triage

triage is a command for coding agents from marcosd4h/DeepExtractRuntime. It costs 0 tokens per session (1,341 once invoked), scanned A, original, MIT.

A command for examining a DeepExtractIDA module, a component produced by a tool that analyzes compiled programs, and ranking its important functions.

In plain words
What is it for?
Use it with a module name to produce a triage report, optionally including a lightweight security check of the highest-ranked entry points.
Why use it?
It turns scattered reverse-engineering work into one report covering the module's binary, functions, possible attack surface, and areas needing closer review.

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/triage
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 triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/triage.svg)](https://agentmods.dev/commands/marcosd4h/deepextractruntime/triage)
Your own site
<a href="https://agentmods.dev/commands/marcosd4h/deepextractruntime/triage"><img src="https://agentmods.dev/badge/commands/marcosd4h/deepextractruntime/triage.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 1,341 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 $0.01341
Opus 5 $0.00000 $0.00671
Sonnet 5 $0.00000 $0.00268
Haiku 4.5 $0.00000 $0.00134

Measured 3d ago against content hash 5748ac33e72f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage 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/triage.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Module Triage

Overview

Perform a complete triage of a DeepExtractIDA module -- identifying the binary, classifying all functions, mapping the attack surface, and producing a prioritized list of functions worth deeper analysis.

The text after /triage is the module name (e.g., /triage appinfo.dll). If omitted, list available modules and ask.

Optional flags:

  • --with-security -- after standard triage, run a lightweight taint scan on the top 3-5 ranked entry points and include a "Quick Security Findings" section in the report.

IMPORTANT: Execution Model

This is an execute-immediately command. Do NOT present anything for user confirmation. Run and write the final triage 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

Before running triage:

  1. Create .claude/workspace/<module>_triage_<timestamp>/.
  2. Pass --workspace-dir <run_dir> and --workspace-step <step_name> to each skill invocation.
  3. Treat stdout as summary-only; do not inline full JSON in chat.
  4. Read full payloads only when needed from <run_dir>/<step_name>/results.json.
  5. Use <run_dir>/manifest.json to track progress and available outputs.

Steps

Step 0: Preflight Validation

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

  1. Find the module DB Use the decompiled-code-extractor skill (find_module_db.py) to resolve the module name to its analysis database path. If the module is not found, run with --list to show all available modules. Alternatively, use list_extracted_modules() from helpers or python .claude/skills/function-index/scripts/index_functions.py --all --stats for instant module enumeration.

Read the full file on GitHub · 89 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 · 89 lines · 0 tokens per session scan A 5748ac33e72f

Subscribe to this mod's changes

triage 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 1,341 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.