codectx

codectx is a Python CLI that scans a source repository, ranks files by importance, extracts AST-derived structured summaries (via tree-sitter), enforces a token budget, and emits a single Markdown context document (e.g., CONTEXT.md) intended to be immediately useful to LLM agents.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml cli code-intelligence context-building tree-sitter llm-agents python
⚙ Agent Friendliness
53
/ 100
Can an agent use this?
🔒 Security
85
/ 100
Is it safe for agents?
⚡ Reliability
24
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
75
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
100
Auth Strength
100
Scope Granularity
100
Dep. Hygiene
55
Secret Handling
60

This appears to be an offline local repository analyzer with no network/auth layer described. Main security risks are operational: it reads/parses repository files that may contain sensitive data; generated CONTEXT.md may inadvertently include such content depending on patterns. Dependency hygiene is moderate-to-unknown from provided data; many tree-sitter grammars and parser dependencies increase supply-chain exposure. No evidence provided about logging of file contents/secrets or safe handling of binary/large files.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
30
AF Security Reliability

Best When

You want deterministic-ish, offline preprocessing of a local repository into an agent-friendly CONTEXT.md, especially when raw repo dumps exceed model context windows.

Avoid When

You need an online service with strong auth/rate-limit guarantees, or you cannot control what files are scanned/excluded (since it will traverse and parse repository contents).

Use Cases

  • Generate compact, structured codebase context for LLM agents (chat, coding, review, debugging).
  • Create task-focused repository context (architecture/debug/feature) with token-budget enforcement.
  • Produce auditable “ranked files” context artifacts for repeatable agent runs.

Not For

  • Serving as a networked API to other services (no REST/GraphQL/SDK surface indicated).
  • Handling secrets or authenticating to third-party systems (no auth mechanisms described).
  • Security-sensitive environments where arbitrary repository scanning could unintentionally process sensitive files without careful include/exclude configuration.

Interface

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

Authentication

OAuth: No Scopes: No

No authentication described; functionality appears to be local filesystem analysis via CLI.

Pricing

Free tier: No
Requires CC: No

No pricing model described (CLI/library). Any costs are indirect (compute/time; optional dependencies like llm/semantic extras).

Agent Metadata

Pagination
none
Idempotent
True
Retry Guidance
Not documented

Known Gotchas

  • No network API; agent integration likely requires spawning the CLI process and capturing the emitted Markdown artifact.
  • Correctness depends on include/exclude patterns and .gitignore/.ctxignore handling; misconfiguration can lead to overly large context or missing key files.
  • First run may be slower due to tree-sitter parsing and graph/ranking computation.
  • Output format is described but downstream consumers must handle large files and ensure token-budget alignment with the target model.

Alternatives

Full Evaluation Report

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

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