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 skills/marcosd4h/deepextractruntime/callgraph-tracerWrote 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/skills/marcosd4h/deepextractruntime/callgraph-tracer)<a href="https://agentmods.dev/skills/marcosd4h/deepextractruntime/callgraph-tracer"><img src="https://agentmods.dev/badge/skills/marcosd4h/deepextractruntime/callgraph-tracer.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.04091 |
| Opus 5 | $0.00042 | $0.02046 |
| Sonnet 5 | $0.00017 | $0.00818 |
| Haiku 4.5 | $0.00008 | $0.00409 |
Grade A, and why
callgraph-tracer 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 6d 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call Graph Tracer & Cross-Module Chain Analysis
Purpose
Trace execution paths and call chains across extracted Windows PE binaries. Builds directed call graphs from simple_outbound_xrefs / simple_inbound_xrefs in analysis DBs, supports path finding, reachability analysis, and cross-module chain analysis -- following function calls across DLL boundaries to retrieve decompiled code at each step.
When NOT to Use
- Tracing how a specific parameter or data value flows through functions -- use data-flow-tracer
- PE-level import/export dependency mapping (loader-level, not code xrefs) -- use import-export-resolver
- General function explanation or understanding decompiled code -- use re-analyst or
/explain - Ranking entry points by attack value -- use map-attack-surface
- Tracing attacker-controlled input to dangerous sinks -- use taint-analysis
Data Sources
- Individual analysis DBs (
extracted_dbs/{module}_{hash}.db): Per-function xrefs, decompiled code, signatures - Tracking DB (
extracted_dbs/analyzed_files.db): Maps module names to their analysis DB paths - Xref fields used:
simple_outbound_xrefs(callees) andsimple_inbound_xrefs(callers)
Key xref properties for cross-module resolution:
function_id: non-null = callee is in the same module (query by ID)function_id: null = callee is external (usemodule_nameto find its DB)module_name: DLL name (e.g.,kernel32.dll) matchingfile_nameinanalyzed_files.db
Not all xrefs are function calls. The module_name field uses sentinel values:
"data"(function_type=4): global variable / data references -- not calls, skipped automatically"vtable"(function_type=8): vtable dispatch references -- indirect, not directly followable"internal"(function_type=1): same-module function -- followable viafunction_id"static_library"(function_type=2): statically linked -- followable viafunction_id
All scripts automatically filter out data and vtable refs from call graphs and chain traversal. See reference.md for the full sentinel value table.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 6.8 KB
- reference.md 10 KB
- scripts/_common.py 1.2 KB runs code
- scripts/analyze_detailed_xrefs.py 14 KB runs code
- scripts/build_call_graph.py 13 KB runs code
- scripts/chain_analysis.py 24 KB runs code
- scripts/cross_module_resolve.py 16 KB runs code
- scripts/generate_diagram.py 15 KB runs code
- scripts/module_dependencies.py 21 KB runs code
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.
- 6d ago First seen · 383 lines · 84 tokens per session scan A 36d01cb4df78
callgraph-tracer is a skill published in the GitHub repository marcosd4h/DeepExtractRuntime (19 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 4,091 once invoked, about $0.0004 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
Orchestrates Volcengine Cloud Detect (云拨测) false-alarm reduction for failing periodic-task dial points. Use for scheduled task scans, retrying failed nodes, control-testing node health, distinguishing real target outages from broken dial points, and suggesting same-type LastMile/IDC/Private replacement nodes. Runs the…