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 pardeike/DecompilerServer --skill decompiler-mcpgit clone --depth 1 https://github.com/pardeike/DecompilerServerWrote 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/pardeike/decompilerserver/decompiler-mcp)<a href="https://agentmods.dev/skills/pardeike/decompilerserver/decompiler-mcp"><img src="https://agentmods.dev/badge/skills/pardeike/decompilerserver/decompiler-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/pardeike/decompilerserver/decompiler-mcp"><img src="https://agentmods.dev/badge/skills/pardeike/decompilerserver/decompiler-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01301 |
| Opus 5.5 | $0.00031 | $0.00520 |
| Sonnet 5.5 | $0.00015 | $0.00260 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
decompiler-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 23d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DecompilerServer MCP
Use DecompilerServer as the primary source of truth for loaded .NET assemblies. Do not guess member IDs or fall back to shell scans after one failed symbol lookup; use the discovery and diagnostic tools first.
Default Workflow
- Load or confirm context:
load_assemblywithassemblyPath, orgameDirplusassemblyFilefor Unity layouts.statusfor readiness and the current context. Uselist_contexts(includeRegistered: true, limit, cursor, filter)only to discover registered aliases. PassingcontextAliasactivates a registered alias on demand.- Use
get_server_statsonly when cache, index, or performance diagnostics matter.
- Discover symbols:
- Use
search_symbolsfirst for fragments or when unsure whether a name is a type or member. - Use
resolve_member_idfirst for fully-qualified or XML-doc-like guesses such asNamespace.Type.Member,Namespace.Type:Member, orM:Namespace.Type.Member. - Use
search_typeswhen looking only for types. - Use
search_memberswhen looking only for methods, fields, properties, or events.
- Use
- Inspect type surface:
- Use
list_membersafter resolving a type (get_members_of_typeis its compatibility alias). - Prefer
mode: "signatures"for orientation andmode: "full"only when extra metadata is needed. - Generated members and accessors are hidden by default; use
includeCompilerGenerated: truewhen those are the subject of inspection.
- Use
- Read code:
- Use
get_decompiled_sourcefor complete focused source. - Use
plan_chunkingandget_source_slicefor large types or methods. - Batch source defaults to 50 lines per member (
maxLinesPerMember). Partial entries havehasMoreandnextStartLine; continue with a source slice. Outertruncatedincludes partial members;budgetTruncatedspecifically means the total character cap was reached.
- Use
- Analyze relationships:
- Use
find_callers,find_callees, andfind_usagesfor call/use questions. - Callers/usages default to
scope: "assembly"; usescope: "workspace"for all currently loaded contexts. InspectsearchedContexts; deferred aliases are not activated by that query. - Callees link exact members in other loaded contexts with
resolution: "workspace"; external targets retain referenced assembly identity. - Use
find_base_types,find_derived_types,get_overrides, andget_implementationsfor inheritance questions. - Type metadata outlines have addressable child IDs and
limit/cursorpaging;maxDepth: 0omits children, and larger values show the direct member level. - Use
get_ilbefore proposing transpiler anchors;suggest_transpiler_targetsshould be treated as a real-IL hint list, not a substitute for reading IL.
- Use
- Compare versions:
- Use
compare_contextsfor structural alias-level overview. - Use
compare_symbolsfor type/member drill-down. - Use
compare_symbolswithcompareMode: "body"only for method bodies.
- Use
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.
- 23d ago Changed · +10 lines cf97681f2098
- 1mo ago First seen · 54 lines · 77 tokens per session scan A 94403822317c
decompiler-mcp is a skill published in the GitHub repository pardeike/DecompilerServer (124 stars, last pushed 24d ago), licensed MIT. It adds 77 tokens to every session and 1,301 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 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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
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.