explore-plan

explore-plan is a command for coding agents from juanmhidalgo/claude-plugins. It costs 36 tokens per session (1,561 once invoked), scanned A, original, MIT.

A command for exploring a multi-part feature and creating a structured implementation plan before coding.

In plain words
What is it for?
Use it to inspect a feature's repository scope, connect it to an optional specification, and produce a plan for implementation.
Why use it?
It organizes the investigation of changes that touch several parts of a codebase, so implementation work has a clear sequence.

Command

Part of the feature-dev plugin — 2 skills, 6 commands, 12 agents shipped together

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/juanmhidalgo/claude-plugins/explore-plan
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Or install feature-dev, the plugin that ships this one along with the rest of its 2 skills, 6 commands, 12 agents.

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-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/explore-plan.svg)](https://agentmods.dev/commands/juanmhidalgo/claude-plugins/explore-plan)
Your own site
<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/explore-plan"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/explore-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,561 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 $0.00036 $0.01561
Opus 5 $0.00018 $0.00781
Sonnet 5 $0.00007 $0.00312
Haiku 4.5 $0.00004 $0.00156

Measured today against content hash 5a5b978dc399, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore-plan 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 today.

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.

feature-dev/commands/explore-plan.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

  • Repository: !git remote get-url origin
  • Current branch: !git branch --show-current
  • Feature: $ARGUMENTS

Phase 0: Resolve Feature and Validate

  1. Resolve the feature:
    • If $ARGUMENTS is provided → use it as the feature description. Record source_spec: null.
    • If $ARGUMENTS is empty → auto-discover spec files. Use Glob with pattern SPEC-*.md in the repo root, then read each file's frontmatter and filter out any spec with status: implemented (those features are already shipped). From the remaining candidates:
      • 0 specsSTOP and ask the user for a feature description.
      • 1 spec → use it. Read its frontmatter, use feature: as the feature description, record the spec path as source_spec. Inform the user: "Auto-selected spec: SPEC-<slug>.md (feature: , status: )". If status: draft, also warn: "This spec is still in draft — the user may not have approved it yet. Proceed anyway?" and wait for confirmation.
      • 2+ specs → use AskUserQuestion to let the user pick (label = feature: value, description = <filename> — status: <status>). Use the chosen spec's feature: as the feature description and record its path as source_spec.
  2. Parse the feature into a one-line summary for agent prompts.
  3. Generate a plan filename: PLAN-<slug>.md (slug = lowercase, hyphenated, max 4 words from the feature name. E.g., PLAN-scheduled-notifications.md). If source_spec is set, reuse its slug: value for consistency.

Phase 1: Explore and Generate Plan (Forked)

Launch a single Agent with subagent_type: "general-purpose" to do all exploration and plan generation in an isolated context.

CRITICAL: The agent MUST write the plan file to disk. The agent's context is discarded after it completes — only the file persists.

Read the full file on GitHub · 169 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. today First seen · 169 lines · 36 tokens per session scan A 5a5b978dc399

Subscribe to this mod's changes

explore-plan is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 1,561 once invoked, about $0.0002 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 2026-09-03.