agent-directives

Load when the user asks to review a PR, branch, diff, local changes, or says approve, merge, or check this change for bugs, regressions, security, maintainability, or merge risk.

Load when changes touch imports, exports, public APIs, file moves, packages, services, layers, shared code, dependency direction, cycles, or the user asks if architecture boundaries still hold.

Load when the user has a PRD, issue, acceptance criteria, or requirements doc and wants a staged implementation task list with relevant files, tests, validation steps, and review checkpoints.

Load when the user wants to turn a feature idea, product request, vague requirement, or problem statement into a concrete PRD/spec before implementation planning or coding.

Load when executing an existing implementation plan with multiple mostly independent tasks using delegated subagents, fresh task context, parent-owned review, and final integration verification.

Load when the user asks for adversarial review, independent failure-mode review, red-team review of a change, or when a high-risk, broad, or agent-authored implementation needs a separate reviewer to find credible bugs, regressions, missing proof, or reasons the change may not work.

Load when adding or reviewing agent harness hooks, start/stop hooks, pre-write/pre-command hooks, post-change automation, or deterministic agent workflow scripts.

Load when adding or reviewing MCP servers, agent tools, tool schemas, internal API bridges, structured search, docs/ticketing/analytics connectors, or agent-accessible write tools.

Load when reviewing TypeScript/JavaScript refactors, cleanup, AI-generated code, shared utilities, dead code, duplication, complexity, circular dependencies, Fallow output, or maintainability drift.

Load when reviewing changes that may affect production safety: persistence, migrations, external services, async jobs, auth/security/privacy, infra/config/deploy, critical user paths, performance/scale, or cross-service compatibility.

Load when the user asks whether implementation matches a spec, requirements doc, acceptance criteria, or design plan, or says check what is missing, incomplete, or divergent before merge.

Load when the user asks to write or review tests, TDD cases, eval scenarios, coverage, assertions, or mocks, or says tests are shallow, flaky, brittle, or too close to implementation.

Load when implementation is past GREEN/REFACTOR and the user asks for pre-PR verification, self-audit, scope check, weakest-assumption review, anomaly triage, or a confidence check.

Load when the user reports a bug, failing test, CI/build/lint/typecheck failure, regression, flaky behavior, unexpected behavior, or asks to fix a failure or root-cause it.