brazil-bench

9 mods across 1 repository, 11 stars between them.

strands-agents-sops

01

brazil-bench/pourpoise

MCP server Claude CodeCodexCursor +2

MCP server "strands-agents-sops" as configured in brazil-bench/pourpoise. Launched with strands-agents-sops mcp --sop-paths ./sop:./venv/lib/python3.13/site-packages/st.

11 7mo ago A tokens not measured original Apache-2.0

code-assist

02

brazil-bench/pourpoise

Skill Claude CodeCodex

This sop guides the implementation of code tasks using test-driven development principles, following a structured Explore, Plan, Code, Commit workflow. It balances automation with user collaboration while adhering to existing package patterns and prioritizing readability and extensibility. The agent acts as a…

11 7mo ago A 105 tokens original Apache-2.0

code-task-generator

03

brazil-bench/pourpoise

Skill Claude CodeCodex

This sop generates structured code task files from rough descriptions, ideas, or PDD implementation plans. It automatically detects the input type and creates properly formatted code task files following Amazon's code task format specification. For PDD plans, it processes implementation steps one at a time to allow…

11 7mo ago A 66 tokens original Apache-2.0

codebase-summary

04

brazil-bench/pourpoise

Skill Claude CodeCodex

This sop analyzes a codebase and generates comprehensive documentation including structured metadata files that describe the system architecture, components, interfaces, and workflows. It can create targeted documentation files like AGENTS.md (README for AI agents), README.md, CONTRIBUTING.md, or generate a complete…

11 7mo ago A 82 tokens original Apache-2.0

compare-attempts

05

brazil-bench/pourpoise

Skill Claude CodeCodex

This SOP compares evaluated brazil-bench attempts across multiple dimensions to produce a ranked leaderboard and detailed comparison summary. It supports up to 10 attempts in the "Top 10" format, automatically pruning lower-ranked entries when more are added.

11 7mo ago A 52 tokens original Apache-2.0

evaluate-attempt

06

brazil-bench/pourpoise

Skill Claude CodeCodex

This SOP evaluates a completed brazil-bench attempt against the spec.md requirements, capturing metrics for comparison across orchestration patterns. Supports Python and Swift/iOS projects.

11 7mo ago A 36 tokens original Apache-2.0

file-issues

07

brazil-bench/pourpoise

Skill Claude CodeCodex

Parse evaluation reports and create GitHub issues on attempt repositories for each shortcoming, warning, or improvement opportunity identified during review. Supports Python and Swift/iOS projects.

11 7mo ago A 37 tokens original Apache-2.0

pdd

08

brazil-bench/pourpoise

Skill Claude CodeCodex

This sop guides you through the process of transforming a rough idea into a detailed design document with an implementation plan and todo list. It follows the Prompt-Driven Development methodology to systematically refine your idea, conduct necessary research, create a comprehensive design, and develop an actionable…

11 7mo ago A 76 tokens original Apache-2.0

re-evaluate

09

brazil-bench/pourpoise

Skill Claude CodeCodex

Re-evaluate attempt repositories after issues are closed, update evaluation reports, and file new issues for any regressions or newly discovered problems.

11 7mo ago A 31 tokens original Apache-2.0