developer-kit

Developer Kit for Claude Code: a modular marketplace of plugins (core + language/infra/tooling plugins) that provide reusable skills, agents, and slash commands to drive a repeatable development workflow (brainstorm/spec-to-tasks/task management/feature development/code review & debugging).

Evaluated Mar 30, 2026 (23d ago)
Repo ↗ DevTools claude-code agents skills-marketplace specification task-management code-review debugging multilanguage
⚙ Agent Friendliness
40
/ 100
Can an agent use this?
🔒 Security
17
/ 100
Is it safe for agents?
⚡ Reliability
25
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
55
Error Messages
0
Auth Simplicity
50
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
35
Secret Handling
25

README indicates a Python pre-tooluse hook `prevent-destructive-commands` to block dangerous Bash commands, which is a positive safety measure. However, no details are provided about how secrets are handled, how credentials are stored, or how permissions/scope boundaries are enforced for plugin actions. The manifest snippet only shows `PyYAML` as a dependency for a different package (`claude-validator`), not for the full developer-kit; dependency hygiene for the full project is therefore unclear from the provided data.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
40
Error Recovery
25
AF Security Reliability

Best When

You want consistent, spec-driven engineering workflows inside Claude Code across multiple languages/frameworks using a plugin marketplace model.

Avoid When

You need a standalone HTTP API/SDK with formal OpenAPI contracts, or you cannot accept that plugin actions (e.g., repo edits, command execution) depend on agent/tool behavior not fully specified here.

Use Cases

  • Generating functional specifications and acceptance criteria for new features
  • Decomposing specifications into executable tasks with complexity scoring
  • Implementing features or executing specific task steps in supported languages/frameworks
  • Reviewing/refactoring/debugging code against specs and conventions
  • Standardizing development workflows across teams using Claude Code

Not For

  • Directly exposing a secure public API for external systems (it is primarily a Claude Code plugin/command system)
  • Highly regulated environments without verifying plugin behavior and data handling
  • Use cases requiring strong, explicit authentication/authorization controls from this package alone

Interface

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

Authentication

Methods: Claude Code / plugin marketplace installation mechanisms (implied)
OAuth: No Scopes: No

No explicit authentication scheme for the package itself is described in the provided README content. Security model likely depends on Claude Code environment and how plugins execute tools/actions.

Pricing

Free tier: No
Requires CC: No

Pricing is not described in the provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Commands may perform destructive operations unless guarded; a hook for blocking dangerous Bash commands is mentioned, but the overall safety boundary is not fully specified here.
  • Task/spec files are written to repository paths (docs/specs/*); repeated runs could overwrite or create duplicates if not designed to be idempotent.

Alternatives

Full Evaluation Report

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

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.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered