search

search is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (1,434 once invoked), scanned A, original, MIT.

A search command for finding code by function names, signatures, text strings, API calls, risky APIs, class names, and exported symbols.

In plain words
What is it for?
Searching one or more modules with substring, regular-expression, or typo-tolerant matching, then ranking the results by relevance.
Why use it?
It removes the need to choose a separate search method for each kind of code detail.

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/marcosd4h/deepextractruntime/search
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,434 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 $0.00000 $0.01434
Opus 5 $0.00000 $0.00717
Sonnet 5 $0.00000 $0.00287
Haiku 4.5 $0.00000 $0.00143

Measured 3d ago against content hash cd571877a8a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search 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.

commands/search.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Search across all analysis dimensions in one call -- function names, signatures, string literals, API calls, dangerous APIs, class names, and exports. Wraps unified_search.py to find everything related to a search term without needing to know which dimension it belongs to.

Supports three matching modes:

  • substring (default) -- case-insensitive substring matching
  • regex -- Python regex via re.search()
  • fuzzy -- typo-tolerant matching via difflib.SequenceMatcher

Results are ranked by relevance score (match quality + context signals like application vs library code, decompiled availability, export status, dangerous API presence, and multi-dimension hits).

The text after /search specifies the search term and optionally the module, mode, and dimensions:

  • /search CreateProcess -- search all modules, all dimensions (substring)
  • /search appinfo.dll CreateProcess -- search specific module
  • /search appinfo.dll --dimensions name,api CreateProcess -- restrict to name and API dimensions
  • /search --all registry -- explicitly search all modules
  • /search appinfo.dll --regex "^Ai.*Process$" -- regex mode
  • /search --fuzzy CreateProces -- fuzzy mode (typo-tolerant)
  • /search appinfo.dll CreateProcess --sort score -- explicitly sort by relevance

If no search term is provided, ask the user.

IMPORTANT: Execution Model

This is an execute-immediately command. Do NOT present anything for user confirmation. Run and write the final search results straight to the chat as your response. The user expects to see the completed output.

Execution Context

IMPORTANT: Any inline Python that imports helpers.* must run with cd <workspace>/.claude (so the .claude/ directory is on sys.path), not from the workspace root. Script invocations like python .claude/skills/.../script.py can be run from the workspace root because those scripts manage their own path setup.

Steps

Step 0: Preflight Validation

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 0 tokens per session scan A cd571877a8a8

Subscribe to this mod's changes

search is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,434 tokens. 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.