agent-profile

Use when a stakeholder request is rough, ambiguous, or underspecified and needs clarification before planning, writing a spec, or creating issues.

Use after a grill-change session is complete to turn the agreement record into an intent-first spec candidate and vertical TDD-ready issue briefs.

Use when a stakeholder request is rough, ambiguous, or underspecified and needs clarification before planning, writing a spec, or creating issues.

Use after a grill-change session is complete to turn the agreement record into an intent-first spec candidate and vertical TDD-ready issue briefs.

Use to run a bounded security-review, patch, and retest loop that stops on green, on no diff, or on a repeated identical finding.

Use before handing off an implementation to compare the diff against the spec, tests, docs, contracts, and safety rules.

Use after synthesis to dispatch the next ready task from the TASKS.md ledger through one subagent-driven implementation cycle, one task per invocation.

Use when changing behavior where a focused failing test or golden fixture must prove RED before implementation and GREEN after the minimal fix.

Use after synthesis to dispatch the next ready task from the TASKS.md ledger through one subagent-driven implementation cycle, one task per invocation.

Use to run a bounded documentation drift scan, update, and re-verify loop that stops when docs match the code, on no diff, or on a repeated identical mismatch.

Use to run a bounded implement, test, and fix loop that stops on green, on no diff, or on a repeated identical failure.

Use to run a bounded review, patch, and retest loop that stops on green, on no diff, or on a repeated identical finding.

Use to run a bounded spec, tests, implementation, and verify cycle that stops on green, on no diff, or on a repeated identical failure.

Use to run a bounded security-review, patch, and retest loop that stops on green, on no diff, or on a repeated identical finding.

Use to run a bounded documentation drift scan, update, and re-verify loop that stops when docs match the code, on no diff, or on a repeated identical mismatch.

Use to run a bounded implement, test, and fix loop that stops on green, on no diff, or on a repeated identical failure.

Use to run a bounded review, patch, and retest loop that stops on green, on no diff, or on a repeated identical finding.

Use to run a bounded spec, tests, implementation, and verify cycle that stops on green, on no diff, or on a repeated identical failure.

Use to run a bounded security-review, patch, and retest loop that stops on green, on no diff, or on a repeated identical finding.

Use to review a proposed change for correctness, security-sensitive behavior, readability, tests, performance when relevant, architecture and contract impact, and generated-file drift.

Review module boundaries, dependency direction, contracts, migration risk, and fit to the product architecture.

Review naming, decomposition, control flow, duplication, comments, error-handling clarity, and unnecessary abstraction.

Use to review a proposed change for correctness, security-sensitive behavior, readability, tests, performance when relevant, architecture and contract impact, and generated-file drift.

Review exploit paths, secret exposure, unsafe permissions, injection, authentication and authorization, supply-chain risk, and data leakage.

Review missing cases, regression coverage, flaky patterns, fixture quality, edge cases, and behavior-versus-implementation testing.

Use to assess whether current documentation through an MCP, docs, or search integration may help with a dependency that may be newer than the client's knowledge.

Use when a scoped implementation can be delegated to an implementation subagent and then independently reviewed for spec compliance before code quality.

Use before handing off an implementation to compare the diff against the spec, tests, docs, contracts, and safety rules.

Use when implementing a meaningful repository change that requires an approved spec before code edits.