rosudrag

21 mods across 1 repository, 2 stars between them.

architect

01

rosudrag/ai-praxis

Agent Claude Code

System architecture specialist. Designs solutions and evaluates architectural trade-offs.

not rated 2 5mo ago A 14 tokens original MIT

rosudrag/ai-praxis

Agent Claude Code

Build error fixer. Runs the build, parses errors, and applies minimal mechanical fixes one at a time.

not rated 2 5mo ago A 26 tokens original MIT

doc-updater

03

rosudrag/ai-praxis

Agent Claude Code

Documentation sync specialist. Detects drift between docs and code, then updates stale references.

not rated 2 5mo ago A 21 tokens original MIT

planner

04

rosudrag/ai-praxis

Agent Claude Code

Feature planning specialist. Analyzes requests and creates implementation plans without modifying code.

not rated 2 5mo ago A 18 tokens original MIT

refactor-cleaner

05

rosudrag/ai-praxis

Agent Claude Code

Dead code removal specialist. Detects and safely removes unused code, dependencies, and duplicates.

not rated 2 5mo ago A 23 tokens original MIT

reviewer

06

rosudrag/ai-praxis

Agent Claude Code

Code review specialist. Performs thorough analysis of code changes for correctness, security, and quality.

not rated 2 5mo ago A 21 tokens original MIT

security-reviewer

07

rosudrag/ai-praxis

Agent Claude Code

Security analysis specialist. Scans code for vulnerabilities following OWASP guidelines.

not rated 2 5mo ago A 18 tokens original MIT

tdd-guide

08

rosudrag/ai-praxis

Agent Claude Code

TDD implementation coach. Guides development through strict RED-GREEN-REFACTOR cycles.

not rated 2 5mo ago A 22 tokens original MIT

build-fix

09

rosudrag/ai-praxis

Command Claude Code

Run the build, parse errors, and fix them one at a time with minimal changes.

not rated 2 5mo ago A 0 tokens original MIT

debug

10

rosudrag/ai-praxis

Command Claude Code

Investigate and fix a bug using a structured debugging methodology.

not rated 2 5mo ago A 0 tokens original MIT

introspect

11

rosudrag/ai-praxis

Command Claude Code

Analyze recent Claude Code conversation transcripts to identify friction points, missing docs, skill gaps, and behavioral corrections.

not rated 2 5mo ago A 0 tokens original MIT

orchestrate

12

rosudrag/ai-praxis

Command Claude Code

You are the orchestrator. Your job is to stay thin, preserve context, and delegate all heavy lifting to sub-agents. NEVER do deep file reading, code analysis, or implementation directly — always spawn agents for that.

not rated 2 5mo ago A 0 tokens original MIT

plan

13

rosudrag/ai-praxis

Command Claude Code

Break down a feature request into an actionable implementation plan.

not rated 2 5mo ago A 0 tokens original MIT

refactor-clean

14

rosudrag/ai-praxis

Command Claude Code

Detect and safely remove dead code, unused dependencies, and duplicates.

not rated 2 5mo ago A 0 tokens original MIT

review

15

rosudrag/ai-praxis

Command Claude Code

Perform a thorough code review of recent changes or specified files.

not rated 2 5mo ago A 0 tokens original MIT

tdd

16

rosudrag/ai-praxis

Command Claude Code

Guide the implementation of a feature using strict TDD methodology.

not rated 2 5mo ago A 0 tokens original MIT

test-coverage

17

rosudrag/ai-praxis

Command Claude Code

Analyze code coverage, identify gaps, and generate tests to reach target thresholds.

not rated 2 5mo ago A 0 tokens original MIT

update-docs

18

rosudrag/ai-praxis

Command Claude Code

Scan documentation for drift from source-of-truth files and update stale sections.

not rated 2 5mo ago A 0 tokens original MIT

verify

19

rosudrag/ai-praxis

Command Claude Code

Run a comprehensive verification loop before creating a PR or committing.

not rated 2 5mo ago A 0 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: