A terminal coding agent engineered around four goals: speed, cost, safety, and deep enterprise integration. Pluggable providers, a fully modifiable harness, permission gating with HITL, and trajectory + cache telemetry that stays on your own infrastructure.
This repository also configures its own agents. See what sid-code tells them →
Skill Claude Code
A structured bug-fixing workflow that takes a problem from reproduction and evidence-based cause finding through approval, implementation, testing, and cleanup.
Skill Claude Code
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.
Skill Claude Code
A guided tool for copying Claude Code settings and project configuration into sid-code. It checks what can be moved, asks before writing, and records what was transferred.
Skill Claude Code
A review skill that checks pull-request changes for software licenses, personal information, compliance details, and an audit trail. An audit trail is a record showing what was checked and why.
Skill Claude Code
A review process for a pull request, which is a proposed set of code changes. It examines the changed code and its surrounding files for bugs, security problems, design issues, and lint errors.
Skill Claude Code
A diagnostic process for producing a structured root-cause analysis of a serious production incident, such as a P0 or P1 outage. It compares logs, measurements, request traces, code changes, and architecture decisions, and gives ranked explanations and actions.
Skill Claude Code
A security review skill for examining code changes in a pull request, which is a proposed set of changes awaiting approval. It reports issues such as injection, exposed secrets, unsafe authentication, weak cryptography, vulnerable dependencies, and infrastructure mistakes.
Skill Claude CodeCodex
A guided helper for creating a new coding-agent skill, meaning a set of instructions that teaches the agent how to handle a particular task.
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: