explore

explore is a skill for Claude Code, Codex from TheWinci/mimirs. It costs 79 tokens per session (394 once invoked), scanned A, original, Apache-2.0.

A code-exploration skill for building a reliable picture of an unfamiliar project or feature before editing it. It maps files, dependencies, entry points, behavior, history, and known caveats.

In plain words
What is it for?
Onboarding to a codebase, locating functionality, following connections between components, and explaining how an area works.
Why use it?
It reduces the risk of changing code without understanding how the surrounding system works.

Skill for Claude CodeCodex

Part of the mimirs plugin — 11 skills, 3 hooks 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 skills/thewinci/mimirs/explore
Any agent
npx skills add TheWinci/mimirs --skill explore
Clone the repo
git clone --depth 1 https://github.com/TheWinci/mimirs

Made for: Claude Code, Codex.

Or install mimirs, the plugin that ships this one along with the rest of its 11 skills, 3 hooks.

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/thewinci/mimirs/explore.svg)](https://agentmods.dev/skills/thewinci/mimirs/explore)
Your own site
<a href="https://agentmods.dev/skills/thewinci/mimirs/explore"><img src="https://agentmods.dev/badge/skills/thewinci/mimirs/explore.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 394 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 $0.00079 $0.00394
Opus 5 $0.00039 $0.00197
Sonnet 5 $0.00016 $0.00079
Haiku 4.5 $0.00008 $0.00039

Measured 3d ago against content hash 7e4b1b1f54ce, 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 3d 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 · 18 lines

What it actually says

Explore

Goal: understand the area from real source before touching it. Prefer the mimirs tools over grep + reading whole files.

  1. Where is itsearch "<topic>" for ranked files, then read_relevant "<topic>" to pull the actual functions/sections with line ranges (not just paths). Two chunks from one file can both appear.
  2. How it connectsproject_map(focus: <key file>) for its neighborhood; dependents <file> for who relies on it; depends_on <file> for what it pulls in.
  3. Read the coreread_relevant "<specific behavior>" on the key files; follow the helper calls a named file delegates to.
  4. History & whygit_context for what changed recently; file_history <file> for how a file evolved; search_commits "<topic>" for why past decisions were made.
  5. Prior contextsearch_conversation "<topic>" and search_checkpoints "<topic>" for earlier discussion and decisions, so you don't re-derive what's already known.
  6. Caveatsget_annotations on the key files for known bugs, fragile spots, or constraints before trusting the code.

Finish: summarize in plain language — entry points, key files, data flow, gotchas — each with a file:line citation. Flag anything still unclear instead of guessing.

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. 3d ago First seen · 18 lines · 79 tokens per session scan A 7e4b1b1f54ce

Subscribe to this mod's changes

explore is a skill published in the GitHub repository TheWinci/mimirs (29 stars, last pushed 19d ago), licensed Apache-2.0. It adds 79 tokens to every session and 394 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

akeneo-webhooks

Receive and verify Akeneo PIM (Events API) webhooks. Use when setting up Akeneo webhook handlers, debugging x-akeneo-request-signature verification, or handling batched product and product-model events like product.created, product.updated, product.removed, productmodel.created, productmodel.updated, or…

hookdeck/webhook-skills · 71 tokens

add-prompt

Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.

cyanheads/pubchem-mcp-server · 37 tokens

add-prompt

Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.

cyanheads/calculator-mcp-server · 37 tokens

openai-webhooks

Receive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like finetuning.job.completed, batch.completed, or realtime.call.incoming.

hookdeck/webhook-skills · 50 tokens

replicate-webhooks

Receive and verify Replicate webhooks. Use when setting up Replicate webhook handlers, debugging signature verification, or handling prediction events like start, output, logs, or completed.

hookdeck/webhook-skills · 40 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens