deepest-plan

Plugin deepest-plan from marketplace deepest-plan-dev in krzemienski/deepest-plan-plugin. Commands read from the repo's manifest — 1 month ago.

Skills (19)

• accessibility-audit

  WCAG 2.1 AA audit via axe-core, keyboard-navigation probe, and screen-reader label verification. Required for any UI plan that ships or modifies a user-visible surface. Optional skill listed in deepest-plan tool_enrichment when in scope.

• api-validation

  API platform validation via curl / httpie against real running servers. Captures full response bodies, headers, status codes. Tests CRUD, auth, error paths, pagination, rate limiting. Cited as platform_skill on API gates in deepest-plan output.

• baseline-quality-assessment

  Capture "before" state BEFORE making changes. Validation later compares against this baseline to prove improvement without regression. Invoked when deepest-plan modifies existing behavior (not greenfield).

• cli-validation

  CLI platform validation via direct binary execution. Captures stdout, stderr, exit codes, file output, pipe behavior. Cited as platform_skill on CLI gates in deepest-plan output.

• condition-based-waiting

  Smart waiting patterns for async operations. Wait for observable conditions (DOM state, HTTP status, file presence, log line) with timeout and failure path — never arbitrary sleeps. Used inside deepest-plan preflight and validation_gate execute blocks.

• create-validation-plan

  Generates e2e-evidence/validation-plan.md — the contract listing every user journey, PASS criteria, evidence requirements, and execution order BEFORE any evidence is captured. Referenced as the first execution command in every deepest-plan PLAN.md.

• deepest-plan

  Deepest-mode planning. Merges ck:plan ranking, deepen-prompt-plan confidence scoring, transform-validation-prompt gate injection, and create-validation-plan phase hierarchy into one consensus-driven workflow. Use when asked to 'plan deepest', 'plan hard and deep', 'deepest mode plan', 'make this pla

• e2e-validate

  End-to-end validation orchestrator. Detects platform, runs preflight, exercises user journeys via real systems, captures evidence, writes PASS/FAIL verdicts, produces a report. Zero mocks. Supports iOS, web, API, CLI, and fullstack. Backing skill for the `/deepest:validate` command.

• error-recovery

  Structured 3-strike recovery loop for validation failures. Diagnoses root cause, applies fix, re-validates from the failed gate. Invoked by deepest-plan when any gate FAILs during execution.

• fullstack-validation

  Fullstack validation using strict bottom-up approach — Database → API → Frontend. Validates each layer independently, then tests integration end-to-end. References api-validation and web-validation for layer-specific procedures. Cited as platform_skill on fullstack gates in deepest-plan output.

• functional-validation

  The 4-step validation protocol — Build → Exercise through UI → Capture evidence → Write verdict. Cited as `protocol="functional-validation"` on every validation_gate in deepest-plan output. Enforces real-system execution; never write mocks or test files.

• gate-validation-discipline

  Evidence-based verdict discipline. Requires personal evidence examination, specific proof citations, and criterion-to-evidence matching before marking any gate, task, or checkpoint complete. Cited as `verdict_by="gate-validation-discipline"` on every validation_gate and phase_gate in deepest-plan ou

• ios-validation

  iOS / macOS platform validation via xcrun simctl + idb. Builds, installs, launches, exercises via deep links or UI taps. Captures screenshots + logs. Cited as platform_skill on iOS gates in deepest-plan output.

• no-mocking-validation-gates

  Enforces the Iron Rule — no mocks, stubs, test doubles, or test files. Detects mock-creation intent and redirects to real system validation. Cited by every gate and mock_guard in deepest-plan output.

• parallel-validation

  Parallel dispatch patterns for independent validation gates or journeys. Launches multiple sub-agents in a single-message Task burst. Optional skill listed in deepest-plan tool_enrichment when journeys are provably independent.

• preflight

  Pre-execution checklist. Verifies prerequisites (servers, databases, tools, env vars, domains) before validation runs. Auto-fixes common failures. Produces e2e-evidence/preflight-report.md with CLEAR | BLOCKED | WARN verdict. First task of every phase in deepest-plan output.

• responsive-validation

  Viewport-matrix testing. Verifies UI renders correctly across mobile / tablet / desktop breakpoints. Captures per-breakpoint screenshots as evidence. Optional skill listed in deepest-plan tool_enrichment when a UI must work across devices.

• verification-before-completion

  Pre-completion checklist for phase transitions and claims. Requires running verification commands and citing evidence before asserting work is "complete" or "ready to ship". Cited inside every phase_gate regression_check in deepest-plan output.

• web-validation

  Web platform validation patterns. Uses Playwright MCP, agent-browser CLI, or Chrome DevTools to exercise real dev servers. Captures screenshots, console logs, network responses, DOM snapshots. Cited as platform_skill on web-platform validation gates in deepest-plan output.

Slash commands (7)

• /deepest-plan:deepest-setup

  One-time deepest-plan validation init for this project (creates .planning/ + e2e-evidence/ + .gitignore entries).

• /deepest-plan:deepest-validate-audit

  Read-only validation audit — capture evidence and classify findings without changing code.

• /deepest-plan:deepest-validate-ci

  Non-interactive validation for CI/CD — no approval gates, exit codes, no fix loop.

• /deepest-plan:deepest-validate-fix

  Auto-fix validation failures and re-validate (3-strike protocol).

• /deepest-plan:deepest-validate-plan

  Generate e2e-evidence/validation-plan.md with PASS criteria for every journey (no execution).

• /deepest-plan:deepest-validate

  Execute the full validation pipeline: preflight → plan → exercise → verdict → report.

• /deepest-plan:deepest

  Deepest-mode plan — consensus + gates + synthesis. Args: [task] [--synthesis N] [--monolith|--tree|--both] [--debate]

Similar plugins