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.
git clone --depth 1 https://github.com/CartapenaBark/DotNetAnalyzerWrote 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/commands/cartapenabark/dotnetanalyzer/analyze)<a href="https://agentmods.dev/commands/cartapenabark/dotnetanalyzer/analyze"><img src="https://agentmods.dev/badge/commands/cartapenabark/dotnetanalyzer/analyze/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/commands/cartapenabark/dotnetanalyzer/analyze"><img src="https://agentmods.dev/badge/commands/cartapenabark/dotnetanalyzer/analyze.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 | $0.00022 | $0.00578 |
| Opus 5.5 | $0.00009 | $0.00231 |
| Sonnet 5.5 | $0.00004 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
analyze 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/netan:analyze — .NET Project Analysis
Analyze a .NET solution or project and present a structured summary of its structure, diagnostics, and recommendations.
Prerequisite Check
- Run
dotnet-analyzer --versionto verify the global tool is installed - If it fails, ask the user: "DotNetAnalyzer global tool is not installed. Shall I run
dotnet tool install --global DotNetAnalyzerfor you?"- If confirmed, run
dotnet tool install --global DotNetAnalyzerand continue - If declined, provide the manual install command and stop
- If confirmed, run
Arguments
The user may optionally provide a project or solution path:
- If provided: use that path directly
- If not provided: auto-detect by looking for
*.slnxor*.slnin the current working directory - If no solution file found: ask the user for the path
Steps
-
Identify the target:
- Use the provided path, or auto-detect
*.slnx/*.slnin the current directory - If it's a
.sln/.slnx, use it assolutionPath - If it's a
.csproj, use it asprojectPath
- Use the provided path, or auto-detect
-
List projects (solution only):
- Call
list_projectswith the solution path - Note project count and dependency relationships
- Call
-
Get solution info (solution only):
- Call
get_solution_infofor build order and startup projects
- Call
-
Get project info:
- Call
get_project_infofor the main project(s) - Note target framework, output type, document count
- Call
-
Check diagnostics:
- Call
get_diagnosticswith the project or solution path - Count errors, warnings, and informational messages
- Call
-
Present summary:
## Analysis Summary: [Solution/Project Name] ### Structure - Projects: N - Build order: [list] - Startup project: [name] ### Diagnostics - Errors: N - Warnings: N - Info: N ### Key Findings - [List notable issues or observations] ### Recommendations - [Actionable suggestions based on findings]
Notes
- Use MCP tools with the prefix
mcp__plugin_netan_dotnet-analyzer__ - If diagnostics show errors, highlight them prominently in the summary
- For large solutions (>10 projects), focus on the main project and its direct dependencies
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 · 72 lines · 22 tokens per session scan A 371abb7c0a4a
analyze is a command published in the GitHub repository CartapenaBark/DotNetAnalyzer (2 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 578 once invoked, about $0.0001 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 commands, from other repositories
map
Generate MAP.md — a relational map of every file, function, signature, and call in the repo.
sanity
Cross-check a dekko callers/uses result against a targeted grep before trusting a low/zero count.
doctor
Diagnose dekko environment/install issues (PATH shadowing, map freshness, MCP registration, plugin, hooks, CLAUDE.md policy block).
validate-consistency
Cross-command consistency validator — detects conflicts between outputs from different /architect: commands.
check-state
Validate project state consistency — schema compliance, type checking, per-command write rule violations.
sdl-drift
Detect architecture drift — compare current codebase against committed SDL and surface topology changes.