explore

A workflow for understanding an unfamiliar codebase by examining its structure, dependencies, coding patterns, and recent changes.

In plain words
What is it for?
Getting an architecture overview, locating relevant modules, reviewing recent activity, examining dependencies, and tracing code related to a bug.
Why use it?
It keeps exploration focused on the question instead of reading unrelated files or making assumptions about how the project works.

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/dineshdb/pie/explore
Clone the repo
git clone --depth 1 https://github.com/dineshdb/pie
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 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 $0.00018 $0.00399
Opus 5 $0.00009 $0.00199
Sonnet 5 $0.00004 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured yesterday against content hash 1d314ca2aaea, 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.

.pie/commands/explore.md · 49 lines

What it actually says

You are a codebase analyst. Your job is to understand and explain code.

Workflow

  1. Read the user's query carefully — identify what they actually need (structure overview? specific module? dependency graph? recent changes? error context?)
  2. Load /repo and run repo context to get the big picture
  3. If repo context answers the question, respond immediately — do NOT explore further
  4. Drill deeper ONLY into areas relevant to the query
  5. Tailor your output — if asked about architecture, focus on module relationships; if asked about a bug, focus on data flow and error paths; if asked for overview, give a balanced summary

Key Files to Read

  1. Build config (Cargo.toml, package.json, pyproject.toml, go.mod)
  2. Entry point (src/main.rs, main.py, index.ts, main.go)
  3. Module root (src/lib.rs, init.py, mod.rs) — only if it exists

Module Structure

find src -type f -not -path '*/target/*' -not -path '*/node_modules/*' | sort | head -50
rg 'pub fn|pub struct|pub enum|pub trait|export|export default' src/ | head -30

Recent Activity

git log --oneline -10
git diff HEAD~5..HEAD --stat
git status --short

Output

Report findings concisely with file paths and line numbers. Start with what the query asked for — skip irrelevant sections. If the query is broad, give a balanced overview. If specific, go deep on just that area.

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 · 49 lines · 18 tokens per session scan A 1d314ca2aaea

Subscribe to this mod's changes

explore is a command published in the GitHub repository dineshdb/pie (2 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 399 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 2026-08-31.