grill

Plugin grill in xiaolai/codex-marketplace. Commands read from the repo's manifest — 1 month ago.

Skills (8)

• grill-architecture

  Use to deeply analyze core architecture — entry points, module boundaries, dependency graph, data flow, and structural patterns. Part of the grill deep-dive phase. Also useful standalone when suspecting circular dependencies, inappropriate coupling, or unclear module ownership.

• grill-core

  Core conventions for all grill analysis skills — output formatting, severity ratings, evidence standards, and untrusted-input handling. Load whenever a grill analysis skill is active.

• grill-edge-cases

  Use to hunt for edge cases, race conditions, boundary values, partial failures, and implicit assumptions across a codebase. Part of the grill deep-dive phase under Paranoid Mode. Also useful standalone after a production incident from unexpected input, to find similar assumption-violations across th

• grill-error-handling

  Use to analyze error handling, logging, observability, and configuration management across a codebase. Part of the grill deep-dive phase. Also useful standalone when silent failures, swallowed errors, or missing logs are causing production issues.

• grill-recon

  Use for initial codebase reconnaissance — quickly survey project structure, tech stack, config files, and existing documentation to establish context before deeper analysis. Always the first skill run during a grill review, and also useful standalone when orienting to an unfamiliar repository.

• grill-roast

  Use when the user asks to grill, roast, audit, interrogate, deep-review, or do a multi-angle architecture review of a codebase or directory. Orchestrates 4-6 specialized analysis skills (recon, architecture, error-handling, security, testing, optionally edge-cases) and synthesizes findings into a se

• grill-security

  Use to analyze the security surface of a codebase — authentication, authorization, input validation, secrets handling, and dependency vulnerabilities. Part of the grill deep-dive phase. Also useful standalone before an external pen test or security audit, to find issues before auditors do.

• grill-testing

  Use to analyze test coverage, test quality, CI/CD setup, and testing infrastructure. Part of the grill deep-dive phase. Also useful standalone when onboarding to a new project and needing to know which parts have coverage and which are completely untested.

Slash commands (1)

• /grill:roast

  Deep codebase interrogation — multi-angle architecture review that forces rigorous, actionable analysis

Subagents (6)

• architecture

  Use this agent to deeply analyze core architecture — entry points, module boundaries, dependency graph, data flow, and structural patterns. Part of the grill deep-dive phase. Also the right choice for structural problems such as circular dependencies, module coupling, or import errors that suggest t

• edge-cases

  Use this agent to hunt for edge cases, race conditions, boundary values, partial failures, and implicit assumptions across a codebase. Part of the grill deep-dive phase (Paranoid Mode). Also use it outside a full review to hunt a whole class of assumption violations after an incident, such as code t

• error-handling

  Use this agent to analyze error handling, logging, observability, and configuration management across a codebase. Part of the grill deep-dive phase. Also the right choice for silent failures — errors swallowed by catch blocks that never reach the logs. Not for secrets handling or sensitive data in l

• recon

  Use this agent for initial codebase reconnaissance — quickly surveys project structure, tech stack, config files, and existing documentation to establish context before deeper analysis. Also use it to orient in an unfamiliar or freshly cloned repository before making changes. Not for analysis or cri

• security

  Use this agent to analyze the security surface of a codebase — authentication, authorization, input validation, secrets handling, and dependency vulnerabilities. Part of the grill deep-dive phase. Also useful proactively, for example before an external pen test, to find concrete exploit scenarios fi

• testing

  Use this agent to analyze test coverage, test quality, CI/CD setup, and testing infrastructure. Part of the grill deep-dive phase. Also use it to map which modules are tested and which are not before starting new development. Not for reviewing the production code itself — structure, security, and fa

Similar plugins