codebase-health-dashboard

A review that examines a .NET codebase and combines its findings into one health report, with scores for areas such as security, design, database use, performance, monitoring, tests, dependencies, and code quality.

In plain words
What is it for?
Use it on a .NET project, solution, or GitHub repository to find problems and receive category scores, supporting findings, and a ranked list of fixes.
Why use it?
It gathers many separate checks in one place so you can see the main risks and decide which fixes matter most.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stefanthecode/dotnet-ai-toolkit/codebase-health-dashboard
Any agent
npx skills add StefanTheCode/dotnet-ai-toolkit --skill codebase-health-dashboard
Clone the repo
git clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkit

Made for: Claude Code, Codex.

Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,151 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00146 $0.01151
Opus 5 $0.00073 $0.00575
Sonnet 5 $0.00029 $0.00230
Haiku 4.5 $0.00015 $0.00115

Measured 3d ago against content hash f17d4b89b174, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-health-dashboard 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 3d 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.

skills/codebase-health-dashboard/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Health Dashboard

Point this at a .NET repo and get back a single scored report card: one overall health score, eight category scores, the findings behind each score, and the highest-leverage fixes. It is the "run everything and tell me where I stand" tool.

Input - point it at your project

Works on a target: a project/solution or a GitHub URL (git clone --depth 1 <url> then scan). Find the surface first:

find <target> -name "*.sln" -o -name "*.csproj" | grep -vi "/obj/\|/bin/"

Workflow

  1. Run the relevant auditors on the repo and collect their findings. Use the installed tools if present, otherwise apply their checklists directly:
    • Security - aspnetcore-security-auditor, secrets-config-auditor
    • Architecture - dotnet-architecture-reviewer
    • EF / Database - db-performance-auditor, ef-core-query-optimizer
    • Performance - async-await-auditor, memory-allocation-analyzer
    • Observability - observability-gap-finder
    • Testing - test-coverage-gap-finder
    • Dependencies - dependency-vuln-scanner, nuget-dependency-analyzer
    • Code Quality - dotnet-code-reviewer
  2. Score each category with the fixed rubric below (deterministic, so re-runs are comparable).
  3. Fill the template references/health-dashboard-template.html - replace /*__HEALTH_DATA__*/ with the JSON object (shape below) and write it to health-dashboard/index.html.
  4. Save a history record to health/health-<YYYY-MM-DD>.json with the same data, so the score can be tracked over time.
  5. Tell the user the overall score and the top 3 actions to raise it the fastest.

Scoring rubric (deterministic)

Each category starts at 100. Subtract per finding by severity, floor at 0:

  • critical: -25
  • high: -12
  • medium: -5
  • low: -2

If a category genuinely has no applicable surface (e.g. no messaging, so some observability checks do not apply), score what exists and note it - do not invent findings to fill it.

Read the full file on GitHub · 85 lines

Files

What ships with it

2 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.

Changes

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.

  1. 3d ago First seen · 85 lines · 146 tokens per session scan A f17d4b89b174

Subscribe to this mod's changes

codebase-health-dashboard is a skill published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 24d ago), licensed MIT. It adds 146 tokens to every session and 1,151 once invoked, about $0.0007 per session on Opus 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.

Related

Other skills, from other repositories

triz-solver

Systematic problem-solving using TRIZ (Theory of Inventive Problem Solving) principles adapted for software engineering. Use when stuck on complex problems, facing technical contradictions, optimizing system design, or seeking innovative solutions beyond trial-and-error. Prevents solving the wrong problem correctly.

d-oit/rust-2026-template · 59 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

d-oit/rust-2026-template · 64 tokens

stacked-prs

Optional workflow for large features using stacked PRs via gh-stack. Use ONLY when a feature has 3+ distinct concerns with clear dependencies. NOT for bug fixes, hotfixes, or small changes. Requires GitHub. Triggers: "stacked PRs", "gh stack", "split into layers", "stack this".

d-oit/rust-2026-template · 72 tokens

verify-actions

Verify GitHub Actions / GitLab CI action versions against actual releases before pinning. Never trust version comments — always resolve the real SHA from the upstream repository. Use when editing CI workflows, adding new actions, auditing pinned versions, or fixing version mismatches.

d-oit/rust-2026-template · 55 tokens

atomic-commit

Atomic git workflow - validates, commits, pushes, creates PR/MR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure. Supports GitHub (gh) and GitLab (glab). Triggers: "commit changes", "push and create PR", "submit code", "atomic commit".

d-oit/rust-2026-template · 76 tokens

crates-io-name-check

Verify that a new Rust crate name is available and appropriate on crates.io before committing to it. Use when creating a new crate, starting a new Rust project, or before the first cargo publish. Triggers: "check crate name", "is name taken", "crates.io available", "new crate".

d-oit/rust-2026-template · 69 tokens