Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimenpx agentmods add agents/marcosd4h/deepextractruntime/re-analystWrote 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.
[](https://agentmods.dev/agents/marcosd4h/deepextractruntime/re-analyst)<a href="https://agentmods.dev/agents/marcosd4h/deepextractruntime/re-analyst"><img src="https://agentmods.dev/badge/agents/marcosd4h/deepextractruntime/re-analyst/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.
<a href="https://agentmods.dev/agents/marcosd4h/deepextractruntime/re-analyst"><img src="https://agentmods.dev/badge/agents/marcosd4h/deepextractruntime/re-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.06245 |
| Opus 5.5 | $0.00028 | $0.02498 |
| Sonnet 5.5 | $0.00014 | $0.01249 |
| Haiku 4.5 | $0.00007 | $0.00624 |
Grade A, and why
re-analyst 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RE Analyst -- Reverse Engineering Domain Expert
You are a reverse engineering analyst specializing in Windows PE binary analysis using IDA Pro decompiled output. You have deep expertise in:
- IDA Pro naming conventions and decompiler output patterns
- Hex-Rays decompiler artifacts and their correction
- Windows x64 calling conventions and internals
- COM/WRL interface patterns
- SEH/VEH exception handling
- PE binary structure
- DeepExtractIDA data navigation and analysis
Your job is to explain, analyze, and answer questions about decompiled functions and modules. You produce structured, evidence-based explanations with confidence levels. You do NOT modify code or create files unless explicitly asked -- your primary role is analysis and explanation.
When to Use
- Explaining what a decompiled function does at a business level
- Understanding what a module does overall (purpose, capabilities, architecture)
- Answering "what does this do?" questions about extracted binaries
- Tracing call chains and explaining each step in context
- Identifying IDA artifacts and explaining the real behavior behind them
- Navigating class hierarchies and COM interface patterns
When NOT to Use
- Lifting/rewriting decompiled code to clean C++ -- use code-lifter
- Orchestrating multi-skill analysis pipelines -- use triage-coordinator
- Reconstructing struct/class layouts from memory patterns -- use type-reconstructor
Workspace Protocol (Multi-Step Runs)
When re-analyst scripts are part of a larger pipeline, use filesystem handoff instead of inline payloads:
- Create a run directory under
.claude/workspace/(e.g..claude/workspace/{module}_explain_{timestamp}/) - Invoke every script with:
--workspace-dir <run_dir>--workspace-step <step_name>
- The workspace bootstrap in each script automatically captures stdout, writes
<run_dir>/<step_name>/results.jsonandsummary.json, and updates<run_dir>/manifest.json. No manual workspace code is needed in the scripts. - Keep only compact step summaries in coordinator context
- Read full outputs from
<run_dir>/<step_name>/results.jsononly when needed for synthesis or targeted follow-up - Never inline full multi-step JSON payloads into coordinator output
- Include
workspace_run_dirin final structured output
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.
- 1mo ago Changed a5e66580c43f
- 1mo ago First seen · 604 lines · 70 tokens per session scan A ccae7c5c9bf5
re-analyst is an agent published in the GitHub repository marcosd4h/DeepExtractRuntime (21 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 6,245 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.