research options using subagents
  4. Cross-verify findings
  5. Create DISCOVERY.md with recommendation
  6. Assign confidence level
  7. Route to planning when complete

<success_criteria>

  • Discovery depth determined
  • Unknowns identified
  • Options researched with sources
  • DISCOVERY.md created (for standard/deep)
  • Recommendation provided with confidence
  • Ready for /paul:plan </success_criteria>
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. 4d ago First seen · 49 lines · 12 tokens per session scan A 85a83d1d270f

Subscribe to this mod's changes

paul:discover is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 13d ago), licensed MIT. It adds 12 tokens to every session and 348 once invoked, about $0.0001 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 2026-08-30.