swift-skeleton

swift-skeleton builds an index of a codebase and extracts a “skeleton” view (type declarations, properties, method signatures, inheritance/relations, file paths, and line ranges) for use by LLM coding agents. It provides embedded library usage, a CLI/daemon interface, and an MCP server for Claude Code to query code structure.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ DevTools code-indexer tree-sitter mcp claude-code codex cli code-structure skeleton-context
⚙ Agent Friendliness
60
/ 100
Can an agent use this?
🔒 Security
24
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
70
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
20
Scope Granularity
0
Dep. Hygiene
45
Secret Handling
60

Primarily a local indexing/parsing tool; no network/API authentication or TLS details are provided. Primary risk is local filesystem access (it will read project paths) rather than credential handling. Dependency and CVE hygiene are not verifiable from provided README alone.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
20
AF Security Reliability

Best When

You want fast, local-to-agent structural indexing of a project to reduce tokens/context before deeper code reading.

Avoid When

You need complete source code, semantic correctness of implementation details, or you cannot safely scan local project files.

Use Cases

  • LLM-assisted codebase exploration by providing structural context instead of full source
  • Pre-flight architecture discovery (types, APIs, relationships, locations) for large repositories
  • Symbol search and targeted skeleton extraction to guide subsequent file reads
  • Integrating code-structure context into agent workflows (Claude Code/Codex via MCP/agent skill)

Not For

  • Retrieving fully accurate implementations or runtime behavior (the tool is skeleton/declarations-focused)
  • Security auditing/compliance workflows requiring complete code execution paths
  • Use in environments where running a local parser/CLI over the entire repository is not allowed

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
Yes
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication is described for the local CLI/MCP/daemon usage; access appears to be based on local execution and provided filesystem paths.

Pricing

Free tier: No
Requires CC: No

Open-source (MIT) and install/build is shown; no hosted pricing is described.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MCP server runs over stdin/stdout; ensure the agent/tool integration supports that transport.
  • The tool extracts skeletons (declarations/signatures); it will not provide full implementation details.
  • Symbol queries depend on the quality/completeness of parsed files; generated code or unusual build setups may reduce accuracy.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for swift-skeleton.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered