No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by diskd-ai · Agent Tool · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codespaces safe to install? View the security audit →
Codespaces Skill Install: | skills.sh Query a graph to discover module boundaries, dependencies, and blast radius before reading source -- so you read the minimal set of files, never whole directories. Scope & Purpose This skill bundles a belief-map query engine and graph builders for architecture discovery, covering: Module boundary and ownership discovery Dependency and reverse-dependency (blast-radius) tracing Architecture-layer and boundary-violation checks Naming-convention (invariant) checks Call-chain and data-flow tracing Cross-language analysis (Python, TypeScript, TSX) Infrastructure topology from Kustomize, Helm, and Terraform When to Use This Skill Triggers: "How does X call Y?" or "Where is this stored?" "What breaks if I change Z?" Root-cause investigations mentioning services, APIs, jobs, events, or UI flows Architecture reviews, impact analysis, or public-contract changes Before any non-trivial code change (boundary check first) Use cases: Scoping the minimal files to read before implementing a change Blast-radius analysis before a refactor Detecting architecture-layer and naming violations Tracing call chains and data flow across modules Mapping infrastructure...
| Stars | 52 |
| Forks | 6 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.6490578975884/100 |
| Last Updated | 2026-08-11 |
| Created | 2026-06-20 |
| Platforms | claude-code, python |
| Est. Tokens | ~15k |
Looking for a codespaces alternative? If you're comparing codespaces with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents,
A Context Compiler for TypeScript. Deterministic, diffable architectural contracts and dependency graphs for A
Cross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius,
Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structur
Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & imp
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input toke
Explore other popular agent tool tools:
codespaces is Architecture-aware code search, dependency graphs, and impact analysis for Python, TypeScript, Rust, C#, Java, Go, Ruby, Rails, Free Pascal, and Lazarus, for AI coding agents.. It is categorized as a Agent Tool with 52 GitHub stars.
codespaces is primarily written in Python. It covers topics such as agent-skill, ai-agents, belief-map.
You can find installation instructions and usage details in the codespaces GitHub repository at github.com/diskd-ai/codespaces. The project has 52 stars and 6 forks, indicating an active community.
codespaces is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codespaces on Agent Skills Hub include ops-codegraph-tool, logicstamp-context, tree-sitter-analyzer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: