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 MingyiSecLab/Mingyi-Atlas --skill ghidragit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/ghidra)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/ghidra"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/ghidra/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/mingyiseclab/mingyi-atlas/ghidra"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/ghidra.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 | $0.00047 | $0.00642 |
| Opus 5 | $0.00023 | $0.00321 |
| Sonnet 5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
ghidra 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 7d 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.
the complete bethington/ghidra-mcp tool surface via bash + curl: How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ghidra Deep Analysis
Ghidra is the primary reverse engineering backend. Two modes:
- MCP bridge (preferred) — 245 tools via HTTP at
$GHIDRA_MCP_URL - Headless (fallback) —
analyzeHeadless+ postScript for JSON output
Prerequisites
ghidra_status()
Check if Ghidra headless and/or MCP bridge are available.
1. Full Analysis
ghidra_analyze(binary="/workspace/target.exe")
Returns: functions (up to 500), imports, exports, language, image base. Auto-selects MCP if running, headless otherwise.
2. Decompile a Function
ghidra_decompile(binary="/workspace/target.exe", function="main")
ghidra_decompile(binary="/workspace/target.exe", function="0x401000")
Accepts symbol name or hex address. Returns C pseudocode.
3. Cross-References (MCP)
ghidra_xrefs(binary="/workspace/target.exe", address="0x401000")
Returns up to 200 xrefs with source function context.
4. Fallback: Script Generation
If headless/MCP are unavailable, generate a recon script and run via bash:
bin_ghidra_script(binary="/workspace/target.exe")
MCP Bridge — Full 245-Tool Coverage
When the Ghidra MCP bridge is running, the reverser also has access to the complete bethington/ghidra-mcp tool surface via bash + curl:
- Function analysis — decompilation, call graphs, completeness scoring
- Data flow — PCode-graph value propagation (forward / backward)
- Structure discovery — struct/union/enum creation, field analysis
- String extraction — regex search, quality filtering
- Import/export analysis — symbol tables, ordinal resolution
- Memory inspection — raw reads, byte pattern search
- Cross-binary documentation — SHA-256 function hash matching
- P-code emulation — run functions in isolation, brute-force API hashes
- Batch operations — bulk rename, comment, type (93% fewer API calls)
- Script management — create, run, update Ghidra scripts via MCP
- Convention enforcement — auto-fix naming, type safety, documentation
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.
- 7d ago First seen · 66 lines · 47 tokens per session scan A eedccbc8034b
ghidra is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 642 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.
cis-aws-foundations-6.1.2
Ensure CIFS access is restricted to trusted networks to prevent unauthorized access.
cis-aws-foundations-2.3
Ensure security contact information is registered.