full-report

full-report is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (2,747 once invoked), scanned A, original, MIT.

A command that creates a detailed reverse-engineering report for a selected program module, such as a DLL file. It combines information about the binary, its functions, call relationships, attack surface, and selected specialized areas.

In plain words
What is it for?
Use it to examine a module's identity, classify its functions, map how functions call one another, find possible attack surfaces, and inspect areas such as COM or global state.
Why use it?
It gathers several analysis results into one report instead of requiring separate commands and manual comparison.

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/full-report
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime

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 full-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/full-report.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/full-report)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/full-report"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/full-report.svg" alt="Measured on agentmods" height="20"></a>
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 2,747 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 $0.02747
Opus 5 $0.00000 $0.01373
Sonnet 5 $0.00000 $0.00549
Haiku 4.5 $0.00000 $0.00275

Measured 4d ago against content hash 8dffb4c69edb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

full-report 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 4d 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/full-report.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Analysis Report

Overview

End-to-end analysis of a DeepExtractIDA module combining multiple analysis passes: binary identity, function classification, attack surface mapping, call graph topology, and specialized analysis (COM, global state). This is the most thorough single-command analysis.

The text after /full-report is the module name (e.g., /full-report appinfo.dll). Add --brief for an abbreviated version. If omitted, list available modules and ask.

IMPORTANT: Execution Model

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

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.

Workspace Protocol

This command orchestrates many skills; always use filesystem handoff:

  1. At setup time, create .claude/workspace/<module>_full_report_<timestamp>/.
  2. For every skill execution in all phases, pass:
    • --workspace-dir <run_dir>
    • --workspace-step <phase_or_step_name>
  3. Treat script stdout as summary-only.
  4. Read full intermediate results only from <run_dir>/<step_name>/results.json when synthesizing the final report.
  5. Use <run_dir>/manifest.json to confirm completed/failed steps and avoid context blowup from large JSON payloads.

Steps

Step 0: Preflight Validation

Validate arguments using helpers.command_validation.validate_command_args("full-report", {"module": "<module>"}). If validation fails, report the errors and stop. On success, use result.resolved["db_path"] for subsequent script calls.

Setup

  1. Find the module DB Use the decompiled-code-extractor skill (find_module_db.py) to resolve the module.

Read the full file on GitHub · 194 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. 4d ago First seen · 194 lines · 0 tokens per session scan A 8dffb4c69edb

Subscribe to this mod's changes

full-report 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 2,747 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.