agents-templated 2.2.11 → 2.2.13

package/agents/commands/README.md

@@ -1,70 +0,0 @@
-# Deterministic Slash Command Contracts
-
-This directory is the modular source of truth for slash-command execution contracts.
-
-- Global protocol and safety framework: `AGENTS.MD` → `Deterministic Slash Command System Standard`
-- Global response schema: `agents/commands/SCHEMA.md`
-- Command contracts:
-  - `plan.md`
-  - `task.md`
-  - `scaffold.md`
-  - `fix.md`
-  - `refactor.md`
-  - `audit.md`
-  - `perf.md`
-  - `test.md`
-  - `pr.md`
-  - `release.md`
-  - `docs.md`
-  - `problem-map.md`
-  - `scope-shape.md`
-  - `arch-check.md`
-  - `ux-bar.md`
-  - `debug-track.md`
-  - `risk-review.md`
-  - `quality-gate.md`
-  - `perf-scan.md`
-  - `release-ready.md`
-  - `docs-sync.md`
-  - `learn-loop.md`
-
-Execution requirements:
-- Parse slash commands deterministically.
-- Return structured output only.
-- No conversational fallback in slash mode.
-- Enforce destructive confirmation token: `CONFIRM-DESTRUCTIVE:<target>`.
-- Enforce unique command purpose for each primary workflow command.
-
-## Command Integrity Guards
-
-- Primary workflow commands must have unique purpose identifiers.
-- Duplicate command purpose definitions fail CLI startup validation.
-- Deprecated aliases are not part of the active command surface.
-
-## Publish Inclusion
-
-The npm package includes command contracts from both:
-
-- `agents/commands/` (root mirror)
-- `templates/agents/commands/` (scaffold source)
-
-## Workflow Command Mapping
-
-Use these lifecycle commands as the recommended specialist sequence:
-
-- `problem-map` -> `plan.md`
-- `scope-shape` -> `plan.md`
-- `arch-check` -> `plan.md`
-- `ux-bar` -> `plan.md`
-- `debug-track` -> `fix.md`
-- `risk-review` -> `audit.md`
-- `quality-gate` -> `test.md`
-- `perf-scan` -> `perf.md`
-- `release-ready` -> `release.md`
-- `docs-sync` -> `docs.md`
-- `learn-loop` -> `task.md`
-
-The CLI command `agents-templated workflow` prints this lifecycle in order:
-
-Think -> Plan -> Build -> Review -> Test -> Ship -> Reflect
-

package/agents/commands/SCHEMA.md

@@ -1,22 +0,0 @@
-# Slash Command Output Schema
-
-All slash command responses MUST include the following top-level fields:
-
-- `command`
-- `execution_id`
-- `mode`
-- `status`
-- `inputs`
-- `prechecks`
-- `execution_log`
-- `artifacts`
-- `risks`
-- `safety_checks`
-- `stop_condition`
-- `next_action`
-
-Constraints:
-- `mode` MUST be one of: `slash-command`, `slash-command-auto`.
-- `status` MUST be one of: `completed`, `blocked`, `failed`.
-- If a field value is unknown, set it to `null`.
-- Unknown or malformed slash commands MUST return structured error output and stop.

package/agents/commands/arch-check.md

@@ -1,33 +0,0 @@
-# /arch-check
-
-## A. Intent
-Validate architecture decisions, dependency boundaries, and failure handling before coding.
-
-## B. When to Use
-Use after scope lock and before implementation starts.
-
-## C. Required Inputs
-- Scoped feature set
-- Existing system boundaries
-- Non-functional requirements
-
-## D. Deterministic Execution Flow
-1. Map data and control flow.
-2. Identify component boundaries.
-3. Enumerate failure modes.
-4. Define testing and validation checkpoints.
-5. Emit architecture decision set.
-
-## E. Structured Output Template
-- `architecture_summary`
-- `boundaries[]`
-- `data_flow`
-- `failure_modes[]`
-- `validation_plan[]`
-
-## F. Stop Conditions
-- Critical dependency unclear.
-- Failure modes not covered.
-
-## G. Safety Constraints
-- Include security and testing gates for each critical path.

package/agents/commands/audit.md

@@ -1,38 +0,0 @@
-# /audit
-
-## A. Intent
-Run structured engineering audit across security, correctness, and maintainability.
-
-## B. When to Use
-Use before high-impact merges, releases, and external reviews.
-
-## C. Required Inputs
-- Audit scope
-- Risk profile
-- Compliance baseline
-- Hardening profile requirement (if applicable)
-
-## D. Deterministic Execution Flow
-1. Resolve audit scope.
-2. Run static checks.
-3. Run security checks.
-4. Run dependency/config checks.
-5. Verify hardening evidence when hardening-required profile applies.
-6. Classify findings by severity.
-7. Emit audit report.
-
-## E. Structured Output Template
-- `scope`
-- `checks_executed[]`
-- `findings[]`
-- `severity_summary`
-- `remediation_plan[]`
-- `hardening_evidence_status`
-
-## F. Stop Conditions
-- Inaccessible scope.
-- Unavailable tooling.
-
-## G. Safety Constraints
-- Classify secret leaks and auth bypass as critical.
-- Classify missing hardening verification evidence as release-blocking when hardening is required.

package/agents/commands/debug-track.md

@@ -1,33 +0,0 @@
-# /debug-track
-
-## A. Intent
-Produce a root-cause-first defect investigation path with bounded fixes.
-
-## B. When to Use
-Use for bugs, regressions, and unexpected runtime behavior.
-
-## C. Required Inputs
-- Defect symptom
-- Reproduction context
-- Expected behavior
-
-## D. Deterministic Execution Flow
-1. Reproduce defect consistently.
-2. Trace data and execution path.
-3. Confirm root cause with evidence.
-4. Propose minimal patch.
-5. Validate fix and regression safety.
-
-## E. Structured Output Template
-- `reproduction_steps[]`
-- `root_cause`
-- `affected_surface[]`
-- `patch_plan`
-- `regression_checks[]`
-
-## F. Stop Conditions
-- Defect not reproducible.
-- Root cause remains unverified.
-
-## G. Safety Constraints
-- Do not patch symptoms without root-cause evidence.

package/agents/commands/docs-sync.md

@@ -1,33 +0,0 @@
-# /docs-sync
-
-## A. Intent
-Keep documentation aligned with shipped behavior and contract changes.
-
-## B. When to Use
-Use after implementation or release-prep changes.
-
-## C. Required Inputs
-- Code changes summary
-- Updated behavior/contracts
-- Target documentation set
-
-## D. Deterministic Execution Flow
-1. Identify behavior and API changes.
-2. Locate affected docs.
-3. Update docs with minimal accurate edits.
-4. Verify examples and command references.
-5. Emit documentation update summary.
-
-## E. Structured Output Template
-- `docs_updated[]`
-- `behavior_changes[]`
-- `contract_updates[]`
-- `example_checks[]`
-- `remaining_doc_gaps[]`
-
-## F. Stop Conditions
-- Behavior changed with no corresponding doc update.
-- Example commands are unverified.
-
-## G. Safety Constraints
-- Do not publish stale setup or command instructions.

package/agents/commands/docs.md

@@ -1,34 +0,0 @@
-# /docs
-
-## A. Intent
-Generate or update documentation aligned to implemented behavior.
-
-## B. When to Use
-Use when code, APIs, operations, or workflows change.
-
-## C. Required Inputs
-- Documentation scope
-- Source changes
-- Target audience
-
-## D. Deterministic Execution Flow
-1. Resolve source-of-truth artifacts.
-2. Extract behavior and API deltas.
-3. Map deltas to sections.
-4. Apply concise updates.
-5. Validate examples/commands.
-6. Emit docs change report.
-
-## E. Structured Output Template
-- `scope`
-- `sources[]`
-- `sections_updated[]`
-- `example_validation`
-- `follow_up_actions[]`
-
-## F. Stop Conditions
-- Missing source artifacts.
-- Unresolved ambiguity.
-
-## G. Safety Constraints
-- Do not publish secrets, tokens, or credentials.

package/agents/commands/fix.md

@@ -1,34 +0,0 @@
-# /fix
-
-## A. Intent
-Apply the smallest safe change that resolves a verified defect.
-
-## B. When to Use
-Use for bugs with reproducible evidence.
-
-## C. Required Inputs
-- Defect description
-- Reproduction evidence
-- Target scope
-
-## D. Deterministic Execution Flow
-1. Validate defect evidence.
-2. Reproduce failure.
-3. Locate root cause.
-4. Generate minimal patch.
-5. Execute targeted validation.
-6. Emit fix report.
-
-## E. Structured Output Template
-- `defect_id`
-- `root_cause`
-- `patch_summary`
-- `files_changed[]`
-- `validation_results[]`
-
-## F. Stop Conditions
-- Non-reproducible failure.
-- Root cause unresolved.
-
-## G. Safety Constraints
-- Do not broaden scope beyond defect boundary.

package/agents/commands/learn-loop.md

@@ -1,33 +0,0 @@
-# /learn-loop
-
-## A. Intent
-Capture delivery lessons and convert them into concrete next-cycle actions.
-
-## B. When to Use
-Use after release or milestone completion.
-
-## C. Required Inputs
-- Completed work summary
-- Incident/defect outcomes
-- Team or process observations
-
-## D. Deterministic Execution Flow
-1. Summarize wins and misses.
-2. Identify repeated friction points.
-3. Propose concrete process and tooling actions.
-4. Assign ownership and priority.
-5. Emit next-cycle action list.
-
-## E. Structured Output Template
-- `wins[]`
-- `misses[]`
-- `root_process_issues[]`
-- `next_actions[]`
-- `owner_map`
-
-## F. Stop Conditions
-- No actionable next steps.
-- Lessons are not tied to observable outcomes.
-
-## G. Safety Constraints
-- Avoid vague retrospectives without owned follow-through actions.

package/agents/commands/perf-scan.md

@@ -1,33 +0,0 @@
-# /perf-scan
-
-## A. Intent
-Measure baseline performance and detect regressions with deterministic thresholds.
-
-## B. When to Use
-Use before and after performance-sensitive changes.
-
-## C. Required Inputs
-- Baseline context
-- Target endpoints or flows
-- Performance thresholds
-
-## D. Deterministic Execution Flow
-1. Capture baseline metrics.
-2. Execute candidate workload.
-3. Compare p95/p99 latency and error rates.
-4. Flag regressions with threshold deltas.
-5. Emit optimization priorities.
-
-## E. Structured Output Template
-- `baseline_metrics`
-- `candidate_metrics`
-- `regressions[]`
-- `threshold_checks[]`
-- `recommendations[]`
-
-## F. Stop Conditions
-- Baseline missing.
-- Thresholds undefined.
-
-## G. Safety Constraints
-- Avoid performance claims without before/after evidence.

package/agents/commands/perf.md

@@ -1,34 +0,0 @@
-# /perf
-
-## A. Intent
-Evaluate and optimize performance using measurable baselines.
-
-## B. When to Use
-Use when latency, throughput, memory, or build-time regressions are reported.
-
-## C. Required Inputs
-- Target metrics
-- Baseline environment
-- Optimization scope
-
-## D. Deterministic Execution Flow
-1. Capture baseline metrics.
-2. Identify bottlenecks.
-3. Apply one optimization unit.
-4. Re-measure metrics.
-5. Compare against baseline.
-6. Emit performance report.
-
-## E. Structured Output Template
-- `baseline_metrics`
-- `optimization_units[]`
-- `post_metrics`
-- `regression_check`
-- `recommendation`
-
-## F. Stop Conditions
-- Missing baseline metrics.
-- Non-reproducible benchmark.
-
-## G. Safety Constraints
-- Do not trade security controls for performance.

package/agents/commands/plan.md

@@ -1,34 +0,0 @@
-# /plan
-
-## A. Intent
-Generate an executable implementation plan with ordered steps and risk controls.
-
-## B. When to Use
-Use for non-trivial work requiring sequencing, dependencies, and checkpoints.
-
-## C. Required Inputs
-- Objective
-- Scope boundaries
-- Constraints
-
-## D. Deterministic Execution Flow
-1. Parse objective and constraints.
-2. Extract atomic work units.
-3. Compute dependency order.
-4. Attach validation checkpoints.
-5. Attach risk and rollback notes.
-6. Emit plan artifacts.
-
-## E. Structured Output Template
-- `plan_summary`
-- `work_units[]`
-- `dependency_graph`
-- `validation_checkpoints[]`
-- `risk_register[]`
-
-## F. Stop Conditions
-- Missing objective or scope.
-- Contradictory constraints.
-
-## G. Safety Constraints
-- Include security and testing gates for code-changing units.

package/agents/commands/pr.md

@@ -1,35 +0,0 @@
-# /pr
-
-## A. Intent
-Prepare a deterministic pull request payload with implementation evidence.
-
-## B. When to Use
-Use after validated changes are ready for review.
-
-## C. Required Inputs
-- Change summary
-- Linked issues/tasks
-- Validation evidence
-
-## D. Deterministic Execution Flow
-1. Collect changed files.
-2. Summarize intent and impact.
-3. Attach validation evidence.
-4. Classify risk and rollout impact.
-5. Build reviewer checklist.
-6. Emit PR package.
-
-## E. Structured Output Template
-- `title`
-- `summary`
-- `files_changed[]`
-- `validation_evidence[]`
-- `risk_assessment`
-- `review_checklist[]`
-
-## F. Stop Conditions
-- Missing validation evidence.
-- Open critical findings.
-
-## G. Safety Constraints
-- Block PR package when critical issues remain unresolved.

package/agents/commands/problem-map.md

@@ -1,33 +0,0 @@
-# /problem-map
-
-## A. Intent
-Define the actual user problem and measurable pain signals before solutioning.
-
-## B. When to Use
-Use at the start of an initiative when the request is a feature idea rather than a validated problem.
-
-## C. Required Inputs
-- Problem statement
-- Current user pain examples
-- Target user segment
-
-## D. Deterministic Execution Flow
-1. Extract user outcomes and friction points.
-2. Separate symptoms from root pain.
-3. Identify constraints and non-goals.
-4. Propose a focused problem frame.
-5. Emit acceptance signals for success.
-
-## E. Structured Output Template
-- `problem_frame`
-- `pain_signals[]`
-- `root_causes[]`
-- `target_user_segment`
-- `success_signals[]`
-
-## F. Stop Conditions
-- Missing target user segment.
-- No concrete pain evidence provided.
-
-## G. Safety Constraints
-- Do not lock implementation details in this stage.

package/agents/commands/quality-gate.md

@@ -1,33 +0,0 @@
-# /quality-gate
-
-## A. Intent
-Enforce quality gates using test signals, behavior checks, and regression controls.
-
-## B. When to Use
-Use before release, and after major bug fixes.
-
-## C. Required Inputs
-- Target build/revision
-- Test scope
-- Critical user flows
-
-## D. Deterministic Execution Flow
-1. Run required test layers.
-2. Validate critical user flows.
-3. Inspect flaky or unstable results.
-4. Define required remediations.
-5. Emit pass/conditional/block outcome.
-
-## E. Structured Output Template
-- `test_results[]`
-- `critical_flow_status[]`
-- `quality_findings[]`
-- `required_fixes[]`
-- `gate_status`
-
-## F. Stop Conditions
-- Critical flow untested.
-- Required tests failed.
-
-## G. Safety Constraints
-- Do not mark pass when critical regressions remain open.

package/agents/commands/refactor.md

@@ -1,34 +0,0 @@
-# /refactor
-
-## A. Intent
-Improve internal structure without changing externally observable behavior.
-
-## B. When to Use
-Use for maintainability and modularity improvements.
-
-## C. Required Inputs
-- Target component/module
-- Non-functional goals
-- Behavior invariants
-
-## D. Deterministic Execution Flow
-1. Capture behavior invariants.
-2. Define refactor units.
-3. Apply one unit at a time.
-4. Verify invariants after each unit.
-5. Measure complexity delta.
-6. Emit refactor report.
-
-## E. Structured Output Template
-- `target`
-- `invariants[]`
-- `transformations[]`
-- `behavior_check_results[]`
-- `complexity_delta`
-
-## F. Stop Conditions
-- Invariant violation.
-- Missing baseline behavior.
-
-## G. Safety Constraints
-- Abort on behavior-change risk.

package/agents/commands/release-ready.md

@@ -1,33 +0,0 @@
-# /release-ready
-
-## A. Intent
-Validate release readiness with checks for quality, risk, and rollback.
-
-## B. When to Use
-Use immediately before opening or merging a release PR.
-
-## C. Required Inputs
-- Change summary
-- Validation evidence
-- Deployment path
-
-## D. Deterministic Execution Flow
-1. Confirm test and quality gate outcomes.
-2. Confirm risk-review status.
-3. Verify migration and deploy prerequisites.
-4. Verify rollback plan.
-5. Emit release readiness decision.
-
-## E. Structured Output Template
-- `release_scope`
-- `checks_passed[]`
-- `blocking_issues[]`
-- `rollback_plan`
-- `ready_status`
-
-## F. Stop Conditions
-- Blocking issue unresolved.
-- Rollback plan absent.
-
-## G. Safety Constraints
-- Do not approve release when required evidence is missing.

package/agents/commands/release.md

@@ -1,39 +0,0 @@
-# /release
-
-## A. Intent
-Produce deterministic release readiness decision and rollout contract.
-
-## B. When to Use
-Use when promoting validated changes to release channels.
-
-## C. Required Inputs
-- Version/tag
-- Change manifest
-- Rollback strategy
-- Hardening verification evidence (when required by risk profile)
-
-## D. Deterministic Execution Flow
-1. Validate release prerequisites.
-2. Validate compatibility and migration risks.
-3. Validate security and test gates.
-4. Validate hardening verification evidence when hardening-required profile applies.
-5. Build release notes.
-6. Build rollout and rollback steps.
-7. Emit release contract.
-
-## E. Structured Output Template
-- `version`
-- `release_readiness`
-- `gates[]`
-- `rollout_plan[]`
-- `rollback_plan[]`
-- `release_notes`
-- `hardening_verification`
-
-## F. Stop Conditions
-- Gate failure.
-- Missing rollback strategy.
-
-## G. Safety Constraints
-- Block release when any critical gate fails.
-- Block release when required hardening evidence is missing.

package/agents/commands/risk-review.md

@@ -1,33 +0,0 @@
-# /risk-review
-
-## A. Intent
-Identify release risks that may pass CI but fail in production.
-
-## B. When to Use
-Use before merge or release candidate approval.
-
-## C. Required Inputs
-- Proposed changes
-- Test and validation status
-- Deployment context
-
-## D. Deterministic Execution Flow
-1. Inspect behavior deltas.
-2. Rank risks by impact and likelihood.
-3. Validate mitigation or rollback paths.
-4. Identify missing tests.
-5. Emit ship recommendation.
-
-## E. Structured Output Template
-- `risk_findings[]`
-- `severity_summary`
-- `mitigations[]`
-- `rollback_readiness`
-- `release_recommendation`
-
-## F. Stop Conditions
-- High-severity risk has no mitigation.
-- Rollback path is undefined.
-
-## G. Safety Constraints
-- Block release for unresolved high-severity findings.