explore

explore is a skill for Claude Code, Codex from jstoup111/ai-conductor. It costs 50 tokens per session (1,841 once invoked), scanned A, original, Apache-2.0.

An exploration step for deciding how a proposed change should be approached and whether it is a product feature or technical work. A product feature affects user-facing behavior; technical work includes refactoring, infrastructure, or dependency changes.

In plain words
What is it for?
Use it only in the active decision workflow when the approach or product-versus-technical classification is still unresolved.
Why use it?
It clarifies the type and direction of work before requirements or implementation documents are written.

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/jstoup111/ai-conductor/explore
Any agent
npx skills add jstoup111/ai-conductor --skill explore
Clone the repo
git clone --depth 1 https://github.com/jstoup111/ai-conductor

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 explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/jstoup111/ai-conductor/explore.svg)](https://agentmods.dev/skills/jstoup111/ai-conductor/explore)
Your own site
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/explore"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/explore.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,841 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 $0.00050 $0.01841
Opus 5 $0.00025 $0.00920
Sonnet 5 $0.00010 $0.00368
Haiku 4.5 $0.00005 $0.00184

Measured 5d ago against content hash 0fc1c87d6996, 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 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.

skills/explore/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

The divergent opening of DECIDE: understand intent, gather context, weigh approaches, and decide what kind of work this is — a product feature (needs a PRD) or technical-only work (refactor/infra/deps — no PRD). Exploration is a thinking step; its durable outputs are the chosen approach (to .memory/decisions/) and the track marker — not a design doc.

Correctness gate: approach recommendations and the track decision are load-bearing. Apply the /verify-claims protocol — attach a grounded confidence % to non-trivial claims about the code or domain, surface every assumption feeding an approach, and HARD-BLOCK (operator approval interactive, HALT if autonomous) on any unconfirmed assumption that changes which approach or track you pick.

Boundaries

explore writes no committed .docs/ design artifact. It MAY write exactly one committed marker: .docs/track/<slug>.md.

Do NOT:

  • Write code, migrations, configs, tests, stubs, plans, stories, or a PRD/design doc
  • Create files in .docs/specs/, .docs/plans/, .docs/stories/, etc.
  • Invoke /prd, /plan, /stories, or any other skill

Working notes (approaches considered, scratch reasoning) are ephemeral — keep them in .pipeline/ (gitignored), never in .docs/. The PRD is authored by /prd (product track only); stories carry acceptance criteria on both tracks.

After the track is decided and the decision persisted, exit the session immediately. The conductor handles the handoff (to /prd on the product track, or straight to architecture on the technical track).

Documentation-only delivery

Before selecting a normal track, determine whether the request is solely a human-facing documentation update. A request is documentation-only only when it changes no product/runtime behavior, machine-consumed contract, configuration semantics, generated artifact, or testable functional surface. If documentation accompanies any functional change, keep it on the normal product or technical route; never split it into a separate story, requirement, or plan task.

Read the full file on GitHub · 170 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 · 170 lines · 50 tokens per session scan A 0fc1c87d6996

Subscribe to this mod's changes

explore is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,841 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens