repo-harness 0.8.1 → 0.8.2

package/AGENTS.md

@@ -30,11 +30,14 @@ This repository self-hosts the `repo-harness` contract; the former `repo-harness
 - Keep `assets/workflow-contract.v1.json` and `.ai/harness/workflow-contract.json` in sync.
 - Keep `CLAUDE.md` and `AGENTS.md` short; put detailed guidance in `docs/reference-configs/`.
 - Treat Codex auto-compact as a fallback only; use `.ai/harness/handoff/current.md` and `.ai/harness/handoff/resume.md` for long-task rollover.
+- Treat `.ai/harness/checks/*.latest.{json,md}` and `.ai/harness/runs/` as ignored runtime evidence cache; commit durable conclusions in `tasks/reviews/`, `tasks/contracts/`, `tasks/notes/`, or `docs/researches/` instead.
+- Treat architecture/spec/research docs as the human reading entrypoint. Before closing a workflow, promote durable conclusions into `docs/architecture/`, `docs/researches/`, `docs/spec.md`, or `tasks/lessons.md`; then archive fulfilled plan/contract/review/notes/todo artifacts so root workflow surfaces represent active work only. `.rgignore` hides archived workflow artifacts and runtime evidence from default `rg` searches; use explicit paths or `rg -uu` for audits.
 - Treat `_ref/` as an occasional ignored external reference checkout cache, not a commit surface or daily workflow. Agents may read or refresh it for comparison; when it influences a decision, cite the source repo plus commit/tag and path in `tasks/notes/` or `docs/researches/`.
 - Treat `deploy/` as the trackable deployment and operations surface for runbooks, submission materials, release checklists, helper scripts, ordered SQL files under `deploy/sql/`, and env examples.
 - Treat `_ops/` as ignored local operations state for secrets, real env files, provider state, artifacts, logs, and scratch files; do not commit or agent-edit `_ops/*`.
 - Treat contract-level task execution as worktree-first: `scripts/plan-to-todo.sh --plan <approved-plan>` starts `scripts/contract-worktree.sh start --plan <approved-plan>` when policy enables it, and completed blocks finish through Waza `/check` plus `scripts/contract-worktree.sh finish`.
-- After Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete plan, capture it with `scripts/capture-plan.sh --slug <slug> --title <title>` so `plans/` becomes the file-backed source of truth; if the user has already approved implementation, capture with `--status Approved --execute` or run `scripts/plan-to-todo.sh --plan <active-plan>`.
+- After Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete work-package plan, capture it with `scripts/capture-plan.sh --artifact-level work-package --slug <slug> --title <title>` so `plans/` becomes the file-backed source of truth; if the user has already approved implementation, capture with `--status Approved --execute --promotion-reason <merge_boundary|rollback_boundary|verification_boundary|risk_boundary|human_decision_boundary|worktree_boundary>` or run `scripts/plan-to-todo.sh --plan <active-plan>`.
+- Promote work into a top-level `plans/plan-*.md` only when `Artifact Level: work-package` is justified by a merge/PR unit, rollback surface, independent verification boundary, review/acceptance boundary, high-risk surface, or otherwise cannot remain a checklist item in the current active plan or sprint backlog. Inline sprint rows and checklist rows stay in the sprint backlog or active plan `## Task Breakdown`; contract rows may expand into plan -> contract -> review -> notes only through the work-package gate.
 - If current repo state conflicts with the task, open an isolated `codex/<task-slug>` worktree, finish there, run Waza `/check`-style validation, then merge back to `main` without absorbing unrelated dirty changes.
 - Route product discovery to gstack `office-hours`, complex engineering plans to gstack `plan-eng-review`, design plans to gstack `plan-design-review`, and daily small/medium planning, bug hunts, and checks to Waza `/think`, `/hunt`, and `/check`.
 - Codex automation profile is runtime-referenced, not vendored: required skills are `health`, `check`, and `diagram-design` from `~/.codex/skills`.

package/CLAUDE.md

@@ -30,11 +30,14 @@ This repository self-hosts the `repo-harness` contract; the former `repo-harness
 - Keep `assets/workflow-contract.v1.json` and `.ai/harness/workflow-contract.json` in sync.
 - Keep `CLAUDE.md` and `AGENTS.md` short; put detailed guidance in `docs/reference-configs/`.
 - Treat Codex auto-compact as a fallback only; use `.ai/harness/handoff/current.md` and `.ai/harness/handoff/resume.md` for long-task rollover.
+- Treat `.ai/harness/checks/*.latest.{json,md}` and `.ai/harness/runs/` as ignored runtime evidence cache; commit durable conclusions in `tasks/reviews/`, `tasks/contracts/`, `tasks/notes/`, or `docs/researches/` instead.
+- Treat architecture/spec/research docs as the human reading entrypoint. Before closing a workflow, promote durable conclusions into `docs/architecture/`, `docs/researches/`, `docs/spec.md`, or `tasks/lessons.md`; then archive fulfilled plan/contract/review/notes/todo artifacts so root workflow surfaces represent active work only. `.rgignore` hides archived workflow artifacts and runtime evidence from default `rg` searches; use explicit paths or `rg -uu` for audits.
 - Treat `_ref/` as an occasional ignored external reference checkout cache, not a commit surface or daily workflow. Agents may read or refresh it for comparison; when it influences a decision, cite the source repo plus commit/tag and path in `tasks/notes/` or `docs/researches/`.
 - Treat `deploy/` as the trackable deployment and operations surface for runbooks, submission materials, release checklists, helper scripts, ordered SQL files under `deploy/sql/`, and env examples.
 - Treat `_ops/` as ignored local operations state for secrets, real env files, provider state, artifacts, logs, and scratch files; do not commit or agent-edit `_ops/*`.
 - Treat contract-level task execution as worktree-first: `scripts/plan-to-todo.sh --plan <approved-plan>` starts `scripts/contract-worktree.sh start --plan <approved-plan>` when policy enables it, and completed blocks finish through Waza `/check` plus `scripts/contract-worktree.sh finish`.
-- After Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete plan, capture it with `scripts/capture-plan.sh --slug <slug> --title <title>` so `plans/` becomes the file-backed source of truth; if the user has already approved implementation, capture with `--status Approved --execute` or run `scripts/plan-to-todo.sh --plan <active-plan>`.
+- After Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete work-package plan, capture it with `scripts/capture-plan.sh --artifact-level work-package --slug <slug> --title <title>` so `plans/` becomes the file-backed source of truth; if the user has already approved implementation, capture with `--status Approved --execute --promotion-reason <merge_boundary|rollback_boundary|verification_boundary|risk_boundary|human_decision_boundary|worktree_boundary>` or run `scripts/plan-to-todo.sh --plan <active-plan>`.
+- Promote work into a top-level `plans/plan-*.md` only when `Artifact Level: work-package` is justified by a merge/PR unit, rollback surface, independent verification boundary, review/acceptance boundary, high-risk surface, or otherwise cannot remain a checklist item in the current active plan or sprint backlog. Inline sprint rows and checklist rows stay in the sprint backlog or active plan `## Task Breakdown`; contract rows may expand into plan -> contract -> review -> notes only through the work-package gate.
 - If current repo state conflicts with the task, open an isolated `codex/<task-slug>` worktree, finish there, run Waza `/check`-style validation, then merge back to `main` without absorbing unrelated dirty changes.
 - Route product discovery to gstack `office-hours`, complex engineering plans to gstack `plan-eng-review`, design plans to gstack `plan-design-review`, and daily small/medium planning, bug hunts, and checks to Waza `/think`, `/hunt`, and `/check`.
 - Codex automation profile is runtime-referenced, not vendored: required skills are `health`, `check`, and `diagram-design` from `~/.codex/skills`.

package/README.es.md

@@ -85,7 +85,7 @@ artifacts.
 ## Novedades
 
 Las notas de versión viven en [`docs/CHANGELOG.md`](docs/CHANGELOG.md). La línea
-actual es `0.8.1`.
+actual es `0.8.2`.
 
 ## Cómo funciona
 
@@ -419,8 +419,8 @@ Guards habituales:
 
 ## Release actual
 
-- npm package: `repo-harness@0.8.1`
-- Generated workflow stamp: `repo-harness@0.8.1+template@0.8.1`
+- npm package: `repo-harness@0.8.2`
+- Generated workflow stamp: `repo-harness@0.8.2+template@0.8.2`
 - GitHub repository: `Ancienttwo/repo-harness`
 - Release history: [`docs/CHANGELOG.md`](docs/CHANGELOG.md)
 

package/README.fr.md

@@ -85,7 +85,7 @@ l'emportent.
 ## Nouveautés
 
 Les notes de version vivent dans [`docs/CHANGELOG.md`](docs/CHANGELOG.md). La
-ligne actuelle est `0.8.1`.
+ligne actuelle est `0.8.2`.
 
 ## Comment ça marche
 
@@ -424,8 +424,8 @@ Guards courants :
 
 ## Release actuelle
 
-- npm package : `repo-harness@0.8.1`
-- Generated workflow stamp : `repo-harness@0.8.1+template@0.8.1`
+- npm package : `repo-harness@0.8.2`
+- Generated workflow stamp : `repo-harness@0.8.2+template@0.8.2`
 - GitHub repository : `Ancienttwo/repo-harness`
 - Release history : [`docs/CHANGELOG.md`](docs/CHANGELOG.md)
 

package/README.ja.md

@@ -75,7 +75,7 @@ review、checks、handoff と食い違う場合は、source artifacts を優先
 ## What's New
 
 リリースノートは [`docs/CHANGELOG.md`](docs/CHANGELOG.md) にあります。現在の
-ラインは `0.8.1` です。
+ラインは `0.8.2` です。
 
 ## 仕組み
 
@@ -398,8 +398,8 @@ hook がブロックしたときは、まず terminal の構造化された出
 
 ## 現在の Release
 
-- npm package：`repo-harness@0.8.1`
-- Generated workflow stamp：`repo-harness@0.8.1+template@0.8.1`
+- npm package：`repo-harness@0.8.2`
+- Generated workflow stamp：`repo-harness@0.8.2+template@0.8.2`
 - GitHub repository：`Ancienttwo/repo-harness`
 - Release history：[`docs/CHANGELOG.md`](docs/CHANGELOG.md)
 

package/README.md

@@ -79,7 +79,7 @@ active plan, contract, review, checks, or handoff, the source artifacts win.
 ## What's New
 
 Release notes live in [`docs/CHANGELOG.md`](docs/CHANGELOG.md). The current line
-is `0.8.1`.
+is `0.8.2`.
 
 ## How It Works
 
@@ -599,8 +599,8 @@ Most common guards:
 
 ## Current Release
 
-- npm package: `repo-harness@0.8.1`
-- Generated workflow stamp: `repo-harness@0.8.1+template@0.8.1`
+- npm package: `repo-harness@0.8.2`
+- Generated workflow stamp: `repo-harness@0.8.2+template@0.8.2`
 - GitHub repository: `Ancienttwo/repo-harness`
 - Release history: [`docs/CHANGELOG.md`](docs/CHANGELOG.md)
 

package/README.zh-CN.md

@@ -69,7 +69,7 @@ review、checks 或 handoff 冲突，以 source artifacts 为准。
 
 ## What's New
 
-Release notes 见 [`docs/CHANGELOG.md`](docs/CHANGELOG.md)，当前版本线是 `0.8.1`。
+Release notes 见 [`docs/CHANGELOG.md`](docs/CHANGELOG.md)，当前版本线是 `0.8.2`。
 
 ## 工作原理
 
@@ -445,8 +445,8 @@ hook block 工作时，先看 terminal 里的结构化输出。核心字段是
 
 ## 当前 Release
 
-- npm package：`repo-harness@0.8.1`
-- Generated workflow stamp：`repo-harness@0.8.1+template@0.8.1`
+- npm package：`repo-harness@0.8.2`
+- Generated workflow stamp：`repo-harness@0.8.2+template@0.8.2`
 - GitHub repository：`Ancienttwo/repo-harness`
 - Release history：[`docs/CHANGELOG.md`](docs/CHANGELOG.md)
 

package/assets/hooks/pre-edit-guard.sh

@@ -115,12 +115,12 @@ run_edit_plan_gate() {
   if [[ -z "$gate_plan" || ! -f "$gate_plan" ]]; then
     echo "[PlanStatusGuard] No active plan covers implementation edit: $FILE_PATH"
     if [[ "$mode" == "advice" ]]; then
-      echo "[PlanStatusGuard] Advisory: capture the approved plan with bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --execute"
+      echo "[PlanStatusGuard] Advisory: capture the approved plan with bash scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --execute"
     else
       hook_structured_error \
         "PlanStatusGuard" \
         "Implementation edit to $FILE_PATH without an active plan." \
-        "Capture the approved planning output with bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --execute, or set policy .guards.edit_plan_gate to advice/off for this repo." \
+        "Capture the approved planning output with bash scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --execute, or set policy .guards.edit_plan_gate to advice/off for this repo." \
         "missing_artifact"
       exit 2
     fi

package/assets/hooks/prompt-guard.sh

@@ -530,8 +530,8 @@ emit_pending_orchestration_capture_gate() {
   [[ -n "$source_ref" ]] && source_arg=" --source-ref <source-ref>"
   echo "[PlanCaptureGate] Implementation requested while a pending plan/orchestration discussion has not been captured."
   echo "[PlanCaptureGate] $(workflow_pending_orchestration_summary)"
-  echo "[PlanCaptureGate] Capture the final plan body first; if implementation is already approved, use --status Approved --execute:"
-  echo "  printf '%s\n' '<approved plan body>' | bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --source ${kind:-host-plan} --orchestration-kind ${kind:-host-plan} --route planning --execute${source_arg}"
+  echo "[PlanCaptureGate] Capture the final plan body first; if implementation is already approved, use --status Approved --execute with a work-package promotion reason:"
+  echo "  printf '%s\n' '<approved plan body>' | bash scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --source ${kind:-host-plan} --orchestration-kind ${kind:-host-plan} --route planning --execute${source_arg}"
   return 0
 }
 
@@ -662,7 +662,7 @@ maybe_capture_embedded_approved_plan() {
   fi
 
   echo "[PlanCaptureGate] Embedded approved plan detected. Capturing and projecting before implementation."
-  if ! capture_output="$(printf '%s\n' "$body" | bash "scripts/capture-plan.sh" --slug "$slug" --title "$title" --status Approved --source user-approved-plan --route planning --execute 2>&1)"; then
+  if ! capture_output="$(printf '%s\n' "$body" | bash "scripts/capture-plan.sh" --slug "$slug" --title "$title" --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --source user-approved-plan --route planning --execute 2>&1)"; then
     printf '%s\n' "$capture_output"
     hook_structured_error \
       "PlanCaptureGate" \
@@ -906,18 +906,18 @@ render_prompt_guard_action() {
       echo "[PlanCaptureGate] Approval detected before an active plan artifact exists."
       echo "[PlanCaptureGate] Let the agent run the approved-plan capture path now:"
       echo "  git status --short --branch -uall"
-      echo "  printf '%s\n' '<approved plan body>' | bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --source waza-think --route planning --execute"
+      echo "  printf '%s\n' '<approved plan body>' | bash scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --source waza-think --route planning --execute"
       exit 0
       ;;
     plan_status_no_active_block)
       echo "[PlanStatusGuard] Advisory: No active plan found in plans/. Implementation edits will be blocked at the edit layer until a plan is captured."
-      echo "[PlanStatusGuard] Capture the approved planning output with: bash scripts/capture-plan.sh --slug <slug> --title <title> --status Approved --execute"
+      echo "[PlanStatusGuard] Capture the approved planning output with: bash scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --execute"
       echo "[PlanStatusGuard] If there is no captured planning output yet, run: bash scripts/ensure-task-workflow.sh --slug <slug> --title <title>"
       exit 0
       ;;
     plan_capture_draft_advice)
       echo "[PlanCaptureGate] Approval detected for $plan_status plan: $active_plan"
-      echo "[PlanCaptureGate] Recapture the exact approved plan body with --status Approved --execute, or mark this plan Approved and run:"
+      echo "[PlanCaptureGate] Recapture the exact approved plan body with --artifact-level work-package --promotion-reason <reason> --status Approved --execute, or mark this plan Approved and run:"
       echo "  bash scripts/plan-to-todo.sh --plan $active_plan"
       exit 0
       ;;

package/assets/hooks/session-start-context.sh

@@ -378,7 +378,7 @@ printf '%s\n' '<decision-complete plan body>' | bash ${capture_script} --slug ${
 If the user has already approved implementation:
 
 \`\`\`bash
-printf '%s\n' '<approved plan body>' | bash ${capture_script} --slug ${prompt_slug:-<slug>} --title <title> --status Approved --source ${capture_source} --orchestration-kind ${capture_source} --route planning --execute${source_arg}
+printf '%s\n' '<approved plan body>' | bash ${capture_script} --slug ${prompt_slug:-<slug>} --title <title> --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --source ${capture_source} --orchestration-kind ${capture_source} --route planning --execute${source_arg}
 \`\`\`
 EOF_CONTEXT
 }

package/assets/hooks/stop-orchestrator.sh

@@ -152,7 +152,7 @@ If the planning answer is decision-complete, capture the final plan body before
   printf '%s\n' '<decision-complete plan body>' | bash scripts/capture-plan.sh --slug $(plan_completeness_shell_quote "$prompt_slug") --title ${title_arg} --status Draft --source $(plan_completeness_shell_quote "$kind") --orchestration-kind $(plan_completeness_shell_quote "$kind") --route planning${source_arg}
 
 If the user already approved implementation, use:
-  printf '%s\n' '<approved plan body>' | bash scripts/capture-plan.sh --slug $(plan_completeness_shell_quote "$prompt_slug") --title ${title_arg} --status Approved --source $(plan_completeness_shell_quote "$kind") --orchestration-kind $(plan_completeness_shell_quote "$kind") --route planning --execute${source_arg}
+  printf '%s\n' '<approved plan body>' | bash scripts/capture-plan.sh --slug $(plan_completeness_shell_quote "$prompt_slug") --title ${title_arg} --artifact-level work-package --promotion-reason human_decision_boundary --status Approved --source $(plan_completeness_shell_quote "$kind") --orchestration-kind $(plan_completeness_shell_quote "$kind") --route planning --execute${source_arg}
 
 Use a short English title/source-ref alias in these runtime instructions; do not paste non-ASCII prompt text into command arguments.
 

package/assets/partials/08-orchestration.partial.md

@@ -14,10 +14,12 @@
 ### 3. Plan Node Default
 - Enter plan mode for non-trivial tasks.
 - If no stable product truth exists, run `bash .ai/harness/scripts/new-spec.sh`.
-- When Codex Plan mode or Waza `/think` reaches a decision-complete plan, capture it with `bash .ai/harness/scripts/capture-plan.sh --slug <slug> --title <title>` and the plan text on stdin.
+- When Codex Plan mode or Waza `/think` reaches a decision-complete work-package plan, capture it with `bash .ai/harness/scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason <merge_boundary|rollback_boundary|verification_boundary|risk_boundary|human_decision_boundary|worktree_boundary>` and the plan text on stdin.
+- When the output is only the next checklist row for the current active plan, capture it with `bash .ai/harness/scripts/capture-plan.sh --artifact-level checklist-row --slug <slug> --title <title>` so the row stays in `## Task Breakdown`.
 - If no captured active execution plan exists, run `bash .ai/harness/scripts/new-plan.sh --slug <slug> --title <title>` or capture a finished planning note with `bash .ai/harness/scripts/capture-plan.sh`.
 - If the user asks for a Sprint backlog, run `bash .ai/harness/scripts/new-sprint.sh --slug <slug> --title <title>`; it writes `plans/sprints/*.sprint.md`, not `plans/plan-*.md`.
-- When the user approves implementation, run `bash .ai/harness/scripts/plan-to-todo.sh --plan <active-plan>` or capture the approved plan with `--status Approved --execute`; this creates contract/review/notes scaffolding and leaves plan tasks in `## Task Breakdown`.
+- When the user approves implementation, run `bash .ai/harness/scripts/plan-to-todo.sh --plan <active-plan>` or capture the approved work-package plan with `--artifact-level work-package --promotion-reason <reason> --status Approved --execute`; this creates contract/review/notes scaffolding and leaves plan tasks in `## Task Breakdown`.
+- Promote work into a top-level plan only when `Artifact Level: work-package` and the Promotion Gate are concrete: merge/PR unit, rollback surface, verification boundary, review/acceptance boundary, high-risk surface, and why it cannot stay a checklist row. Inline sprint rows stay in the sprint backlog or active plan `## Task Breakdown`.
 - Re-plan when execution drifts.
 
 ### 4. Research Delegation Strategy

package/assets/partials-agents/02-operating-mode.partial.md

@@ -38,7 +38,7 @@
 - After substantive repo changes, run `bash .ai/harness/scripts/check-task-sync.sh` and `bash .ai/harness/scripts/check-task-workflow.sh --strict`.
 - Primary worktree warns by default; enforce via `.claude/.require-worktree`.
 - Contract-level execution is worktree-first: `.ai/harness/scripts/plan-to-todo.sh --plan <approved-plan>` starts a linked `codex/<slug>` worktree when policy enables it, and `.ai/harness/scripts/contract-worktree.sh finish` merges back only after Waza `/check` and sprint verification pass.
-- After Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete plan, capture it with `.ai/harness/scripts/capture-plan.sh --slug <slug> --title <title>`; if implementation is already approved, capture with `--status Approved --execute` or run `.ai/harness/scripts/plan-to-todo.sh --plan <active-plan>`.
+- After Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete work-package plan, capture it with `.ai/harness/scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason <merge_boundary|rollback_boundary|verification_boundary|risk_boundary|human_decision_boundary|worktree_boundary>` only when `Artifact Level: work-package` and the Promotion Gate are concrete; if implementation is already approved, capture with `--artifact-level work-package --promotion-reason <reason> --status Approved --execute` or run `.ai/harness/scripts/plan-to-todo.sh --plan <active-plan>`. Inline sprint rows stay in the sprint backlog or active plan `## Task Breakdown`; checklist-row captures should use `--artifact-level checklist-row` and must not expand into plan -> contract -> review -> notes.
 - If repo state conflicts with the task, use an isolated `codex/<task-slug>` worktree, validate with Waza `/check`, and merge back to `main` without unrelated dirty changes.
 
 ---

package/assets/partials-agents/03-orchestration.partial.md

@@ -12,7 +12,7 @@
 ### 3. Plan Node Default
 - Enter plan mode for non-trivial tasks.
 - If `docs/spec.md` is missing, run `bash .ai/harness/scripts/new-spec.sh` first.
-- Capture decision-complete Codex Plan mode or Waza `/think` output with `bash .ai/harness/scripts/capture-plan.sh --slug <slug> --title <title>`; if no captured active execution plan exists, use `new-plan.sh`; after approval, run `plan-to-todo.sh` or capture with `--status Approved --execute`.
+- Capture decision-complete work-package output from Codex Plan mode or Waza `/think` with `bash .ai/harness/scripts/capture-plan.sh --slug <slug> --title <title> --artifact-level work-package --promotion-reason <merge_boundary|rollback_boundary|verification_boundary|risk_boundary|human_decision_boundary|worktree_boundary>`; if no captured active execution plan exists, use `new-plan.sh`; after approval, run `plan-to-todo.sh` or capture with `--artifact-level work-package --promotion-reason <reason> --status Approved --execute`.
 - Use `new-sprint.sh` only for Sprint backlogs; it writes `plans/sprints/*.sprint.md`, while PRDs stay in `plans/prds/`.
 - Keep active checklist items in the active plan's `## Task Breakdown`; record only deferred goals in `tasks/todos.md`.
 

package/assets/partials-agents/04-task-protocol.partial.md

@@ -9,7 +9,7 @@ TASK_SOURCES:
   - tasks/reviews/
   - tasks/notes/
   - tasks/lessons.md
-  - .ai/harness/checks/latest.json
+  - .ai/harness/checks/latest.json (ignored runtime evidence)
   - .ai/harness/handoff/current.md
   - plans/
 
@@ -17,7 +17,7 @@ PHASES: research -> spec -> plan -> contract -> implement -> verify -> check ->
 
 ARCHIVE:
   PLAN: plans/archive/
-  TODO: tasks/archive/
+  TASK_ARTIFACTS: tasks/archive/
 
 RULES:
   - Treat repo-local artifact files as the primary cross-agent workflow contract
@@ -28,7 +28,7 @@ RULES:
   - Treat .ai/harness/active-plan as authoritative only for this worktree; .ai/harness/active-worktree records the owner; .claude/.active-plan is a legacy fallback during transition
   - Keep multiple active plans in parallel worktrees when tasks diverge; fill workflow inventory before implementation: active plan, owning worktree, contract, review, notes, deferred ledger, checks, runs, scope owner, switching rule, and worktree path
   - Process annotation notes before implementing
-  - Project approved plans with .ai/harness/scripts/plan-to-todo.sh; the execution checklist stays in the plan ## Task Breakdown
+  - Project approved plans with .ai/harness/scripts/plan-to-todo.sh only after a concrete Promotion Gate; the execution checklist stays in the plan ## Task Breakdown, inline sprint rows stay inline, and only contract rows generate contract/review/notes artifacts
   - Define task contracts in tasks/contracts/{plan-stem}.contract.md
   - Fill tasks/reviews/{plan-stem}.review.md from Waza /check after verification
   - Record only non-obvious implementation decisions, deviations, tradeoffs, and open questions in tasks/notes/{plan-stem}.notes.md
@@ -39,14 +39,14 @@ RULES:
   - Distill repeated corrections into tasks/lessons.md instead of keeping them in tasks/todos.md
   - Capture deep findings and hidden contracts in docs/researches/
   - Keep sprint-level verification notes, behavior diffs, and residual risks in tasks/reviews/{plan-stem}.review.md
-  - Do not use implementation notes as durable memory or task logs; archive them on close and promote only after evidence shows the rule should outlive the sprint
+  - Do not use implementation notes as durable memory or task logs; before closeout, promote durable truth into docs/architecture/, docs/researches/, docs/spec.md, or tasks/lessons.md, then archive fulfilled plan/contract/review/notes/todo artifacts so root workflow surfaces represent active work only
   - Promote implementation-ready follow-up work into a new plans/plan-{timestamp}-{slug}.md file; keep deferred goals in tasks/todos.md only when intentionally postponed
   - Treat `.ai/hooks/` as the shared automation entrypoint when repo scripts reference hook-backed workflow checks
   - Treat user-level `~/.claude/settings.json` and `~/.codex/hooks.json` as host adapters; do not add repo-local project hook adapters unless explicitly migrating legacy config
   - For Codex sessions, treat `bash .ai/harness/scripts/check-task-sync.sh` and `bash .ai/harness/scripts/check-task-workflow.sh --strict` as required repo-local checks
   - Before ending a session, refresh `.ai/harness/handoff/current.md` when the task state changed
   - Update `tasks/workstreams/` only when durable capability progress changes
-  - Archive completed/abandoned plans and todos with metadata
+  - Archive completed/abandoned plans, contracts, reviews, notes, and todos with metadata
 {{#IF FACTOR_FACTORY_ENABLED}}
   - Treat `tasks/factors/registry.json` as the source of truth for factor lifecycle state
   - Create factor candidates with `bash .ai/harness/scripts/factor-lab-new.sh --name <slug>`

package/assets/reference-configs/agentic-development-flow.md

@@ -70,17 +70,18 @@ work, or shared contracts, report the P1/P2/P3 evidence explicitly.
 1. Route the request by intent before reading broadly.
 2. Read the repo-local contract first: `AGENTS.md` or `CLAUDE.md`, `tasks/todos.md`, `tasks/lessons.md`, and `.ai/harness/policy.json`.
 3. Use the selected skill or mode to produce either an approved plan, a root cause, or a review verdict.
-4. When Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete plan, capture it into `plans/` with `.ai/harness/scripts/capture-plan.sh --slug <slug> --title <title>` and the plan text on stdin.
+4. When Codex Plan mode, Waza `/think`, or `repo-harness-plan` produces a decision-complete work-package plan, capture it into `plans/` with `.ai/harness/scripts/capture-plan.sh --artifact-level work-package --slug <slug> --title <title>` and the plan text on stdin.
 5. Approved plans must include `## Evidence Contract` with state/progress path, verification evidence, evaluator rubric, stop condition, and rollback surface before execution. `capture-plan.sh` supplies this contract for captured planning output.
-6. Convert approved plans to execution scaffolding with `.ai/harness/scripts/plan-to-todo.sh --plan <plan>`; if approval is already explicit, use `.ai/harness/scripts/capture-plan.sh --status Approved --execute ...`. The plan's own `## Task Breakdown` remains the execution checklist; `tasks/todos.md` remains a deferred-goal ledger. Contract-level plans are projected into a linked `codex/<slug>` worktree when the policy enables it.
-7. For Sprint execution, treat each row in `plans/sprints/*.sprint.md` as a long-task waypoint. Use `$think` to expand the row into a decision-complete `plans/plan-*.md` before coding; do not treat the sprint row itself as an implementation plan.
-8. Use `.ai/harness/scripts/refresh-current-status.sh` for an explicit `tasks/current.md` preview or `--write` snapshot. In non-target worktrees, `git show <target>:tasks/current.md` reads the mainline snapshot, but it never replaces source artifacts.
-9. After substantive changes, run project checks and record evidence in `tasks/`. For contract worktrees, run Waza `/check`, start host-aware external acceptance in parallel, fill the review artifact from both verdicts, then use `repo-harness-ship` for default PR closeout. It calls `.ai/harness/scripts/contract-worktree.sh finish --no-merge`, pushes the `codex/<slug>` branch, and opens a draft PR. Use `repo-harness-ship --local-merge` only when an explicit maintainer workflow wants the older fast-forward merge and cleanup path.
+6. Convert approved work-package plans to execution scaffolding with `.ai/harness/scripts/plan-to-todo.sh --plan <plan>`; if approval is already explicit, use `.ai/harness/scripts/capture-plan.sh --artifact-level work-package --status Approved --execute --promotion-reason <reason> ...`. The plan's own `## Task Breakdown` remains the execution checklist; `tasks/todos.md` remains a deferred-goal ledger. Contract-level plans are projected into a linked `codex/<slug>` worktree when the policy enables it.
+7. Approved work-package plans must also include `> **Artifact Level**: work-package`, `> **Promotion Reason**:`, and `## Promotion Gate` with the merge/PR unit, rollback surface, independent verification boundary, review/acceptance boundary, high-risk surface, and why the work cannot remain a checklist row.
+8. For Sprint execution, treat each row in `plans/sprints/*.sprint.md` as a long-task waypoint. `contract` rows may expand with `$think` into a decision-complete `plans/plan-*.md`; `inline` rows stay in the sprint backlog or active plan `## Task Breakdown` and must not create contract/review/notes artifacts.
+9. Use `.ai/harness/scripts/refresh-current-status.sh` for an explicit `tasks/current.md` preview or `--write` snapshot. In non-target worktrees, `git show <target>:tasks/current.md` reads the mainline snapshot, but it never replaces source artifacts.
+10. After substantive changes, run project checks and record evidence in `tasks/`. For contract worktrees, run Waza `/check`, start host-aware external acceptance in parallel, fill the review artifact from both verdicts, then use `repo-harness-ship` for default PR closeout. It calls `.ai/harness/scripts/contract-worktree.sh finish --no-merge`, pushes the `codex/<slug>` branch, and opens a draft PR. Use `repo-harness-ship --local-merge` only when an explicit maintainer workflow wants the older fast-forward merge and cleanup path.
 
 ## Passive Plan Capture
 
 - Codex Plan mode and Waza `/think` do not need the user to remember `new-sprint` or `plan-to-todo`.
-- The agent should capture decision-complete planning output with `.ai/harness/scripts/capture-plan.sh`; the script sets `.ai/harness/active-plan`, writes `.ai/harness/active-worktree`, mirrors `.claude/.active-plan`, and writes a timestamped `plans/plan-*.md` artifact.
+- The agent should capture decision-complete work-package planning output with `.ai/harness/scripts/capture-plan.sh --artifact-level work-package`; the script sets `.ai/harness/active-plan`, writes `.ai/harness/active-worktree`, mirrors `.claude/.active-plan`, and writes a timestamped `plans/plan-*.md` artifact with a concrete Artifact Level and Promotion Gate. Use `--artifact-level checklist-row` when the captured output should only extend the active plan's `## Task Breakdown`.
 - Planning capture is allowed before implementation. Contract, review, notes, and worktree artifacts are generated only after explicit implementation approval; `tasks/todos.md` is not a duplicate of plan tasks.
 - Current-status capture is separate from planning capture: `tasks/current.md` is regenerated from artifacts for orientation, not edited as a plan or task list.
 

package/assets/reference-configs/document-generation.md

@@ -29,6 +29,7 @@ Create these only when the agent has concrete repo evidence or the user asks:
 - Do not create root `specs/`; use `docs/spec.md` for stable product intent, `interfaces/` for machine-consumed runtime boundaries, and tests for executable behavior.
 - Do not duplicate workflow rules already indexed in `docs/reference-configs/`.
 - Prefer short docs that name sources, owners, and verification commands.
+- Use `plans/plan-*.md` plus contract/review/notes only for `Artifact Level: work-package` boundaries. Sprint rows, red/green steps, and local run traces stay in the active plan, sprint backlog, or ignored `.ai/harness/*` runtime state.
 - Let capability `CLAUDE.md` and `AGENTS.md` carry local contract projections; root docs stay concise.
 - Keep complete workstream TODOs in `tasks/workstreams/<domain>/<capability>/`; contract blocks should link to them instead of becoming task logs.
 - Keep onboarding docs split by reader: agents read active source artifacts first; humans review the Human Review Card, diff, latest trace, and rollback first.

package/assets/reference-configs/harness-overview.md

@@ -11,8 +11,8 @@ or refreshes a repo. The harness gives agents three durable surfaces:
   `AGENTS.md`, and root `CLAUDE.md` explain stable product intent, coding
   rules, and local workflow boundaries.
 - **Task contracts**: `plans/`, `tasks/contracts/`, `tasks/reviews/`, and
-  `.ai/harness/checks/` turn a request into scoped implementation work with
-  evidence-backed completion.
+  the current `.ai/harness/checks/latest.json` pointer turn a request into
+  scoped implementation work with evidence-backed completion.
 - **Session journal**: `.ai/harness/handoff/`, `tasks/current.md`, and
   `.ai/harness/events.jsonl` let a new agent session resume from repo state
   without treating chat history as authority.
@@ -76,14 +76,16 @@ with the project.
 
 - Notes: `tasks/notes/<plan-stem>.notes.md` is task-local and auditable. It should not be treated as durable knowledge by default.
 - Current status: `tasks/current.md` is a tracked derived snapshot for orientation only. It must be regenerated from source artifacts and must not contain hand-written kanban/checklist state.
-- Evidence: `.ai/harness/checks/latest.json` is the current gate, while `.ai/harness/runs/*.json` keeps immutable verification snapshots for later audit.
+- Evidence: `.ai/harness/checks/latest.json` is the current gate, while `.ai/harness/runs/*.json` keeps ignored local verification snapshots for the current workflow audit. Task-specific `.ai/harness/checks/*.latest.{json,md}` reports are ignored runtime cache; promote durable conclusions into reviews, contracts, notes, or research.
+- Human reading surface: `docs/spec.md`, `docs/architecture/`, and durable `docs/researches/` conclusions are the default entrypoint. Root workflow artifacts should describe active work only; completed plan/contract/review/notes/todo artifacts move to `plans/archive/` or `tasks/archive/`, and `.rgignore` keeps those archives plus runtime evidence out of default `rg` results.
+- Closeout order: promote durable truth first, then archive the workflow artifacts. If a fact only lives in a review/contract/checks file, the workflow is not ready to disappear from the active reading surface.
 - Memory: `docs/researches/`, `tasks/lessons.md`, and gbrain are advisory. Current repo state and evidence override summaries.
 - External knowledge: `brain/<project>/*` stores long-form explanations, runbooks, decisions, and patterns. Hooks may write only explicitly opted-in `repo-to-brain` manifest entries; checks must not require gbrain or MCP.
 - Assets: policies, hooks, scripts, templates, and reference configs only change when a pattern has evidence across tasks or fixtures.
 
 ## Trace Evidence
 
-`scripts/verify-sprint.sh` writes `.ai/harness/checks/latest.json` and an immutable `.ai/harness/runs/*.json` snapshot using `schema: repo-harness-run-trace.v1`. The trace is local evidence for workflow grading, not a cloud tracing dependency.
+`scripts/verify-sprint.sh` writes `.ai/harness/checks/latest.json` and an ignored `.ai/harness/runs/*.json` snapshot using `schema: repo-harness-run-trace.v1`. The trace is local evidence for workflow grading, not a cloud tracing dependency or a committed durable artifact.
 
 Required v1 fields:
 

package/assets/reference-configs/sprint-contracts.md

@@ -16,12 +16,14 @@ The word "sprint" historically named a single execution slice in this harness. T
 - A PRD decomposes `docs/spec.md` intent into product direction, users, success criteria, acceptance scenarios, module behavior, data model, performance targets, and developer handoff. `repo-harness-prd` writes PRDs with compact/standard tiers and evidence rules for `[UNKNOWN]` / `[UNVERIFIED]` facts.
 - A Sprint decomposes a PRD or `docs/spec.md` into an ordered backlog; each backlog task executes as one task-contract slice through the existing plan -> contract -> worktree -> verify flow.
 - `tasks/todos.md` stays the deferred-goal ledger; it never carries the sprint backlog or any active checklist.
+- Backlog row mode is a granularity decision. `contract` rows are allowed to become a top-level plan plus task contract only when they are captured as `Artifact Level: work-package` and pass the plan Promotion Gate. `inline` and `checklist-row` work stays inside the sprint backlog or active plan `## Task Breakdown` and must not generate contract/review/notes artifacts.
 - Legacy filenames: `verify-sprint.sh` and `new-sprint.sh` predate the program layer and are kept for downstream compatibility. Read them as task-contract verification helpers. New generated artifact headings and plan metadata should use **Task Contract** and **Task Review**.
 - Sprint lifecycle: `Draft -> Approved -> Executing -> Done -> Archived`, tracked in the sprint file's `> **Status**:` line. Where the sprint layer is installed, `scripts/sprint-backlog.sh` is the compatibility command and delegates to the installed helper runtime under `.ai/harness/scripts/`; `.ai/harness/sprint/active-sprint` (runtime state, not committed) marks the single active sprint. Harness installs predating the sprint layer do not ship the helper, so check for the script before invoking it. `check-task-workflow.sh` rejects Approved/Executing sprints whose PRD/source section is placeholder-only or whose backlog rows lack a concrete acceptance line.
 
 ## Inventory First
 
-- Every execution-ready `plans/plan-*.md` should name the active plan, owning worktree, expected contract, review, notes file, deferred-goal ledger, `.ai/harness/checks/latest.json`, `.ai/harness/runs/`, scope authority, plan switching rule, and worktree isolation path.
+- Every execution-ready `plans/plan-*.md` should name the active plan, owning worktree, expected contract, review, notes file, deferred-goal ledger, `.ai/harness/checks/latest.json`, `.ai/harness/runs/`, scope authority, plan switching rule, and worktree isolation path. Checks latest files are runtime evidence pointers/cache, not commit surface.
+- Every execution-ready `plans/plan-*.md` should declare `> **Artifact Level**: work-package`, `> **Promotion Reason**:`, `> **Verification Boundary**:`, and `> **Rollback Surface**:`. It should also fill `## Promotion Gate` with the merge/PR unit, rollback surface, verification boundary, review/acceptance boundary, high-risk surface, and why this cannot remain a checklist row.
 - Every `tasks/contracts/*.contract.md` should repeat the source plan, deferred-goal ledger, review, notes, checks, run snapshots, scope gate, and completion gate.
 - If the inventory is incomplete, keep the plan in Draft or revise the contract before editing implementation files.
 
@@ -81,6 +83,7 @@ Existing contracts without this block remain valid. `.ai/harness/scripts/verify-
 - A contract is not truly done until the matching review file records a passing recommendation.
 - `tasks/reviews/<plan-stem>.review.md` should be filled from Waza `/check` after verification and cite the contract, implementation notes, checks file, run snapshot, `## External Acceptance Advice`, and any manual observations.
 - `tasks/notes/<plan-stem>.notes.md` captures task-local decisions and should be archived or promoted deliberately, not left as hidden long-term memory.
+- Closeout is promote-then-archive: durable truths move into `docs/architecture/`, `docs/researches/`, `docs/spec.md`, or `tasks/lessons.md` before `archive-workflow.sh` moves fulfilled plan/contract/review/notes/todo artifacts into `plans/archive/` and `tasks/archive/`.
 
 ## Worktree Lifecycle
 

package/assets/reference-configs/workflow-orchestration.md

@@ -12,3 +12,15 @@
 Concrete project execution still flows through plans, contracts, tasks,
 workstreams, checks, and handoff files. The general multi-phase orchestration
 pattern belongs in the external pattern page.
+
+## Promotion Gate
+
+Do not promote every sprint row or checklist step into a new `plans/plan-*.md`.
+Create a top-level plan only when the slice is a coherent merge/PR unit, has a
+separate rollback surface, needs independent verification, needs its own
+review/acceptance boundary, touches a high-risk surface, or cannot remain a
+checklist row in the active plan or sprint backlog.
+
+Inline sprint rows stay in the sprint backlog or the active plan's
+`## Task Breakdown`. Contract rows may expand through the full plan -> contract
+-> review -> notes flow.

package/assets/skill-commands/repo-harness-gptpro/SKILL.md

@@ -47,7 +47,8 @@ Use GPT Pro language with the user. Treat the `browser-*` command names as imple
 When asking GPT Pro to review repo updates, include an explicit acceptance requirement in the prompt:
 
 - Use the recorded ChatGPT MCP server name from `chatgpt.serverName` to read the current repo state before producing findings or a merge/readiness verdict.
-- Before a Pro MCP attempt, open ChatGPT Settings -> Connectors for the recorded server name, run Refresh or Scan Tools, verify the expected Action is listed, then start a fresh chat and select the Connector from `+` -> More.
+- Before a Pro MCP attempt, open ChatGPT Settings -> Connectors for the recorded server name, run Refresh or Scan Tools, verify the expected Action is listed, then start a fresh chat with Deep research enabled when the review requires Pro research, and select the Connector from `+` -> More.
+- For multi-repo or user-scope reads, first call `discover_harness_repos` with `query`, `name`, or `repo_path` for repo-like text such as `my-app/`; use the returned exact target for follow-up workflow reads. Do not rely on a literal relative path guess.
 - Read at least the changed-file list or status, the relevant diffs or changed files, and any requested session/handoff artifacts through that recorded MCP server; pasted summaries are context, not sufficient evidence.
 - Include a short `MCP Read Evidence` section in the final answer naming the recorded MCP server, the reads performed, and the files, diffs, or artifacts inspected.
 - If the recorded MCP server name is missing, or `mcp doctor --json` reports `chatgpt.serverNameConfigured:false`, route to `repo-harness:gptpro_setup` so initialization can record it before review.

package/assets/skill-commands/repo-harness-sprint/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: repo-harness-sprint
-description: Program-level sprint planning and execution entrypoint. Uses upper-layer PRDs from plans/prds/ when present, writes ordered sprint backlogs in plans/sprints/, then expands each row with $think before the existing plan, contract, and worktree flow.
+description: Program-level sprint planning and execution entrypoint. Uses upper-layer PRDs from plans/prds/ when present, writes ordered sprint backlogs in plans/sprints/, expands contract rows with $think into plan/contract/worktree flow, and keeps inline rows inside the sprint backlog or active plan checklist.
 when_to_use: "repo-harness-sprint, plan a sprint, create sprint backlog, from-prd, PRD to sprint, sprint from PRD, run next sprint task, sprint status"
 ---
 
@@ -19,15 +19,16 @@ Use this command to plan a program-level Sprint from an upper-layer PRD or sourc
    - Read the PRD `Problem`, `Users`, `Success Criteria`, `Acceptance Scenarios`, and `Non-goals`; summarize them into the Sprint `## PRD` section and set `> **Source PRD**:` to the PRD path.
    - Derive backlog rows from `Module Behaviors (P0)` and acceptance scenario groups. Preserve dependency order and make every acceptance line traceable to a PRD acceptance scenario.
    - Keep discussion focused on ordering, slice granularity, and mode selection; do not re-decide the product intent unless the PRD has blocking contradictions.
-   - Use one row for one plan -> contract -> worktree cycle. Split larger work at stable integration boundaries.
+   - Use `contract` rows for one plan -> contract -> worktree cycle. Split larger work at stable integration boundaries.
    - Acceptance lines must be machine-checkable, such as a test command, file existence assertion, grep pattern, or numeric assertion. Avoid subjective wording such as "works well".
    - Default mode is `contract`; use `inline` only for small isolated documentation, configuration, or single-file changes.
 4. Route `run` (incremental, one backlog task per invocation):
    - Run `bash .ai/harness/scripts/sprint-backlog.sh next` to resolve the next pending row; when it exits 3, report the backlog as complete and recommend setting the sprint Status to Done after review.
-   - Treat the row as a long-task waypoint, not a detailed implementation plan. Invoke `$think` with the sprint path, row task, mode, and acceptance line so the coding agent expands it into a decision-complete plan.
-   - Capture the approved `$think` output with `bash .ai/harness/scripts/capture-plan.sh --source waza-think --source-ref sprint:<sprint-file>#<task> --status Approved --execute` so the plan projects through the contract worktree flow.
-   - `bash .ai/harness/scripts/sprint-backlog.sh start-task` remains a compatibility helper for reserving a row and generating a thin plan seed; its generated plan must still run `$think` before code edits.
-   - Execute the slice as usual (implement, `/check`, external acceptance, `bash .ai/harness/scripts/contract-worktree.sh finish`); finish back-fills the backlog row warn-only.
+   - Treat the row as a long-task waypoint, not a detailed implementation plan.
+   - For `contract` rows, invoke `$think` with the sprint path, row task, mode, acceptance line, and Promotion Gate fields so the coding agent expands it into a decision-complete plan. Capture the approved `$think` output with `bash .ai/harness/scripts/capture-plan.sh --artifact-level work-package --promotion-reason worktree_boundary --source waza-think --source-ref sprint:<sprint-file>#<task> --status Approved --execute`.
+   - For `inline` rows, do not create a new `plans/plan-*.md` or task contract. Keep the work in the sprint backlog or the current active plan's `## Task Breakdown`, then complete the row when the acceptance line is verified.
+   - `bash .ai/harness/scripts/sprint-backlog.sh start-task` remains a compatibility helper for reserving a row. It captures a thin plan seed only for `contract` rows; inline rows append checklist-row content to the current active plan before recording an in-flight marker.
+   - Execute contract slices as usual (implement, `/check`, external acceptance, `bash .ai/harness/scripts/contract-worktree.sh finish`); finish back-fills the backlog row warn-only.
 5. Route `status`: report `bash .ai/harness/scripts/sprint-backlog.sh status` plus the Active Sprint section of `tasks/current.md`; mutate nothing.
 6. After each completed task, re-read the sprint file before starting the next one; user edits to the backlog override stale session memory.
 
@@ -40,7 +41,7 @@ Use this command to plan a program-level Sprint from an upper-layer PRD or sourc
 
 ## Boundaries
 
-- Does not implement backlog tasks itself; execution always flows through the existing plan -> contract -> worktree -> verify gates.
+- Does not implement backlog tasks itself; contract rows flow through the existing plan -> contract -> worktree -> verify gates, while inline rows stay in sprint/active-plan checklist scope.
 - Does not set `> **Status**: Approved` without explicit user approval of the PRD and backlog.
 - Never bypasses `/check`, external acceptance, or `verify-sprint.sh` to mark a backlog row complete.
 - Goal mode (`run --goal`, autonomous continuation) is not part of this command yet; treat requests for it as future work and say so.

package/assets/skill-version.json

@@ -1,6 +1,6 @@
 {
-  "version": "0.8.1",
-  "templateVersion": "0.8.1",
+  "version": "0.8.2",
+  "templateVersion": "0.8.2",
   "skillName": "repo-harness",
   "contractId": "tasks-first-harness-v1",
   "compatibility": {
@@ -171,6 +171,10 @@
     {
       "version": "0.8.1",
       "description": "Adds General Repo MCP CodeGraph access, removes the ChatGPT extension bridge provider, and suppresses Codex Stop decision stdout"
+    },
+    {
+      "version": "0.8.2",
+      "description": "Hardens two-tier plan artifact gates, rejects transient and inline projection misuse, keeps CodeGraph tooling on latest, and reduces completed workflow artifact noise"
     }
   ],
   "generatedProjectStamp": {

package/assets/templates/helpers/archive-workflow.sh

@@ -256,6 +256,42 @@ if [[ -f "$notes_file" ]]; then
   rm -f "$notes_file"
 fi
 
+contract_file="tasks/contracts/${artifact_stem}.contract.md"
+if [[ ! -f "$contract_file" && -f "tasks/contracts/${slug}.contract.md" ]]; then
+  contract_file="tasks/contracts/${slug}.contract.md"
+fi
+if [[ -f "$contract_file" ]]; then
+  archive_contract="$(unique_archive_path "tasks/archive/contract-${timestamp}-${slug}.md")"
+  {
+    echo "> **Archived**: ${timestamp_human}"
+    echo "> **Related Plan**: ${archive_plan_path}"
+    echo "> **Outcome**: ${outcome}"
+    echo "> **Lifecycle**: contract"
+    echo "> **Parent Run ID**: ${parent_run_id}"
+    echo
+    cat "$contract_file"
+  } > "$archive_contract"
+  rm -f "$contract_file"
+fi
+
+review_file="tasks/reviews/${artifact_stem}.review.md"
+if [[ ! -f "$review_file" && -f "tasks/reviews/${slug}.review.md" ]]; then
+  review_file="tasks/reviews/${slug}.review.md"
+fi
+if [[ -f "$review_file" ]]; then
+  archive_review="$(unique_archive_path "tasks/archive/review-${timestamp}-${slug}.md")"
+  {
+    echo "> **Archived**: ${timestamp_human}"
+    echo "> **Related Plan**: ${archive_plan_path}"
+    echo "> **Outcome**: ${outcome}"
+    echo "> **Lifecycle**: review"
+    echo "> **Parent Run ID**: ${parent_run_id}"
+    echo
+    cat "$review_file"
+  } > "$archive_review"
+  rm -f "$review_file"
+fi
+
 if todo_is_deferred_ledger tasks/todos.md; then
   touch_deferred_ledger_update_marker tasks/todos.md
 else