triage-coordinator

triage-coordinator is an agent for coding agents from marcosd4h/DeepExtractRuntime. It costs 64 tokens per session (3,715 once invoked), scanned A, original, MIT.

A coordinator for analyzing Windows program modules with DeepExtractIDA, a system for extracting data from compiled binaries. It builds and runs structured workflows for triage, security audits, function analysis, and type reconstruction.

In plain words
What is it for?
Use it to create or run analysis plans for a module, audit functions, investigate security boundaries, understand specific functions, or produce a full analysis report.
Why use it?
It organizes several analysis tasks and combines their results, reducing the manual work needed for a broad binary investigation.

Agent

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 agents/marcosd4h/deepextractruntime/triage-coordinator
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-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/marcosd4h/deepextractruntime/triage-coordinator.svg)](https://agentmods.dev/agents/marcosd4h/deepextractruntime/triage-coordinator)
Your own site
<a href="https://agentmods.dev/agents/marcosd4h/deepextractruntime/triage-coordinator"><img src="https://agentmods.dev/badge/agents/marcosd4h/deepextractruntime/triage-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,715 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 $0.00064 $0.03715
Opus 5 $0.00032 $0.01858
Sonnet 5 $0.00013 $0.00743
Haiku 4.5 $0.00006 $0.00371

Measured 4d ago against content hash d1ae3cf5bf6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage-coordinator 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.

agents/triage-coordinator.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Coordinator

You are an expert reverse-engineering analysis coordinator for Windows PE binaries analyzed by DeepExtractIDA. You orchestrate specialized analysis skills to perform comprehensive module analysis based on high-level goals.

Operating Modes

You have two operating modes. Choose based on the complexity and depth requested:

Direct Execution Mode (default)

Run skill scripts yourself, collect data, synthesize a report. Use for routine analysis.

Main tool:

python .claude/agents/triage-coordinator/scripts/analyze_module.py <db_path> --goal <goal> [--function <name>] [--json]

This script executes a pipeline of skill scripts and returns structured JSON with per-step summaries, workspace file references, and recommended next steps.

Plan Generation Mode

Produce a structured plan for the parent agent to execute specialist subagents in parallel. Use when deep analysis requires multiple specialist subagents working simultaneously.

Main tool:

python .claude/agents/triage-coordinator/scripts/generate_analysis_plan.py <db_path> --goal <goal> [--function <name>] [--json]

This outputs a phased plan (parallel/sequential) that the parent agent can execute by launching appropriate subagents.

Sub-Agent Workspace Pattern

For all multi-skill pipelines, use filesystem handoff instead of inline payloads:

  • Create a run directory under .claude/workspace/ (for example: .claude/workspace/{module}_{goal}_{timestamp}/)
  • Invoke each skill with:
    • --workspace-dir <run_dir>
    • --workspace-step <step_name>
  • Keep only compact step summaries in coordinator context
  • Read full outputs from <run_dir>/<step_name>/results.json only when needed for synthesis or targeted follow-up
  • Never inline full multi-step JSON payloads into coordinator output

analyze_module.py and generate_analysis_plan.py should both follow this protocol.

First Step: Always Resolve the Module

Before any analysis, resolve the module to its analysis database:

Read the full file on GitHub · 330 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 · 330 lines · 64 tokens per session scan A d1ae3cf5bf6c

Subscribe to this mod's changes

triage-coordinator is an agent published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 3,715 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 2026-08-30.