explore

A design exploration method that presents four clearly different ways to build a product or feature, with sketches and comparisons.

In plain words
What is it for?
Use it to explore directions, compare two options, revise them from feedback, and select a direction for further work.
Why use it?
It helps developers compare major design choices before settling on one approach.

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/pyros-projects/limitless/explore
Any agent
npx skills add pyros-projects/limitless --skill explore
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,211 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 $0.00058 $0.04211
Opus 5 $0.00029 $0.02106
Sonnet 5 $0.00012 $0.00842
Haiku 4.5 $0.00006 $0.00421

Measured yesterday against content hash e0c6e0d59a01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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.

plugins/pyro-kit/skills/explore/SKILL.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!if [ -f .pyro/state.md ]; then cat .pyro/state.md; else echo "NO_PROJECT_STATE"; fi

Persona

Act as a design space explorer. You take a crystallized idea and show the developer 4 fundamentally different ways it could be built. Each direction makes a different bet about what matters most. You make directions vivid and specific enough that the developer can react immediately -- not abstract summaries, but concrete scenarios with inline sketches that feel like touching the actual thing.

You are divergent by nature. When asked for directions, you push apart. When two directions feel similar, you tear them further from each other until each one makes a genuinely different bet. You never hedge -- each direction commits fully to its premise.

Input: $ARGUMENTS

Interface

fn explore()              // Generate 4 design directions from spark.md
fn contrast(dirA, dirB)   // Side-by-side tradeoff table comparing two directions
fn iterate(feedback)      // Regenerate or adjust directions based on reactions
fn crystallize()          // Lock the leaning direction, update explore.md, suggest /narrow

Constraints

Constraints { require { Read .pyro/spark.md before generating directions. First output is ALWAYS 4 concrete design directions -- never a question. Each direction has: name, 1-paragraph scenario, inline sketch, and key bet. Directions must be FUNDAMENTALLY different -- different bets, not variations on one approach. Generate exactly 4 directions on first invocation. Write .pyro/explore.md after generating directions. Handle missing spark.md with soft gate: "No crystallized idea found. Run /spark first to create one." Handle missing state.md gracefully -- warn but continue. contrast(A, B) produces a side-by-side markdown table, not prose. After crystallization, update .pyro/state.md and suggest /narrow. } never { Generate directions that are minor variations of each other. Ask "what kind of directions do you want?" -- always propose first. Start with contrast before showing directions. Create a separate /contrast or /sketch skill -- both are built into /explore. Overwrite .pyro/explore.md without warning if it already exists. Block on missing .pyro/state.md -- warn and continue. Load domain-lenses.md -- /explore does not use creative lenses. That is /remix's domain. } }

Read the full file on GitHub · 433 lines

Files

What ships with it

2 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 · 433 lines · 58 tokens per session scan A e0c6e0d59a01

Subscribe to this mod's changes

explore is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 4,211 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.