# Token Efficient Exploration

> Explores codebases with minimal context load. Use before implementing, debugging, or reviewing unfamiliar code. Search and read narrowly instead of dumping whole files into context.

- Skill: `aresiddharthareddy/token-efficient-exploration` (Agent Skill)
- Install (CLI): `npx skillmds@latest add aresiddharthareddy/token-efficient-exploration`
- Raw SKILL.md: https://api.skillmd.com/api/skills/aresiddharthareddy/token-efficient-exploration/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: aresiddharthareddy (https://skillmd.com/u/aresiddharthareddy)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/aresiddharthareddy/token-efficient-exploration

---


# Token-Efficient Exploration

## Goal

Learn **just enough** to act. Every file read and every line in chat costs tokens.

## Search ladder (use in order)

1. **Grep** exact symbol, error string, or route — not broad keywords.
2. **Glob** by filename when you know the artifact (`*auth*`, `*.test.ts`).
3. **Read** only the matched file — use `offset`/`limit` for large files.
4. **Task/explore subagent** only when the question spans many modules.

Stop as soon as you can name: file, function, and change.

## Read discipline

| Do | Don't |
|----|-------|
| Read 30–80 lines around the match | Read 500-line files whole |
| Read one example, infer the pattern | Read every similar file |
| Open `package.json` / imports for deps | Web-search what the repo already uses |
| Parallel grep on independent symbols | Sequential guess-and-check reads |

## Tool hygiene

- Batch independent greps/reads in **one** turn.
- Never paste large file contents into the user reply.
- Cite code with `startLine:endLine:path` — don't duplicate blocks in prose.
- Skip reading files you won't edit unless required for correctness.

## When stuck

1. Narrow the question ("where is X **called**?" not "how does the app work?").
2. Grep callers/callees of the last symbol you found.
3. Read tests for the target — tests are often shorter than implementation.

## Exit criteria

Proceed to implementation when you can answer:

- What file(s) change?
- What function(s) change?
- What existing pattern to mirror?

If not, one more **targeted** grep — not another broad read.