lsprag-deep-think

lsprag-deep-think is a skill for Claude Code from Gwihwan-Go/lsprag-skills. It costs 59 tokens per session (1,051 once invoked), scanned A, original, MIT.

A code-analysis skill that follows a symbol and the code it depends on in breadth-first order. A symbol is a named piece of code, such as a function, class, or variable.

In plain words
What is it for?
Use it to inspect dependency trees, understand unfamiliar functions, prepare tests, refactor code, or audit a larger change.
Why use it?
It shows how a complex piece of code is connected to the rest of the program before you change it. This reduces the chance of missing dependencies during testing or refactoring.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the lsprag-skills plugin — 1 skill shipped together

Good fit Use it to inspect dependency trees, understand unfamiliar functions, prepare tests, refactor code, or audit a larger change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gwihwan-go/lsprag-skills/lsprag-deep-think
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.

Any agent
npx skills add Gwihwan-Go/lsprag-skills --skill lsprag-deep-think
Clone the repo
git clone --depth 1 https://github.com/Gwihwan-Go/lsprag-skills

Made for: Claude Code.

Or install lsprag-skills, the plugin that ships this one along with the rest of its 1 skill.

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 lsprag-deep-think

README.md
[![agentmods](https://agentmods.dev/badge/skills/gwihwan-go/lsprag-skills/lsprag-deep-think/github.svg)](https://agentmods.dev/skills/gwihwan-go/lsprag-skills/lsprag-deep-think)
Your own site
<a href="https://agentmods.dev/skills/gwihwan-go/lsprag-skills/lsprag-deep-think"><img src="https://agentmods.dev/badge/skills/gwihwan-go/lsprag-skills/lsprag-deep-think/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lsprag-deep-think

Your own site · 80×15
<a href="https://agentmods.dev/skills/gwihwan-go/lsprag-skills/lsprag-deep-think"><img src="https://agentmods.dev/badge/skills/gwihwan-go/lsprag-skills/lsprag-deep-think.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.01051
Opus 5 $0.00030 $0.00526
Sonnet 5 $0.00012 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 11d ago against content hash bbb5cef1d18c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lsprag-deep-think 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 11d 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/lsprag-deep-think/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LSPRAG Deep Think — BFS Code Understanding

Note: deep-think is one tool in the lsprag analysis toolkit. See the main lsprag skill for the full adaptive analysis loop, decision framework, and when to use each skill.

If lsprag is not found, ask the user to run bash install.sh from the lsprag-skills root directory.

Overview

lsprag deep-think performs BFS expansion of a symbol's entire dependency graph:

  1. Retrieves the full source of the starting symbol
  2. Lists every token dependency (what that symbol calls/uses)
  3. For each dependency, retrieves its source and its own dependencies
  4. Continues until the configured depth is reached or all symbols are visited
  5. Outputs a Summary and Agent Instructions with concrete follow-up commands

When to Use

Situation Use deep-think?
Writing a test for a function you haven't seen before Yes — depth 1 or 2
Refactoring a function with many dependencies Yes — depth 2
Pre-audit before a large change Yes — depth 2-3
Just need one function's source No — use getDefinition
Need token-level dependency map No — use getTokens

Start at depth 1. Follow the Agent Instructions in the output to dig into specific branches.

Command

lsprag deep-think --file <absolute_path> --symbol <name> [--depth <n>]
Arg Description Default
--file Absolute path to source file required
--symbol Starting symbol name required
--depth Max BFS depth (0 = root only, 1 = root + direct deps, 2 = +their deps) 2

Always use absolute paths:

lsprag deep-think --file "$(realpath src/server.ts)" --symbol handleRequest --depth 2

Example Output

# Deep Think: 'handleRequest' (max depth: 2)
# File: src/server.ts

## Level 0: handleRequest (src/server.ts:15:10)

function handleRequest(req, res) {
  const body = parseBody(req);
  sendResponse(res, formatJSON(body));
}

**Dependencies:**

  L  16:C  7  parseBody    ->  src/server.ts:42:10
  L  17:C  3  sendResponse ->  src/server.ts:58:10
  L  17:C 16  formatJSON   ->  src/server.ts:73:10

---

## Level 1: parseBody (src/server.ts:42:10)
...

---

## Summary

| Metric | Value |
|--------|-------|
| Root symbol | `handleRequest` (src/server.ts) |
| Symbols visited | 5 |
| Max depth reached | 2 |
| Leaf nodes | formatJSON |
| Truncated (depth limit) | sendResponse |

## Agent Instructions

Continue exploring with these commands:

### Look up leaf node definitions
`lsprag getDefinition --file "$(realpath src/server.ts)" --symbol formatJSON`

### Explore truncated branches (hit depth limit)
`lsprag getTokens --file "$(realpath src/server.ts)" --symbol sendResponse`

### Find callers of the root symbol
`lsprag getReference --file "$(realpath src/server.ts)" --symbol handleRequest`

### Search for related patterns
`rg -n "handleRequest" . --type ts`

Read the full file on GitHub · 125 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. 11d ago First seen · 125 lines · 59 tokens per session scan A bbb5cef1d18c

Subscribe to this mod's changes

lsprag-deep-think is a skill published in the GitHub repository Gwihwan-Go/lsprag-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 1,051 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

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens