Opencode Coding

Enforce senior-level coding standards with a focus on verification, minimal diffs, and evidence-based bug fixing.

Install
cmdop skills install agensi-opencode-coding

Opencode Coding is a skill published by agensi that imposes a structured engineering workflow on AI coding agents. Rather than generating speculative code changes, it mandates a three-part contract: reproduce and verify failures before touching code, implement the narrowest defensible change, and report exactly what was verified, what was inferred, and what remains unknown.

The skill is framework-agnostic, meaning it can be applied to any tech stack without configuration changes. Its evidence-based debugging approach requires the agent to identify root causes and reproduce failures before proposing a fix, reducing the risk that a patch addresses symptoms rather than the underlying problem.

Minimal-impact diffs are a core constraint: the skill directs the agent to preserve existing project patterns and limit the scope of every change, which lowers regression risk in established codebases. A verification-first workflow requires running targeted tests, linters, or manual validation steps before a task is declared complete, rather than relying on visual inspection of generated code.

Every completed task produces a standardized Response Contract output that explicitly labels which conclusions are verified, which are inferred, and which are still unknown. This makes the agent’s confidence level transparent and auditable.

The skill is intended for complex feature implementation, surgical bug fixing, refactoring legacy modules, and PR reviews where functional correctness must be demonstrated rather than assumed.

Use cases

  • Enforce minimal, localized diffs when fixing bugs in a production codebase
  • Require an agent to reproduce a failure before generating a fix
  • Apply consistent verification steps (tests, linters) before marking a task complete
  • Refactor legacy modules while preserving existing project patterns
  • Generate PR reviews that separate verified findings from inferred observations
  • Implement new features with a systematic engineering contract rather than speculative generation

When to use it

  • When an agent's code changes must be scoped and traceable to a specific root cause
  • When working in a codebase where regression risk from broad changes is a concern
  • When auditability of what was actually verified versus assumed is required
  • When enforcing a consistent coding standard across multiple AI models or agents

When not to use it

  • When rapid, exploratory prototyping is the goal and strict verification overhead is unwanted
  • When no tools or test infrastructure exist to support the verification-first workflow
  • When the task has no exposed tools list — this skill provides no callable tools itself