Borrowing it
Nothing to install: this file belongs to widoriezebos/descartes-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/widoriezebos/descartes-mcp/main/.agents/skills/descartes-debug/SKILL.mdgit clone --depth 1 https://github.com/widoriezebos/descartes-mcpWrote 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/widoriezebos/descartes-mcp/descartes-debug)<a href="https://agentmods.dev/skills/widoriezebos/descartes-mcp/descartes-debug"><img src="https://agentmods.dev/badge/skills/widoriezebos/descartes-mcp/descartes-debug/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/skills/widoriezebos/descartes-mcp/descartes-debug"><img src="https://agentmods.dev/badge/skills/widoriezebos/descartes-mcp/descartes-debug.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 | $0.00073 | $0.05671 |
| Opus 5 | $0.00036 | $0.02835 |
| Sonnet 5 | $0.00015 | $0.01134 |
| Haiku 4.5 | $0.00007 | $0.00567 |
Grade A, and why
descartes-debug scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Proxy mode**: Only debugger tools, `thread_analyzer`, and `object_inspector` are available (11 tools). You must ask the user to trigger the workload, use `curl`/HTTP, or instruct manual action. How it starts
The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Descartes MCP Debugger Skill
You are debugging Java applications via JDWP (Java Debug Wire Protocol) using 11 Descartes MCP tools. You operate like an IDE debugger — attaching to a live JVM, setting breakpoints, stepping through code, inspecting variables, and evaluating expressions — but you do it autonomously through tool calls.
Tool Reference
| Tool | Purpose | Key Operations |
|---|---|---|
debugger_session |
Session lifecycle | start, stop, status, threads, suspend, resume, resume_all |
debugger_breakpoints |
Breakpoint management | set, upsert, resolve_line, remove, remove_all, list, enable, disable |
debugger_step |
Step execution | step_over, step_into, step_out |
debugger_threads |
Thread list/control | list, inspect, suspend, resume, resume_all |
debugger_stacktrace |
Stack frames | capture, capture_filtered, get_frame, get_current_frame |
debugger_variables |
Variable inspection | get_variables, get_child_variables, get_static_fields |
debugger_evaluate |
Expression evaluation | evaluate |
debugger_watch |
Watch expressions | add, remove, remove_all, list, enable, disable, evaluate |
debugger_events |
Event polling | wait, fetch, clear |
thread_analyzer |
Thread analysis | thread_list, thread_inspect, thread_search, deadlocks, thread_dump |
object_inspector |
Context object inspection | inspect, fields, methods, type, value |
Runtime Reality Checks
- Breakpoint
conditionis accepted and stored, but current runtime behavior does not reliably enforce it as a hit filter. Treat it as metadata; filter manually withdebugger_evaluateat breakpoint hits. debugger.method_entry,debugger.method_exit, anddebugger.exceptionevents require corresponding JDI event requests. Current public debugger tools do not expose method/exception request setup.object_inspectorevaluates JShell expressions in the proxy JVM against the proxy's sharedcontextmap — not in the debuggee. Breakpoints set in the debuggee will never fire on code executed viaobject_inspector. The proxycontextmap is separate from any application-level context in the debuggee. For inspecting state at a suspended frame in the debuggee, usedebugger_variablesanddebugger_evaluate.
What ships with it
7 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.
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.
- 12d ago First seen · 482 lines · 73 tokens per session scan A f3c79f661499
descartes-debug is a skill published in the GitHub repository widoriezebos/descartes-mcp (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 5,671 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
wxjava-troubleshooter
A troubleshooting guide for WxJava, a Java library used to connect applications to WeChat services. It organizes problems involving setup, access tokens, signatures, payment certificates, callbacks, data conversion, network requests, and multiple accounts.
performance-smell-detection
Detect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measure before optimizing. For JPA/database performance, use jpa-patterns instead.
126-java-exception-handling
Use when you need to apply Java exception handling best practices — including using specific exception types, managing resources with try-with-resources, securing exception messages, preserving error context via exception chaining, validating inputs early with fail-fast principles, handling thread interruption…
evo-maven-build-diagnosis
Executes Maven builds, captures output, and parses error logs to identify root causes of build failures. Handles compilation errors, dependency resolution failures, POM configuration issues, and JDK version incompatibilities.
evo-maven-patch-generation
Generates GNU-compatible unified diff patches for proposed code or POM fixes, writes them to numbered patch files, and applies them to the repository.