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.
npx skills add hjtrbo/PcmHackMCP --skill pcmhack-mcpgit clone --depth 1 https://github.com/hjtrbo/PcmHackMCPWrote 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/hjtrbo/pcmhackmcp/pcmhack-mcp)<a href="https://agentmods.dev/skills/hjtrbo/pcmhackmcp/pcmhack-mcp"><img src="https://agentmods.dev/badge/skills/hjtrbo/pcmhackmcp/pcmhack-mcp/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/hjtrbo/pcmhackmcp/pcmhack-mcp"><img src="https://agentmods.dev/badge/skills/hjtrbo/pcmhackmcp/pcmhack-mcp.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 | $0.00129 | $0.02376 |
| Opus 5.5 | $0.00052 | $0.00950 |
| Sonnet 5.5 | $0.00026 | $0.00475 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
pcmhack-mcp 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PcmHackMCP run_python - the things that bite
run_python ships a whole Jython 2.7 script to a live Ghidra session and runs it as a GhidraScript in one call, returning only what the script prints. Same interpreter and same Ghidra API as ghidra_bridge, but the transport and a few rules are different.
If you forget everything else:
- It's Jython 2.7 + the Ghidra Flat API. Every Jython/API gotcha from the
ghidra-bridgeskill applies to the script you send. The critical three are inlined below; the full trap shelf + API method-name table live in that skill (Nathan:~/.claude/skills/ghidra-bridge/SKILL.md) - read it for anything non-trivial. - Send one complete script;
printwhat you want back. No return value crosses the wire - only stdout/stderr. Emit results withprint(json.dumps(...)). - The transaction is automatic - and commits even on error. Don't open one. But guard each row (bare
except:), because work done before an uncaught exception is saved, not rolled back. - Imports work directly.
from ghidra.program.model.symbol import SourceTypejust works - you are already server-side. There is noremote_eval,remote_exec, orremote_importhere.
Repo: https://github.com/hjtrbo/PcmHackMCP
The dedicated tools can overflow - page, filter, or summarize
run_python is the bulk workhorse, but the same MCP server also exposes dedicated listing
tools (list_functions, list_data_items, list_strings, list_segments, ...). The trap:
a whole-program listing can return thousands of rows and blow the single tool-response
limit. A typical automotive ECU image has many thousands of functions and tens of thousands
of data items, so an unfiltered list_functions or list_data_items will overflow in one shot.
When you need a slice, do not dump the whole list:
- Use the tool's own paging/filter args, or
search_functions_by_namefor a targeted lookup. - For counts, scans, or aggregates over the whole program, push the work into
run_pythonandprintonly the count plus a bounded sample - never round-trip thousands of rows just to filter them client-side.
What ships with it
1 file 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.
- 1mo ago First seen · 178 lines · 129 tokens per session scan A 7652e12a19cd
pcmhack-mcp is a skill published in the GitHub repository hjtrbo/PcmHackMCP (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 129 tokens to every session and 2,376 once invoked, about $0.0005 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 2026-08-31.
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.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.