project-tiny-context-harness 0.2.78 → 0.2.80

package/README.md

@@ -84,7 +84,7 @@ For long-running tasks, externalize the target first. Use explicit Skill invocat
 ```text
 Web GPT or another external planning model produces the long-task source inputs
 -> /normal-long-task produces the full checklist and optional generic target-mode prompt
--> /superpowers-long-task consumes Product / Architecture Source + Technical Realization Plan + Acceptance Checklist when Superpowers execution is needed
+-> /composite-long-task-workflow consumes Product / Architecture Source + Technical Realization Plan + Acceptance Checklist when Superpowers-backed execution is needed
 -> Superpowers derives concrete implementation slices
 -> execution maintains task-state.json, append-only events.ndjson and generated derived views
 -> each slice follows the workflow contract + project_context/**
@@ -94,15 +94,19 @@ For ordinary target-mode preparation, a two-document upstream input remains enou
 
 The ordinary long-task path uses `/normal-long-task`. It is the non-Superpowers acceptance pass: it can generate or reuse the full acceptance checklist and can produce a generic target-mode prompt.
 
-The Superpowers long-task path uses `/superpowers-long-task` when three inputs already exist: `Product / Architecture Source`, `Technical Realization Plan` and `Acceptance Checklist`. The product/architecture source preserves original intent and scope; the technical realization plan is the execution blueprint and plan-conformance source; the checklist is the acceptance authority. The Skill does not perform complexity routing: invocation means Superpowers long-task execution was already selected. Two-document compatibility is allowed only when the first document clearly contains both product/architecture source and technical realization plan sections. If only a product/architecture source and checklist exist, the Skill stops with a Missing Fields Report for a missing `Technical Realization Plan` instead of generating one. The technical realization plan must already satisfy the required Superpowers-ready Markdown implementation plan fields; if it does, the prompt binds it directly to Superpowers execution rather than regenerating the plan, and if it does not, the Skill stops before generating a prompt. The prompt is Tiny Context's adapter layer, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema. It may wrap Superpowers with Tiny Context authority, conformance and acceptance gates, but it must not redefine or fork Superpowers execution mechanics. It requires parent-level `Product Context Delta` and `Technical Context Delta` checks before implementation and uses a canonical state kernel under `tmp/ty-context/plan-acceptance/<plan-slug>/`: `task-state.json` is the only execution state source, `events.ndjson` is append-only and `derived/**` contains generated local audit, plan-conformance matrix, final acceptance verdict, progress ledger, evidence index, context alignment and final summary views. Complete acceptance rows are externally reviewable evidence claims derived from `task-state.evidence[]`: the checklist supplies the proof chain, fresh reviewable evidence must satisfy every required layer, and material drift, missing layers or unapproved sibling substitution prevent `complete`. Goal-mode wording separates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`: implementation / execution goals complete only when `ty-context superpowers final-gate` computes `product_goal_complete=true`; read-only audit goals may end at `audit_task_complete`, but a non-accepted verdict says `Audit workflow completed; acceptance target not complete.` and does not use unqualified `Goal achieved` or `update_goal(status="complete")` as acceptance of the user target.
+The Composite Long-Task Workflow path uses `/composite-long-task-workflow` when three inputs already exist: `Product / Architecture Source`, `Technical Realization Plan` and `Acceptance Checklist`. The product/architecture source preserves original intent and scope; the technical realization plan is the execution blueprint and plan-conformance source; the checklist is the acceptance authority. The Skill does not perform complexity routing: invocation means Superpowers-backed composite execution was already selected. Two-document compatibility is allowed only when the first document clearly contains both product/architecture source and technical realization plan sections. If only a product/architecture source and checklist exist, the Skill stops with a Missing Fields Report for a missing `Technical Realization Plan` instead of generating one. The technical realization plan must already satisfy the required Superpowers-ready Markdown implementation plan fields. When it does, the Skill freezes the package-managed workflow into `workflow-protocol.md`, writes task-local `execution-binding.md`, and renders `goal-objective.txt` as a thin Codex Goal objective instead of packing the full workflow into goal text. This is intentional: the Goal objective stays small enough to preserve the persistent completion contract, while the complete executable workflow lives in the protocol snapshot and the task-specific binding. The expected runtime effect is explicit fusion rather than agent improvisation: Tiny Context Workflow Contract first, then three-input authority, state compilation, Superpowers implementation slices, canonical evidence/state updates, generated views, slice/epoch gates and final-gate completion. The workflow is Tiny Context's composite adapter layer, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema; it is not the Tiny Context Workflow Contract itself, not a business fact source, not a generic prompt generator and not a Superpowers fork. It may wrap Superpowers with Tiny Context authority, conformance and acceptance gates, but it must not redefine or fork Superpowers execution mechanics. It requires parent-level `Product Context Delta` and `Technical Context Delta` checks before implementation and uses a canonical state kernel under `tmp/ty-context/plan-acceptance/<plan-slug>/`: `task-state.json` is the only execution state source, `events.ndjson` is append-only and `derived/**` contains generated local audit, plan-conformance matrix, final acceptance verdict, progress ledger, evidence index, context alignment and final summary views. Complete acceptance rows are externally reviewable evidence claims derived from `task-state.evidence[]`: the checklist supplies the proof chain, fresh reviewable evidence must satisfy every required layer, and material drift, missing layers or unapproved sibling substitution prevent `complete`. Goal-mode wording separates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`: implementation / execution goals complete only when `ty-context composite-long-task final-gate` computes `product_goal_complete=true`; read-only audit goals may end at `audit_task_complete`, but a non-accepted verdict says `Audit workflow completed; acceptance target not complete.` and does not use unqualified `Goal achieved` or `update_goal(status="complete")` as acceptance of the user target.
 
 The three inputs also carry capability-first delivery boundaries. Product / Architecture Source declares `delivery_scope`, `full_population_required`, samples that validate the claim, samples that do not validate it and out-of-scope backlog. Each Technical Realization Plan item declares delivery scope, capability target, representative samples, full-population boundary and non-required population. Each Acceptance Checklist item declares acceptance scope, what it validates and does not validate, sample boundary and full-population requirement. `scope_conflict_requires_decision` blocks completion when source, plan and checklist disagree between system capability build, representative sample validation and full-population operation. Sample evidence or framework-only implementation cannot prove all-provider, all-interface, all-platform or full-population completion unless the AC explicitly allows it; when full population is not explicitly required, generated views report it as `not_in_scope`.
 
-For non-trivial Superpowers slices, the generated prompt requires a structured `slice-delta.json`. The executor applies it with `ty-context superpowers apply-slice-delta <workdir> <slice-delta.json>`, then runs `ty-context superpowers derive` and `ty-context superpowers slice-gate`. Each delta records touched plan items/ACs, code changes, closed and remaining proof layers, blockers, cleanup assertions, `progress_value` and canonical evidence records with `proves`, `does_not_prove`, freshness, redaction and reviewability. Default slice guidance is to group 2-4 strongly related missing layers that share an AC, runtime scenario, proof environment or verification path, while single-gap slices are reserved for blockers, contradictions or small metadata cleanup. The prompt also asks executors to classify missing layers, reuse DB/API/Browser environments only with unique proof prefixes and cleanup assertions, and run a stale/overclaim scan after deriving artifacts.
+`ty-context composite-long-task compile` uses a strict heading-based grammar for that packet. Product / Architecture Source is one document-level object with fixed fields. Technical Realization Plan items are definitions only when written as Markdown headings such as `## PI-001: ...`; Acceptance Checklist items are definitions only when written as headings such as `## AC-001: ...`. Fields inside those sections must use fixed `key: value`, indented-list or `key: |` syntax. Plain prose, tables, mapping previews and ordinary lists that mention `PI-001` or `AC-001` are references, not definitions; old list-style definitions such as `- PI-001: ...` followed by delivery fields now fail at compile time with file and line guidance.
+
+For non-trivial Superpowers-backed slices, the workflow protocol requires a structured `slice-delta.json`. The executor applies it with `ty-context composite-long-task apply-slice-delta <workdir> <slice-delta.json>`, then runs `ty-context composite-long-task derive` and `ty-context composite-long-task slice-gate`. Each delta records touched plan items/ACs, code changes, closed and remaining proof layers, blockers, cleanup assertions, `progress_value` and canonical evidence records with `proves`, `does_not_prove`, freshness, redaction and reviewability. Default slice guidance is to group 2-4 strongly related missing layers that share an AC, runtime scenario, proof environment or verification path, while single-gap slices are reserved for blockers, contradictions or small metadata cleanup. The protocol also asks executors to classify missing layers, reuse DB/API/Browser environments only with unique proof prefixes and cleanup assertions, and run a stale/overclaim scan after deriving artifacts.
 
 The generated Superpowers prompt uses Slice Gate / Epoch Gate / Final Gate cadence instead of running a full final gate after every slice. Progress Accounting tracks AC acceptance completion, engineering implementation progress, runtime/proof progress, system capability progress, representative sample progress, real object coverage, full population operation progress, artifact budget, proof-layer milestone status and workflow overhead in state and generated `derived/progress-ledger.*`. Workflow overhead backpressure asks executors to batch shared provider/browser/runtime/security epoch proof environments, prune stale artifacts and choose the Next 3-5 high-value clusters that close the most blocking AC/proof-layer gaps.
 
-The recommended Superpowers layer is the specific [obra/Superpowers](https://github.com/obra/superpowers) plugin/workflow, not a generic planning substitute. After `/superpowers-long-task` accepts the input packet, prefer `superpowers:subagent-driven-development` when subagents are available and `superpowers:executing-plans` otherwise. Behavior changes should use `superpowers:test-driven-development`. Final gate order is derive all views, `superpowers:verification-before-completion`, `ty-context validate-superpowers-state <dir>`, `ty-context validate-plan-acceptance <dir>`, read-only auditor when available, rederive/revalidate if auditor fixes changed state or evidence, final stale/overclaim scan, then `ty-context superpowers final-gate <dir>` computes completion. The auditor reconstructs AC proof chains with a fixed auditor checklist and finds gaps, but does not become proof. Superpowers review and verification remain useful execution checks, but they cannot override Tiny Context gates: passing Superpowers review does not by itself prove plan conformance or checklist acceptance.
+The recommended Superpowers layer is the specific [obra/Superpowers](https://github.com/obra/superpowers) plugin/workflow, not a generic planning substitute. After `/composite-long-task-workflow` accepts the input packet, prefer `superpowers:subagent-driven-development` when subagents are available and `superpowers:executing-plans` otherwise. Behavior changes should use `superpowers:test-driven-development`. Final gate order is derive all views, `superpowers:verification-before-completion`, `ty-context validate-superpowers-state <dir>`, `ty-context validate-plan-acceptance <dir>`, read-only auditor when available, rederive/revalidate if auditor fixes changed state or evidence, final stale/overclaim scan, then `ty-context composite-long-task final-gate <dir>` computes completion. The auditor reconstructs AC proof chains with a fixed auditor checklist and finds gaps, but does not become proof. Superpowers review and verification remain useful execution checks, but they cannot override Tiny Context gates: passing Superpowers review does not by itself prove plan conformance or checklist acceptance.
+
+Hallucination guard: do not register `workflow-protocol.md` in `project_context/context.toml`, treat it as business Context, let `derived/**` rewrite Product / Plan / Checklist, use local audit or Superpowers review as quality proof, use sample evidence as full-population proof, claim full alignment while Source-to-Context Coverage or Context-to-Implementation Binding has unresolved required gaps, handwrite `product_goal_complete`, or complete an implementation Goal before final-gate passes.
 
 The reason is drift control. The workflow contract plus Context layer is intentionally a soft constraint. It works well for short tasks, and Context can still capture the expected facts for long tasks, but long execution makes the Context-to-code step drift as the context window grows, work is handed off, subagents split scope or validation loops multiply. The extra Tiny Context gates exist because Superpowers alone can still drift under long-running execution pressure: it strengthens execution discipline, but it does not by itself preserve source authority, prevent scope shrinkage, prove full conformance to the Technical Realization Plan or enforce AC-by-AC evidence against the Acceptance Checklist. A product/architecture source, technical realization plan, acceptance checklist, explicit long-task Skill invocation, target-mode prompt, canonical task state, generated derived views and optional Superpowers execution layer make implementation conformance and completion evidence recoverable without restoring a phase-gated workflow.
 
@@ -159,7 +163,7 @@ npm ci
 npm run smoke:quickstart
 npm run preview:pack
 cd /path/to/your/test-repo
-npm install -D /path/to/project-tiny-context-harness/tmp/ty-context/source-preview/package/project-tiny-context-harness-0.2.78.tgz
+npm install -D /path/to/project-tiny-context-harness/tmp/ty-context/source-preview/package/project-tiny-context-harness-0.2.80.tgz
 npx --no-install ty-context init --adopt
 make validate-context
 ```
@@ -228,7 +232,7 @@ For existing projects:
 npx --yes --package project-tiny-context-harness@latest ty-context init --adopt
 ```
 
-`init` creates `project_context/context.toml`, `project_context/global.md`, `project_context/architecture.md`, `project_context/areas/main.md`, `project_context/areas/main/verification.md`, agent guidance, Context authoring Skills, a Product Surface Contract Skill, a full-project export Skill, a Harness upgrade Skill, the `/normal-long-task` and `/superpowers-long-task` Skills, managed templates/tools, a Makefile include and `.github/workflows/harness.yml`. The generated workflow runs only the selected Harness gate: `validate-context`, `validate-code-modularity` or the composite `validate-harness`; `validate-plan-contract` and `validate-plan-acceptance` are explicit commands for complex plan surfaces and long-task artifacts, not default workflow gates. Maintainer-only package tests and source-drift checks are intentionally kept out of consumer projects. It does not create business Product Surface Contract files, stage work-product trees, lifecycle state or stage skills by default.
+`init` creates `project_context/context.toml`, `project_context/global.md`, `project_context/architecture.md`, `project_context/areas/main.md`, `project_context/areas/main/verification.md`, agent guidance, Context authoring Skills, a Product Surface Contract Skill, a full-project export Skill, a Harness upgrade Skill, the `/normal-long-task` and `/composite-long-task-workflow` Skills, managed templates/tools, a Makefile include and `.github/workflows/harness.yml`. The generated workflow runs only the selected Harness gate: `validate-context`, `validate-code-modularity` or the composite `validate-harness`; `validate-plan-contract` and `validate-plan-acceptance` are explicit commands for complex plan surfaces and long-task artifacts, not default workflow gates. Maintainer-only package tests and source-drift checks are intentionally kept out of consumer projects. It does not create business Product Surface Contract files, stage work-product trees, lifecycle state or stage skills by default.
 
 ## FAQ
 
@@ -274,7 +278,7 @@ Use `npx --no-install ty-context ...` only when you explicitly want the already
 | Full project context export Skill | `<harnessRoot>/skills/context_full_project_export/SKILL.md` | Handles explicit full-project, project-overall, Source Pack or code-level export requests and uses `export-context --source-pack`, `--code-index`, `--task-context`, `--all`, `--full` or `--code` to create temporary artifacts under `tmp/ty-context/context-exports/**`. |
 | Harness upgrade Skill | `<harnessRoot>/skills/context_harness_upgrade/SKILL.md` | Handles explicit Tiny Context / Project Tiny Context Harness upgrade requests such as “upgrade Tiny Context” and “use the Tiny Context upgrade skill to upgrade this project”; it runs the canonical `upgrade` path, handles only migration-scoped `manual_required` / `blocked` follow-up, then runs diagnostics. |
 | Ordinary long-task Skill | `<harnessRoot>/skills/normal-long-task/SKILL.md` | Invoke as `/normal-long-task` to turn a referenced plan, RFC, implementation proposal or two-document upstream input into a falsifiable acceptance checklist and optional generic paste-ready goal/target-mode prompt under `tmp/ty-context/plan-acceptance/**`; if the plan already contains an explicit concrete checklist, the Skill reuses it verbatim in the separate full-checklist file; compact summaries are only navigation/priority, but the Skill does not execute the plan or prove completion. |
-| Superpowers long-task Skill | `<harnessRoot>/skills/superpowers-long-task/SKILL.md` | Invoke as `/superpowers-long-task` when Product / Architecture Source, Technical Realization Plan and Acceptance Checklist exist and Superpowers execution is needed. It emits a Superpowers-specific prompt with Context Delta checks, official workflow skill names, capability-first delivery scope fields, plan-conformance matrix, final acceptance verdict and externally reviewable evidence discipline, and stops when required input fields are missing. It does not generate the technical plan, checklist or execute the plan. |
+| Composite long-task workflow Skill | `<harnessRoot>/skills/composite-long-task-workflow/SKILL.md` | Invoke as `/composite-long-task-workflow` when Product / Architecture Source, Technical Realization Plan and Acceptance Checklist exist and Superpowers-backed execution is needed. It freezes `workflow-protocol.md`, writes `execution-binding.md`, renders `goal-objective.txt`, binds official workflow skill names, capability-first delivery scope fields, plan-conformance matrix, final acceptance verdict and externally reviewable evidence discipline, and stops when required input fields are missing. It does not generate the technical plan, checklist or execute the plan. |
 | Project-local Skills | `<harnessRoot>/skills/<role>/SKILL.md` | Optional local product/design/development Skills created by the project, such as `product_plan`, `uiux_design` or `development_engineer`. They supersede package-managed default Skills when more specific, are not overwritten by `sync`, and should keep front matter trigger keywords aligned with the project `AGENTS.md` role-trigger rule. |
 | Managed file sync | `make ty-context-sync` or `npx --yes --package project-tiny-context-harness@latest ty-context sync` | Refreshes package-managed guidance, default Skills, Makefile include, context templates, tools and workflow YAML. It does not run migrations or perform semantic Context generation; it may block only direct asset-refresh safety issues such as invalid managed blocks or deprecated managed Skill overrides. |
 | Upgrade | `make ty-context-upgrade` or `npx --yes --package project-tiny-context-harness@latest ty-context upgrade` | Use for releases marked `upgrade-required` or `manual-required`. Builds an upgrade plan, stops before writes when `blocked` items exist, otherwise applies `safe_pending` migrations, runs `sync` and `doctor`, and exits non-zero when manual follow-up or diagnostics remain. |
@@ -290,9 +294,9 @@ Use `npx --no-install ty-context ...` only when you explicitly want the already
 | Harness validation | `make validate-harness` | Composite gate for `validate-context` and `validate-code-modularity`. |
 | Context validation | `npx --yes --package project-tiny-context-harness@latest ty-context validate-context`, `make validate-context` | Checks required project recovery fields, Context graph metadata, declared paths/roles and fake test-execution claims. |
 | Plan contract validation | `npx --yes --package project-tiny-context-harness@latest ty-context validate-plan-contract <plan.md\|dir>` | Checks Source-to-Context Coverage and Context-to-Implementation Binding for structural consistency, referenced path existence and weak-proof complete/bound contradictions. |
-| Superpowers state validation | `npx --yes --package project-tiny-context-harness@latest ty-context validate-superpowers-state <dir>` | Checks canonical Superpowers `task-state.json`, source hashes, graph references, delivery scope fields/conflicts, evidence/proof-layer consistency, stale evidence, sibling substitution, auditor blockers, derived drift and final completion rules. |
+| Superpowers state validation | `npx --yes --package project-tiny-context-harness@latest ty-context validate-superpowers-state <dir>` | Checks canonical Superpowers-backed `task-state.json`, source hashes, graph references, delivery scope fields/conflicts, evidence/proof-layer consistency, stale evidence, sibling substitution, auditor blockers, derived drift and final completion rules. |
 | Plan acceptance validation | `npx --yes --package project-tiny-context-harness@latest ty-context validate-plan-acceptance <dir>` | Checks legacy matrix/verdict artifacts when no state exists; when `task-state.json` exists, validates state-backed derived artifacts. It rejects contradictory complete claims, dangling evidence references, weak-proof complete rows, missing proof layers, material/critical drift, unapproved sibling substitution, blocking auditor findings, raw secrets/tokens/cookies, generated active-count drift, missing plan/AC cross-references and declared surface/architecture binding gaps. `errors` block; `warnings` / `hygiene` report cleanup. |
-| Superpowers state helpers | `npx --yes --package project-tiny-context-harness@latest ty-context superpowers <subcommand>` | Explicit `/superpowers-long-task` state helper for `init`, `compile`, `apply-slice-delta`, `derive`, `slice-gate`, `epoch-gate`, `final-gate` and `next-slices` under `tmp/ty-context/plan-acceptance/**`. |
+| Composite long-task state helpers | `npx --yes --package project-tiny-context-harness@latest ty-context composite-long-task <subcommand>` | Explicit `/composite-long-task-workflow` state helper for `init`, `compile`, `apply-slice-delta`, `derive`, `slice-gate`, `epoch-gate`, `final-gate`, `next-slices` and `render-goal` under `tmp/ty-context/plan-acceptance/**`. |
 | Diagnostics | `make ty-context-doctor` or `npx --yes --package project-tiny-context-harness@latest ty-context doctor` | Reports Harness root, package version, schema version and required Minimal Context paths. |
 | Package source checks | `ty-context package sync-source`, `ty-context package check-source` | Maintainer-only commands for keeping package canonical assets aligned with the source workspace. |
 
@@ -302,7 +306,7 @@ Technical architecture support is a Minimal Context capability: use restrained `
 
 For long-running plans, RFCs or implementation proposals, invoke `/normal-long-task` to turn a plan plus relevant Context into a falsifiable acceptance checklist and an optional generic paste-ready goal/target-mode prompt. It also supports a two-document upstream input from Web GPT or another external planner: `Development Plan` for execution direction and `Acceptance and Tests` for target-mode acceptance input. If the plan already contains an explicit concrete acceptance checklist, the Skill copies that checklist verbatim into a separate full-checklist file instead of generating a competing checklist. The two-document packet path is strict mode: when required fields cannot be fully parsed from both documents, the Skill preserves the inputs, reports the missing fields, and stops without generating a checklist or goal/target-mode prompt. It is one pre-execution acceptance pass, not a task planner or workflow engine: it stores temporary inputs under `tmp/ty-context/plan-acceptance/**`, asks for confirmation when durable assumptions are unclear, and leaves execution evidence to the future executor, tests, CI, review or human acceptance. The generated prompt may require a local audit under the same temporary directory so future sessions can recover acceptance progress; that audit is not Context, not a quality proof and not a replacement for the project's Tiny Context workflow contract. When the prompt references a full checklist, that checklist is the acceptance authority; compact prompt text is only navigation, priority and recovery guidance.
 
-When the next step explicitly needs Superpowers, invoke `/superpowers-long-task` on the Product / Architecture Source, Technical Realization Plan and Acceptance Checklist. It emits the `Superpowers input packet` and execution binding so the future executor sees which inputs feed Context Delta assessment, `superpowers:subagent-driven-development`, `superpowers:executing-plans`, TDD, `superpowers:verification-before-completion`, canonical `task-state.json`, append-only `events.ndjson`, generated `derived/**` views, proof-chain evidence and optional auditor review. This is Tiny Context's adapter layer for Superpowers workflows, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema. It may wrap Superpowers with authority, conformance and acceptance gates, but it must not redefine, duplicate or fork Superpowers execution mechanics; if a future Tiny Context-added step would conflict with, duplicate or override a Superpowers responsibility, stop and surface the boundary conflict instead of silently merging workflows. It cannot replace `/normal-long-task` for ordinary checklist preparation, does not route complexity, and does not derive a technical plan from a product plan; the Technical Realization Plan must already be a Superpowers-ready Markdown implementation plan or the Skill stops before generating a prompt. A two-document packet is accepted only when the first document explicitly contains both product/architecture source and technical realization plan sections. Product / Architecture Source, Technical Realization Plan and Acceptance Checklist remain the upstream authorities, while state/derived views/validator/auditor artifacts cannot rewrite them. Capability-first delivery scope stays inside those same three inputs: source, plan items and ACs must explicitly distinguish reusable system capability build, representative sample validation, full population operation and out-of-scope backlog; `scope_conflict_requires_decision` blocks completion, and sample/framework evidence cannot prove full population unless the AC says so. The generated prompt also disambiguates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`; implementation / execution goals finish only when `product_goal_complete=true`, while a read-only audit goal can end at `audit_task_complete` only with a non-accepted verdict reported as `Audit workflow completed; acceptance target not complete.`, not as `Goal achieved`.
+When the next step explicitly needs Superpowers-backed long-task execution, invoke `/composite-long-task-workflow` on the Product / Architecture Source, Technical Realization Plan and Acceptance Checklist. It emits `workflow-protocol.md`, `execution-binding.md` and `goal-objective.txt` so the future executor sees which inputs feed Context Delta assessment, `superpowers:subagent-driven-development`, `superpowers:executing-plans`, TDD, `superpowers:verification-before-completion`, canonical `task-state.json`, append-only `events.ndjson`, generated `derived/**` views, proof-chain evidence and optional auditor review. This is Tiny Context's composite adapter layer for Superpowers-backed workflows, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema. It may wrap Superpowers with authority, conformance and acceptance gates, but it must not redefine, duplicate or fork Superpowers execution mechanics; if a future Tiny Context-added step would conflict with, duplicate or override a Superpowers responsibility, stop and surface the boundary conflict instead of silently merging workflows. It cannot replace `/normal-long-task` for ordinary checklist preparation, does not route complexity, and does not derive a technical plan from a product plan; the Technical Realization Plan must already be a Superpowers-ready Markdown implementation plan or the Skill stops before rendering entry artifacts. A two-document packet is accepted only when the first document explicitly contains both product/architecture source and technical realization plan sections. Product / Architecture Source, Technical Realization Plan and Acceptance Checklist remain the upstream authorities, while state/derived views/validator/auditor artifacts cannot rewrite them. Capability-first delivery scope stays inside those same three inputs: source, plan items and ACs must explicitly distinguish reusable system capability build, representative sample validation, full population operation and out-of-scope backlog; `scope_conflict_requires_decision` blocks completion, and sample/framework evidence cannot prove full population unless the AC says so. The generated Goal objective also disambiguates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`; implementation / execution goals finish only when `product_goal_complete=true`, while a read-only audit goal can end at `audit_task_complete` only with a non-accepted verdict reported as `Audit workflow completed; acceptance target not complete.`, not as `Goal achieved`.
 
 For Product Surface work, `context_surface_contract` turns broad product/page/UI principles into project-owned surface responsibilities. A Product Surface can be a Web page, mobile screen, desktop window, game UI/HUD/menu, CLI/TUI output, extension UI or embedded/device interface. Cross-surface contracts use the existing `contract` role; area-owned screen facts stay in `area` or `subdomain`; repeatable validation paths use `verification`. The Harness does not add a new surface-specific role or create business surface contracts during `init` or `upgrade`. Product Surface Context authoring is not a default product-quality validator; plan validators only check declared temporary surface bindings for structural consistency. Projects that want mandatory task blocks should add a separate project-local Skill, while `product-surface-contract.md` is only a compact managed template for optional Context authoring.
 
@@ -514,7 +518,7 @@ $EDITOR <harnessRoot>/skills/uiux_design/SKILL.md
 
 When a project-local Skill and a package-managed default Skill both apply, agents should use the more specific project-local Skill first. The local Skill should keep durable conclusions in `project_context/**` and `DESIGN.md`. Its front matter `description` should stay aligned with the matching default `context_*` Skill and the project `AGENTS.md` role-trigger rule; update both the local Skill and agent guidance when adding or narrowing product/design/development trigger terms. `sync` does not merge Skill overrides and does not overwrite separate project-local Skills. Existing `<harnessRoot>/ty-context-managed/override_skills/*.md` files should be migrated into standalone project-local Skills before running `sync`.
 
-Do not customize the package-managed Surface Contract, Harness upgrade, `/normal-long-task` or `/superpowers-long-task` Skills directly. Project-specific surface responsibilities, upgrade facts and acceptance semantics belong in `project_context/**`; recurring project-local procedures belong in separate project-local Skills.
+Do not customize the package-managed Surface Contract, Harness upgrade, `/normal-long-task` or `/composite-long-task-workflow` Skills directly. Project-specific surface responsibilities, upgrade facts and acceptance semantics belong in `project_context/**`; recurring project-local procedures belong in separate project-local Skills.
 
 ## Sync And Upgrade Boundary
 

package/assets/README.md

@@ -94,7 +94,7 @@ That smoke packs the local workspace, installs it into a disposable repo, runs `
 ```sh
 npm run preview:pack
 cd /path/to/your/test-repo
-npm install -D /path/to/project-tiny-context-harness/tmp/ty-context/source-preview/package/project-tiny-context-harness-0.2.78.tgz
+npm install -D /path/to/project-tiny-context-harness/tmp/ty-context/source-preview/package/project-tiny-context-harness-0.2.80.tgz
 npx --no-install ty-context init --adopt
 make validate-context
 ```
@@ -128,7 +128,7 @@ For long-running tasks, externalize the target first. Use explicit Skill invocat
 ```text
 Web GPT or another external planning model produces the long-task source inputs
 -> /normal-long-task produces the full checklist and optional generic target-mode prompt
--> /superpowers-long-task consumes Product / Architecture Source + Technical Realization Plan + Acceptance Checklist when Superpowers execution is needed
+-> /composite-long-task-workflow consumes Product / Architecture Source + Technical Realization Plan + Acceptance Checklist when Superpowers-backed execution is needed
 -> Superpowers derives concrete implementation slices
 -> execution maintains task-state.json, append-only events.ndjson and generated derived views
 -> each slice follows the workflow contract + project_context/**
@@ -138,15 +138,17 @@ For ordinary target-mode preparation, a two-document upstream input remains enou
 
 The ordinary long-task path uses `/normal-long-task`. It is the non-Superpowers acceptance pass: it can generate or reuse the full acceptance checklist and can produce a generic target-mode prompt.
 
-The Superpowers long-task path uses `/superpowers-long-task` when three inputs already exist: `Product / Architecture Source`, `Technical Realization Plan` and `Acceptance Checklist`. The product/architecture source preserves original intent and scope; the technical realization plan is the execution blueprint and plan-conformance source; the checklist is the acceptance authority. The Skill does not perform complexity routing: invocation means Superpowers long-task execution was already selected. Two-document compatibility is allowed only when the first document clearly contains both product/architecture source and technical realization plan sections. If only a product/architecture source and checklist exist, the Skill stops with a Missing Fields Report for a missing `Technical Realization Plan` instead of generating one. The technical realization plan must already satisfy the required Superpowers-ready Markdown implementation plan fields; if it does, the prompt binds it directly to Superpowers execution rather than regenerating the plan, and if it does not, the Skill stops before generating a prompt. The prompt is Tiny Context's adapter layer, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema. It may wrap Superpowers with Tiny Context authority, conformance and acceptance gates, but it must not redefine or fork Superpowers execution mechanics. It requires parent-level `Product Context Delta` and `Technical Context Delta` checks before implementation and uses a canonical state kernel under `tmp/ty-context/plan-acceptance/<plan-slug>/`: `task-state.json` is the only execution state source, `events.ndjson` is append-only and `derived/**` contains generated local audit, plan-conformance matrix, final acceptance verdict, progress ledger, evidence index, context alignment and final summary views. Complete acceptance rows are externally reviewable evidence claims derived from `task-state.evidence[]`: the checklist supplies the proof chain, fresh reviewable evidence must satisfy every required layer, and material drift, missing layers or unapproved sibling substitution prevent `complete`. Goal-mode wording separates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`: implementation / execution goals complete only when `ty-context superpowers final-gate` computes `product_goal_complete=true`; read-only audit goals may end at `audit_task_complete`, but a non-accepted verdict says `Audit workflow completed; acceptance target not complete.` and does not use unqualified `Goal achieved` or `update_goal(status="complete")` as acceptance of the user target.
+The Composite Long-Task Workflow path uses `/composite-long-task-workflow` when three inputs already exist: `Product / Architecture Source`, `Technical Realization Plan` and `Acceptance Checklist`. The product/architecture source preserves original intent and scope; the technical realization plan is the execution blueprint and plan-conformance source; the checklist is the acceptance authority. The Skill does not perform complexity routing: invocation means Superpowers-backed composite execution was already selected. Two-document compatibility is allowed only when the first document clearly contains both product/architecture source and technical realization plan sections. If only a product/architecture source and checklist exist, the Skill stops with a Missing Fields Report for a missing `Technical Realization Plan` instead of generating one. The technical realization plan must already satisfy the required Superpowers-ready Markdown implementation plan fields. When it does, the Skill freezes the package-managed workflow into `workflow-protocol.md`, writes task-local `execution-binding.md`, and renders `goal-objective.txt` as a thin Codex Goal objective instead of packing the full workflow into goal text. This is intentional: the Goal objective stays small enough to preserve the persistent completion contract, while the complete executable workflow lives in the protocol snapshot and the task-specific binding. The expected runtime effect is explicit fusion rather than agent improvisation: Tiny Context Workflow Contract first, then three-input authority, state compilation, Superpowers implementation slices, canonical evidence/state updates, generated views, slice/epoch gates and final-gate completion. The workflow is Tiny Context's composite adapter layer, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema; it is not the Tiny Context Workflow Contract itself, not a business fact source, not a generic prompt generator and not a Superpowers fork. It may wrap Superpowers with Tiny Context authority, conformance and acceptance gates, but it must not redefine or fork Superpowers execution mechanics. It requires parent-level `Product Context Delta` and `Technical Context Delta` checks before implementation and uses a canonical state kernel under `tmp/ty-context/plan-acceptance/<plan-slug>/`: `task-state.json` is the only execution state source, `events.ndjson` is append-only and `derived/**` contains generated local audit, plan-conformance matrix, final acceptance verdict, progress ledger, evidence index, context alignment and final summary views. Complete acceptance rows are externally reviewable evidence claims derived from `task-state.evidence[]`: the checklist supplies the proof chain, fresh reviewable evidence must satisfy every required layer, and material drift, missing layers or unapproved sibling substitution prevent `complete`. Goal-mode wording separates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`: implementation / execution goals complete only when `ty-context composite-long-task final-gate` computes `product_goal_complete=true`; read-only audit goals may end at `audit_task_complete`, but a non-accepted verdict says `Audit workflow completed; acceptance target not complete.` and does not use unqualified `Goal achieved` or `update_goal(status="complete")` as acceptance of the user target.
 
 The three inputs also carry capability-first delivery boundaries. Product / Architecture Source declares `delivery_scope`, `full_population_required`, samples that validate the claim, samples that do not validate it and out-of-scope backlog. Each Technical Realization Plan item declares delivery scope, capability target, representative samples, full-population boundary and non-required population. Each Acceptance Checklist item declares acceptance scope, what it validates and does not validate, sample boundary and full-population requirement. `scope_conflict_requires_decision` blocks completion when source, plan and checklist disagree between system capability build, representative sample validation and full-population operation. Sample evidence or framework-only implementation cannot prove all-provider, all-interface, all-platform or full-population completion unless the AC explicitly allows it; when full population is not explicitly required, generated views report it as `not_in_scope`.
 
-For non-trivial Superpowers slices, the generated prompt requires a structured `slice-delta.json`. The executor applies it with `ty-context superpowers apply-slice-delta <workdir> <slice-delta.json>`, then runs `ty-context superpowers derive` and `ty-context superpowers slice-gate`. Each delta records touched plan items/ACs, code changes, closed and remaining proof layers, blockers, cleanup assertions, `progress_value` and canonical evidence records with `proves`, `does_not_prove`, freshness, redaction and reviewability. Default slice guidance is to group 2-4 strongly related missing layers that share an AC, runtime scenario, proof environment or verification path, while single-gap slices are reserved for blockers, contradictions or small metadata cleanup. The prompt also asks executors to classify missing layers, reuse DB/API/Browser environments only with unique proof prefixes and cleanup assertions, and run a stale/overclaim scan after deriving artifacts.
+`ty-context composite-long-task compile` uses a strict heading-based grammar for that packet. Product / Architecture Source is one document-level object with fixed fields. Technical Realization Plan items are definitions only when written as Markdown headings such as `## PI-001: ...`; Acceptance Checklist items are definitions only when written as headings such as `## AC-001: ...`. Fields inside those sections must use fixed `key: value`, indented-list or `key: |` syntax. Plain prose, tables, mapping previews and ordinary lists that mention `PI-001` or `AC-001` are references, not definitions; old list-style definitions such as `- PI-001: ...` followed by delivery fields now fail at compile time with file and line guidance.
+
+For non-trivial Superpowers-backed slices, the workflow protocol requires a structured `slice-delta.json`. The executor applies it with `ty-context composite-long-task apply-slice-delta <workdir> <slice-delta.json>`, then runs `ty-context composite-long-task derive` and `ty-context composite-long-task slice-gate`. Each delta records touched plan items/ACs, code changes, closed and remaining proof layers, blockers, cleanup assertions, `progress_value` and canonical evidence records with `proves`, `does_not_prove`, freshness, redaction and reviewability. Default slice guidance is to group 2-4 strongly related missing layers that share an AC, runtime scenario, proof environment or verification path, while single-gap slices are reserved for blockers, contradictions or small metadata cleanup. The protocol also asks executors to classify missing layers, reuse DB/API/Browser environments only with unique proof prefixes and cleanup assertions, and run a stale/overclaim scan after deriving artifacts.
 
 The generated Superpowers prompt uses Slice Gate / Epoch Gate / Final Gate cadence instead of running a full final gate after every slice. Progress Accounting tracks AC acceptance completion, engineering implementation progress, runtime/proof progress, system capability progress, representative sample progress, real object coverage, full population operation progress, artifact budget, proof-layer milestone status and workflow overhead in state and generated `derived/progress-ledger.*`. Workflow overhead backpressure asks executors to batch shared provider/browser/runtime/security epoch proof environments, prune stale artifacts and choose the Next 3-5 high-value clusters that close the most blocking AC/proof-layer gaps.
 
-The recommended Superpowers layer is the specific [obra/Superpowers](https://github.com/obra/superpowers) plugin/workflow, not a generic planning substitute. After `/superpowers-long-task` accepts the input packet, prefer `superpowers:subagent-driven-development` when subagents are available and `superpowers:executing-plans` otherwise. Behavior changes should use `superpowers:test-driven-development`. Final gate order is derive all views, `superpowers:verification-before-completion`, `ty-context validate-superpowers-state <dir>`, `ty-context validate-plan-acceptance <dir>`, read-only auditor when available, rederive/revalidate if auditor fixes changed state or evidence, final stale/overclaim scan, then `ty-context superpowers final-gate <dir>` computes completion. The auditor reconstructs AC proof chains with a fixed auditor checklist and finds gaps, but does not become proof. Superpowers review and verification remain useful execution checks, but they cannot override Tiny Context gates: passing Superpowers review does not by itself prove plan conformance or checklist acceptance.
+The recommended Superpowers layer is the specific [obra/Superpowers](https://github.com/obra/superpowers) plugin/workflow, not a generic planning substitute. After `/composite-long-task-workflow` accepts the input packet, prefer `superpowers:subagent-driven-development` when subagents are available and `superpowers:executing-plans` otherwise. Behavior changes should use `superpowers:test-driven-development`. Final gate order is derive all views, `superpowers:verification-before-completion`, `ty-context validate-superpowers-state <dir>`, `ty-context validate-plan-acceptance <dir>`, read-only auditor when available, rederive/revalidate if auditor fixes changed state or evidence, final stale/overclaim scan, then `ty-context composite-long-task final-gate <dir>` computes completion. The auditor reconstructs AC proof chains with a fixed auditor checklist and finds gaps, but does not become proof. Superpowers review and verification remain useful execution checks, but they cannot override Tiny Context gates: passing Superpowers review does not by itself prove plan conformance or checklist acceptance.
 
 The reason is drift control. The workflow contract plus Context layer is intentionally a soft constraint. It works well for short tasks, and Context can still capture the expected facts for long tasks, but long execution makes the Context-to-code step drift as the context window grows, work is handed off, subagents split scope or validation loops multiply. The extra Tiny Context gates exist because Superpowers alone can still drift under long-running execution pressure: it strengthens execution discipline, but it does not by itself preserve source authority, prevent scope shrinkage, prove full conformance to the Technical Realization Plan or enforce AC-by-AC evidence against the Acceptance Checklist. A product/architecture source, technical realization plan, acceptance checklist, explicit long-task Skill invocation, target-mode prompt, canonical task state, generated derived views and optional Superpowers execution layer make implementation conformance and completion evidence recoverable without restoring a phase-gated workflow.
 
@@ -276,7 +278,7 @@ npx --yes --package project-tiny-context-harness@latest ty-context init --adopt
 - `<harnessRoot>/skills/context_full_project_export/SKILL.md`
 - `<harnessRoot>/skills/context_harness_upgrade/SKILL.md`
 - `<harnessRoot>/skills/normal-long-task/SKILL.md`
-- `<harnessRoot>/skills/superpowers-long-task/SKILL.md`
+- `<harnessRoot>/skills/composite-long-task-workflow/SKILL.md`
 - `<harnessRoot>/ty-context-managed/context_templates/**`
 - `<harnessRoot>/ty-context-managed/make/ty-context.mk`
 - `tools/**`
@@ -311,7 +313,7 @@ No. It checks that recovery facts exist and avoids fake test-result claims. Prod
 
 It should stay smaller than a full process. Ordinary bug fixes and local refactors do not update Context unless they produce durable product, architecture, API, state or validation facts.
 
-The default Skills are Minimal Context helpers for explicit product-planning, UI/UX-design, development-engineering, Product Surface Contract, full-project-export, Tiny Context upgrade and explicit long-task requests. Product, screen-flow, surface responsibility and durable engineering conclusions go to `project_context/**`; visual identity and design tokens go to root `DESIGN.md`. Export artifacts are temporary files under `tmp/ty-context/context-exports/**`, not Context. Long-task artifacts are temporary files under `tmp/ty-context/plan-acceptance/**`; they define completion criteria or execution evidence for a referenced plan but do not execute it or become durable Context. The ordinary long-task Skill is invoked as `/normal-long-task`: if the plan already contains an explicit concrete checklist, it reuses that checklist verbatim in the separate full-checklist file. For a two-document upstream input, the external planner should provide a `Development Plan` and an `Acceptance and Tests` packet; `/normal-long-task` preserves both source roles and, only when strict-mode required fields are fully parseable from both documents, turns them into the full checklist plus optional generic target prompt. When a generated prompt references a full checklist, that checklist is the authoritative acceptance standard; the compact prompt summary is only navigation and priority guidance. The Superpowers long-task Skill is invoked as `/superpowers-long-task`: it consumes `Product / Architecture Source`, `Technical Realization Plan` and `Acceptance Checklist`, emits the Superpowers-specific target-mode prompt, directly binds a Superpowers-ready external implementation plan when supplied, requires capability-first delivery scope fields, `Product Context Delta`, `Technical Context Delta`, `plan-conformance-matrix.*`, `final-acceptance-verdict.*` and externally reviewable proof-chain evidence during future execution, and stops if required fields are missing. The Harness upgrade Skill handles requests such as “upgrade Tiny Context” and “use the Tiny Context upgrade skill to upgrade this project” by following the release update mode, using `upgrade` for migration-bearing releases, and limiting manual cleanup to migration-scoped follow-up.
+The default Skills are Minimal Context helpers for explicit product-planning, UI/UX-design, development-engineering, Product Surface Contract, full-project-export, Tiny Context upgrade and explicit long-task requests. Product, screen-flow, surface responsibility and durable engineering conclusions go to `project_context/**`; visual identity and design tokens go to root `DESIGN.md`. Export artifacts are temporary files under `tmp/ty-context/context-exports/**`, not Context. Long-task artifacts are temporary files under `tmp/ty-context/plan-acceptance/**`; they define completion criteria or execution evidence for a referenced plan but do not execute it or become durable Context. The ordinary long-task Skill is invoked as `/normal-long-task`: if the plan already contains an explicit concrete checklist, it reuses that checklist verbatim in the separate full-checklist file. For a two-document upstream input, the external planner should provide a `Development Plan` and an `Acceptance and Tests` packet; `/normal-long-task` preserves both source roles and, only when strict-mode required fields are fully parseable from both documents, turns them into the full checklist plus optional generic target prompt. When a generated prompt references a full checklist, that checklist is the authoritative acceptance standard; the compact prompt summary is only navigation and priority guidance. The Composite Long-Task Workflow Skill is invoked as `/composite-long-task-workflow`: it consumes `Product / Architecture Source`, `Technical Realization Plan` and `Acceptance Checklist`, freezes `workflow-protocol.md`, writes `execution-binding.md`, renders `goal-objective.txt`, directly binds a Superpowers-ready external implementation plan when supplied, requires capability-first delivery scope fields, `Product Context Delta`, `Technical Context Delta`, `plan-conformance-matrix.*`, `final-acceptance-verdict.*` and externally reviewable proof-chain evidence during future execution, and stops if required fields are missing. The Harness upgrade Skill handles requests such as “upgrade Tiny Context” and “use the Tiny Context upgrade skill to upgrade this project” by following the release update mode, using `upgrade` for migration-bearing releases, and limiting manual cleanup to migration-scoped follow-up.
 
 Multilingual trigger phrases are compatibility details. Public README, npm and launch copy stay English-first, and public/package-managed surfaces must remain English-complete; literal non-English examples are documented only where they explain generated Skill matching and must not be the sole activation path.
 
@@ -321,9 +323,11 @@ Technical architecture support is a Minimal Context capability: use restrained `
 
 For long-running plans, RFCs or implementation proposals, invoke `/normal-long-task` to turn a plan plus relevant Context into a falsifiable acceptance checklist and an optional generic paste-ready goal/target-mode prompt. It also supports a two-document upstream input from Web GPT or another external planner: `Development Plan` for execution direction and `Acceptance and Tests` for target-mode acceptance input. If the plan already contains an explicit concrete acceptance checklist, the Skill copies that checklist verbatim into a separate full-checklist file instead of generating a competing checklist. The two-document packet path is strict mode: when required fields cannot be fully parsed from both documents, the Skill preserves the inputs, reports the missing fields, and stops without generating a checklist or goal/target-mode prompt. This is one pre-execution acceptance pass, not a task planner or workflow engine: it stores temporary inputs under `tmp/ty-context/plan-acceptance/**`, asks for confirmation when durable assumptions are unclear, and leaves execution evidence to the future executor, tests, CI, review or human acceptance. The generated prompt may require a local audit under the same temporary directory so future sessions can recover acceptance progress; that audit is not Context, not a quality proof and not a replacement for the project's Tiny Context workflow contract. The full checklist is the acceptance authority, while any compact prompt summary exists for navigation, priority and recovery after context compaction.
 
-When the next step explicitly needs Superpowers, invoke `/superpowers-long-task` on the Product / Architecture Source, Technical Realization Plan and Acceptance Checklist. It emits the `Superpowers input packet` and execution binding so the future executor sees which inputs feed Context Delta assessment, `superpowers:subagent-driven-development`, `superpowers:executing-plans`, TDD, `superpowers:verification-before-completion`, canonical `task-state.json`, append-only `events.ndjson`, generated `derived/**` views, proof-chain evidence and optional auditor review. This is Tiny Context's adapter layer for Superpowers workflows, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema. It may wrap Superpowers with authority, conformance and acceptance gates, but it must not redefine, duplicate or fork Superpowers execution mechanics; if a future Tiny Context-added step would conflict with, duplicate or override a Superpowers responsibility, stop and surface the boundary conflict instead of silently merging workflows. It cannot replace `/normal-long-task` for ordinary checklist preparation, does not route complexity, and does not derive a technical plan from a product plan; the Technical Realization Plan must already be a Superpowers-ready Markdown implementation plan or the Skill stops before generating a prompt. A two-document packet is accepted only when the first document explicitly contains both product/architecture source and technical realization plan sections. Product / Architecture Source, Technical Realization Plan and Acceptance Checklist remain the upstream authorities, while state/derived views/validator/auditor artifacts cannot rewrite them. Capability-first delivery scope stays inside those same three inputs: source, plan items and ACs must explicitly distinguish reusable system capability build, representative sample validation, full population operation and out-of-scope backlog; `scope_conflict_requires_decision` blocks completion, and sample/framework evidence cannot prove full population unless the AC says so. The generated prompt also disambiguates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`; implementation / execution goals finish only when `product_goal_complete=true`, while a read-only audit goal can end at `audit_task_complete` only with a non-accepted verdict reported as `Audit workflow completed; acceptance target not complete.`, not as `Goal achieved`.
+When the next step explicitly needs Superpowers-backed long-task execution, invoke `/composite-long-task-workflow` on the Product / Architecture Source, Technical Realization Plan and Acceptance Checklist. It emits `workflow-protocol.md`, `execution-binding.md` and `goal-objective.txt` so the future executor sees which inputs feed Context Delta assessment, `superpowers:subagent-driven-development`, `superpowers:executing-plans`, TDD, `superpowers:verification-before-completion`, canonical `task-state.json`, append-only `events.ndjson`, generated `derived/**` views, proof-chain evidence and optional auditor review. This is Tiny Context's composite adapter layer for Superpowers-backed workflows, aligned to the official Superpowers skills while remaining a Tiny Context-owned adapter rather than an upstream-owned schema. It may wrap Superpowers with authority, conformance and acceptance gates, but it must not redefine, duplicate or fork Superpowers execution mechanics; if a future Tiny Context-added step would conflict with, duplicate or override a Superpowers responsibility, stop and surface the boundary conflict instead of silently merging workflows. It cannot replace `/normal-long-task` for ordinary checklist preparation, does not route complexity, and does not derive a technical plan from a product plan; the Technical Realization Plan must already be a Superpowers-ready Markdown implementation plan or the Skill stops before rendering entry artifacts. A two-document packet is accepted only when the first document explicitly contains both product/architecture source and technical realization plan sections. Product / Architecture Source, Technical Realization Plan and Acceptance Checklist remain the upstream authorities, while state/derived views/validator/auditor artifacts cannot rewrite them. Capability-first delivery scope stays inside those same three inputs: source, plan items and ACs must explicitly distinguish reusable system capability build, representative sample validation, full population operation and out-of-scope backlog; `scope_conflict_requires_decision` blocks completion, and sample/framework evidence cannot prove full population unless the AC says so. The generated Goal objective also disambiguates `audit_task_complete`, `acceptance_target_status` and computed `product_goal_complete`; implementation / execution goals finish only when `product_goal_complete=true`, while a read-only audit goal can end at `audit_task_complete` only with a non-accepted verdict reported as `Audit workflow completed; acceptance target not complete.`, not as `Goal achieved`.
+
+Important usage note: Minimal Context intentionally keeps Context read order, Context/code priority and drift checks as agent-level soft constraints rather than machine-enforced gates. That tradeoff works well for short tasks, but long tasks with large context windows, multiple handoffs or many verification loops are expected to drift unless product intent, technical implementation target and acceptance target are externalized. Superpowers alone can still drift under this pressure: it strengthens execution discipline, but it does not by itself preserve source authority, prevent scope shrinkage, prove full conformance to the Technical Realization Plan or enforce AC-by-AC evidence against the Acceptance Checklist. Use `/normal-long-task` before long-running execution when ordinary checklist preparation is needed; use `/composite-long-task-workflow` when the three upstream inputs already exist and Superpowers-backed execution is desired. Treat `task-state.json` as the only execution state source, `events.ndjson` as append-only, `derived/**` as generated reading views and `task-state.evidence[]` as the canonical evidence ledger. `validate-superpowers-state` and state-backed `validate-plan-acceptance` are still artifact/state-consistency validators, not product-quality proof; a subagent auditor is an extra gap-finding pass on top of executor self-evidence and validator checks, not a replacement for either. Passing Superpowers review or verification does not bypass incomplete state rows, weak evidence, missing proof layers or blocking auditor findings.
 
-Important usage note: Minimal Context intentionally keeps Context read order, Context/code priority and drift checks as agent-level soft constraints rather than machine-enforced gates. That tradeoff works well for short tasks, but long tasks with large context windows, multiple handoffs or many verification loops are expected to drift unless product intent, technical implementation target and acceptance target are externalized. Superpowers alone can still drift under this pressure: it strengthens execution discipline, but it does not by itself preserve source authority, prevent scope shrinkage, prove full conformance to the Technical Realization Plan or enforce AC-by-AC evidence against the Acceptance Checklist. Use `/normal-long-task` before long-running execution when ordinary checklist preparation is needed; use `/superpowers-long-task` when the three upstream inputs already exist and Superpowers execution is desired. Treat `task-state.json` as the only execution state source, `events.ndjson` as append-only, `derived/**` as generated reading views and `task-state.evidence[]` as the canonical evidence ledger. `validate-superpowers-state` and state-backed `validate-plan-acceptance` are still artifact/state-consistency validators, not product-quality proof; a subagent auditor is an extra gap-finding pass on top of executor self-evidence and validator checks, not a replacement for either. Passing Superpowers review or verification does not bypass incomplete state rows, weak evidence, missing proof layers or blocking auditor findings.
+Hallucination guard: do not register `workflow-protocol.md` in `project_context/context.toml`, treat it as business Context, let `derived/**` rewrite Product / Plan / Checklist, use local audit or Superpowers review as quality proof, use sample evidence as full-population proof, claim full alignment while Source-to-Context Coverage or Context-to-Implementation Binding has unresolved required gaps, handwrite `product_goal_complete`, or complete an implementation Goal before final-gate passes.
 
 For Product Surface work, `context_surface_contract` turns broad product/page/UI principles into project-owned surface responsibilities. A Product Surface can be a Web page, mobile screen, desktop window, game UI/HUD/menu, CLI/TUI output, extension UI or embedded/device interface. Cross-surface contracts use the existing `contract` role; area-owned screen facts stay in `area` or `subdomain`; repeatable validation paths use `verification`. The Harness does not add a new surface-specific role or create business surface contracts during `init` or `upgrade`. Product Surface Context authoring is not a default product-quality validator; plan validators only check declared temporary surface bindings for structural consistency. Projects that want mandatory task blocks should add a separate project-local Skill, while `product-surface-contract.md` is only a compact managed template for optional Context authoring.
 
@@ -376,7 +380,7 @@ The expected Context Priority Ladder is: read Context first, run the product/pag
 
 Managed `AGENTS.md` guidance is intentionally a startup router, not a full manual. It should contain fact-source entry points, hard boundaries, key triggers and shortest validation commands; package consumers default long design reasoning to Context unless they already have a local spec/design convention. In this source workspace, `PROJECT_SPEC.md` holds stable Harness workflow rationale. Role procedures belong in Skills and human usage guidance in README. The recommended 40-70 line range is a soft budget, not a validator gate.
 
-The default `context_*` Skills and package-managed utility Skills are generated files. `sync` overwrites them, so project-specific product/design/development/surface-contract rules should live in separate project-local Skills such as `.codex/skills/product_plan/SKILL.md`, `.codex/skills/uiux_design/SKILL.md`, `.codex/skills/development_engineer/SKILL.md` or `.codex/skills/surface_contract/SKILL.md`. When a project-local Skill and a default Skill both apply, agents should use the more specific project-local Skill first while keeping durable conclusions in `project_context/**` and `DESIGN.md`. Keep the project-local Skill front matter `description` triggers aligned with the matching default `context_*` Skill and the project `AGENTS.md` role-trigger rule; if a project adds or narrows product/design/development/surface keywords, update both the local Skill and the agent guidance together. The Surface Contract, Harness upgrade, `/normal-long-task` and `/superpowers-long-task` Skills are also package-managed; customize project semantics in Context or separate project-local Skills, not by editing those generated Skills.
+The default `context_*` Skills and package-managed utility Skills are generated files. `sync` overwrites them, so project-specific product/design/development/surface-contract rules should live in separate project-local Skills such as `.codex/skills/product_plan/SKILL.md`, `.codex/skills/uiux_design/SKILL.md`, `.codex/skills/development_engineer/SKILL.md` or `.codex/skills/surface_contract/SKILL.md`. When a project-local Skill and a default Skill both apply, agents should use the more specific project-local Skill first while keeping durable conclusions in `project_context/**` and `DESIGN.md`. Keep the project-local Skill front matter `description` triggers aligned with the matching default `context_*` Skill and the project `AGENTS.md` role-trigger rule; if a project adds or narrows product/design/development/surface keywords, update both the local Skill and the agent guidance together. The Surface Contract, Harness upgrade, `/normal-long-task` and `/composite-long-task-workflow` Skills are also package-managed; customize project semantics in Context or separate project-local Skills, not by editing those generated Skills.
 
 ## CLI Entry Safety
 
@@ -401,9 +405,9 @@ Use `npx --no-install ty-context ...` only when you explicitly want the already
 | `npx --yes --package project-tiny-context-harness@latest ty-context check-modularity --touched [--limit 300] [--fail-on-warning]` | Reports selected handwritten source files over the physical line-count limit; `--file <path>` and `--base <ref>` select explicit files or branch changes, and config waivers are reported distinctly. |
 | `npx --yes --package project-tiny-context-harness@latest ty-context validate-context` | Checks minimum project recovery fields, Context graph metadata, declared paths/roles and fake test-execution claims. |
 | `npx --yes --package project-tiny-context-harness@latest ty-context validate-plan-contract <plan.md\|dir>` | Checks Source-to-Context Coverage and Context-to-Implementation Binding for structural consistency, referenced path existence and weak-proof complete/bound contradictions. |
-| `npx --yes --package project-tiny-context-harness@latest ty-context validate-superpowers-state <dir>` | Checks canonical Superpowers `task-state.json`, source hashes, graph references, delivery scope fields/conflicts, evidence/proof-layer consistency, stale evidence, sibling substitution, auditor blockers, derived drift and final completion rules. |
+| `npx --yes --package project-tiny-context-harness@latest ty-context validate-superpowers-state <dir>` | Checks canonical Superpowers-backed `task-state.json`, source hashes, graph references, delivery scope fields/conflicts, evidence/proof-layer consistency, stale evidence, sibling substitution, auditor blockers, derived drift and final completion rules. |
 | `npx --yes --package project-tiny-context-harness@latest ty-context validate-plan-acceptance <dir>` | Checks legacy matrix/verdict artifacts when no state exists; when `task-state.json` exists, validates state-backed derived artifacts. It rejects contradictory complete claims, dangling evidence references, weak-proof complete rows, missing proof layers, material/critical drift, unapproved sibling substitution, blocking auditor findings, raw secrets/tokens/cookies, generated active-count drift, missing plan/AC cross-references and declared surface/architecture binding gaps. `errors` block; `warnings` / `hygiene` report cleanup. |
-| `npx --yes --package project-tiny-context-harness@latest ty-context superpowers <subcommand>` | Explicit `/superpowers-long-task` state helper for `init`, `compile`, `apply-slice-delta`, `derive`, `slice-gate`, `epoch-gate`, `final-gate` and `next-slices` under `tmp/ty-context/plan-acceptance/**`. |
+| `npx --yes --package project-tiny-context-harness@latest ty-context composite-long-task <subcommand>` | Explicit `/composite-long-task-workflow` state helper for `init`, `compile`, `apply-slice-delta`, `derive`, `slice-gate`, `epoch-gate`, `final-gate`, `next-slices` and `render-goal` under `tmp/ty-context/plan-acceptance/**`. |
 | `make validate-context` | Makefile wrapper for `validate-context`. |
 | `make validate-code-modularity` | Hard gate for touched handwritten source modularity; CI can set `TY_CONTEXT_MODULARITY_BASE=<ref>` to audit PR/base changes. |
 | `make validate-harness` | Composite gate for `validate-context` and `validate-code-modularity`. |

package/assets/README.zh-CN.md

@@ -54,15 +54,19 @@ Tiny Context 有两个核心层。Minimal Context 是长期事实源层：说明
 
 对于长程任务，Harness 提供两个显式调用的长程任务 Skill。普通长程任务用 `/normal-long-task`：它把方案和验收输入临时放到 `tmp/ty-context/plan-acceptance/**`，生成或复用完整验收清单，并可输出普通目标模式文本。如果外部规划模型参与，推荐仍然只给两份产物：`《开发方案》` 作为执行方向和 plan traceability source，`《验收清单和测试用例》` 作为 Codex target-mode acceptance input packet。第一份应包含可逐项追踪的 plan item、预期落点 surface、full scope 与 sampled/optional 边界；第二份应包含 AC、required evidence、测试命令、真实产品路径 / core path、证据分层、无效证据、状态机、local audit 和 blocker。Source Pack 只是临时上传材料，不是 durable Context。如果方案里已经有明确、具体的“验收清单”，`/normal-long-task` 会直接复用那份清单并单独写入完整验收清单文件；两份输入包走 strict mode，如果两份内容无法完整解析出 required fields，或第二份缺少 required evidence、verification method、fail condition、状态机、无效证据规则等必要字段，Skill 会停止并列出缺失项，不生成完整验收清单或目标模式文本。
 
-Superpowers 长程任务 Skill 用 `/superpowers-long-task`。如果下一步明确要 Superpowers 目标模式文本，推荐在三份输入都存在后调用：`Product / Architecture Source`（产品/架构原始意图源）、`Technical Realization Plan`（具体技术实现方案）和 `Acceptance Checklist`（验收清单）。它不做复杂度分流；调用它表示上游已经决定使用 Superpowers 长程执行。它不要求先跑 `/normal-long-task`，但也不会把产品方案现场翻译成技术方案；如果只有产品/架构方案和验收清单，Skill 会用 Missing Fields Report 停止并报告缺少 `Technical Realization Plan`。两份输入兼容只限第一份明确包含产品/架构源和技术实现方案两个章节。`Technical Realization Plan` 必须已经满足 Superpowers-ready Markdown implementation plan 的必填字段；满足时它跳过方案生成，直接绑定 Superpowers 执行，不满足时直接中断并报告缺失字段，不生成 prompt。它显式输出 `Superpowers 输入包` 和执行绑定，让未来 executor 清楚哪些输入进入 parent-level Product Context Delta / Technical Context Delta、slice-level new durable fact check、subagent/inline execution、TDD、`superpowers:verification-before-completion`、canonical `task-state.json`、append-only `events.ndjson`、generated `derived/**` views、proof-chain evidence 和 optional auditor review。这个 prompt 是面向 Superpowers workflow 的 Tiny Context 适配层，对齐官方 Superpowers skills，但不是上游维护的 schema；它可以在 Superpowers 外层增加 Tiny Context 的权威、对图纸和验收门禁，但不能重新定义、重复或分叉 Superpowers 执行机制。如果未来改动让 Tiny Context 新增步骤和官方 Superpowers 职责冲突、重复或覆盖，应停止修改并提示边界冲突，不要静默合并两套流程。它不生成技术方案或验收清单、不执行计划、不证明完成，也不会把临时 state、derived views 或 verdict 注册成 `project_context/**`。三输入是上游权威，state / derived views / validator / auditor 不能改写它们。`task-state.json` 是唯一执行状态源，`events.ndjson` 追加记录状态变更，`derived/**` 只生成 local audit、plan-conformance matrix、final acceptance verdict、progress ledger、evidence index、context alignment 和 final summary 等阅读视图。完整验收行按外部审计证据处理：proof chain 来自验收清单，fresh evidence 必须通过 `task-state.evidence[]` 满足每个 required layer，存在 material drift、缺 required layer 或未批准 sibling substitution 时不能标 `complete`。Goal mode 表述必须区分 `audit_task_complete`、`acceptance_target_status` 和 computed `product_goal_complete`：实现/执行目标只在 `ty-context superpowers final-gate` 计算出 `product_goal_complete=true` 时完成；只读审计目标可在 `audit_task_complete` 时结束，但 verdict 不是 accepted/complete 时，回复写 `Audit workflow completed; acceptance target not complete.`，不能用未限定的 `Goal achieved` 或 `update_goal(status="complete")` 表示用户验收目标已完成。
+Composite Long-Task Workflow Skill 用 `/composite-long-task-workflow`。如果下一步明确要 Superpowers-backed 目标模式执行，推荐在三份输入都存在后调用：`Product / Architecture Source`（产品/架构原始意图源）、`Technical Realization Plan`（具体技术实现方案）和 `Acceptance Checklist`（验收清单）。它不做复杂度分流；调用它表示上游已经决定使用 composite long-task execution。它不要求先跑 `/normal-long-task`，但也不会把产品方案现场翻译成技术方案；如果只有产品/架构方案和验收清单，Skill 会用 Missing Fields Report 停止并报告缺少 `Technical Realization Plan`。两份输入兼容只限第一份明确包含产品/架构源和技术实现方案两个章节。`Technical Realization Plan` 必须已经满足 Superpowers-ready Markdown implementation plan 的必填字段；满足时它跳过方案生成，直接绑定 Superpowers 执行，不满足时直接中断并报告缺失字段，不生成 prompt。它输出 `workflow-protocol.md`、`execution-binding.md` 和可直接用于 Codex Goal mode 的薄 `goal-objective.txt`，不是把完整 workflow 塞进 4000 字 Goal：Goal 只保留持续完成契约，完整可执行流程放在 protocol snapshot 和 task-specific binding。预期运行效果是显式融合而不是让 agent 自行发挥：先 Tiny Context 流程契约，再三份输入权威，再编译 task-state，再进入 Superpowers implementation slice，每个 slice 更新 canonical state/evidence，derive 出阅读视图，经过 slice/epoch gate，最后 final-gate 计算完成。这个 workflow 是面向 Superpowers execution 的 Tiny Context 适配层，对齐官方 Superpowers skills，但不是上游维护的 schema；它不是 Tiny Context 流程契约本身、不是业务事实源、不是普通 prompt generator、也不是 Superpowers fork。它可以在 Superpowers 外层增加 Tiny Context 的权威、对图纸和验收门禁，但不能重新定义、重复或分叉 Superpowers 执行机制。如果未来改动让 Tiny Context 新增步骤和官方 Superpowers 职责冲突、重复或覆盖，应停止修改并提示边界冲突，不要静默合并两套流程。它不生成技术方案或验收清单、不执行计划、不证明完成，也不会把临时 state、derived views 或 verdict 注册成 `project_context/**`。三输入是上游权威，state / derived views / validator / auditor 不能改写它们。`task-state.json` 是唯一执行状态源，`events.ndjson` 追加记录状态变更，`derived/**` 只生成 local audit、plan-conformance matrix、final acceptance verdict、progress ledger、evidence index、context alignment 和 final summary 等阅读视图。完整验收行按外部审计证据处理：proof chain 来自验收清单，fresh evidence 必须通过 `task-state.evidence[]` 满足每个 required layer，存在 material drift、缺 required layer 或未批准 sibling substitution 时不能标 `complete`。Goal mode 表述必须区分 `audit_task_complete`、`acceptance_target_status` 和 computed `product_goal_complete`：实现/执行目标只在 `ty-context composite-long-task final-gate` 计算出 `product_goal_complete=true` 时完成；只读审计目标可在 `audit_task_complete` 时结束，但 verdict 不是 accepted/complete 时，回复写 `Audit workflow completed; acceptance target not complete.`，不能用未限定的 `Goal achieved` 或 `update_goal(status="complete")` 表示用户验收目标已完成。
 
 三份输入还必须承载 capability-first delivery 边界。Product / Architecture Source 声明 `delivery_scope`、`full_population_required`、哪些 representative samples 能验证 claim、哪些不能验证、以及 `out_of_scope_backlog`。每个 Technical Realization Plan item 声明 delivery scope、capability target、representative samples、full-population boundary 和 non-required population。每个 Acceptance Checklist item 声明 acceptance scope、`ac_validates`、`ac_does_not_validate`、sample boundary 和 full-population requirement。source / plan / checklist 在 system capability build、representative sample validation、full population operation 之间冲突时，`scope_conflict_requires_decision` 阻塞完成。sample evidence 或 framework-only implementation 不能证明 all-provider、all-interface、all-platform 或 full-population 完成，除非 AC 明确批准；未显式要求 full population 时，generated views 必须报告 `not_in_scope`。
 
-对于非平凡 slice，生成的 Superpowers prompt 要求使用结构化 `slice-delta.json`。executor 通过 `ty-context superpowers apply-slice-delta <workdir> <slice-delta.json>` 应用 delta，然后运行 `ty-context superpowers derive` 和 `ty-context superpowers slice-gate`。每个 delta 记录 touched plan items / ACs、code changes、closed / remaining proof layers、blockers、cleanup assertions、`progress_value`，以及带有 `proves`、`does_not_prove`、freshness、redaction 和 reviewability 的 canonical evidence records。默认 slice 策略是把同一 AC、runtime 场景、proof 环境或验证路径下的 2-4 个强相关 missing layers 合并处理；单 gap slice 只留给 blocker、contradiction 或小型 metadata cleanup。prompt 还会要求先分类 missing layer、复用 DB/API/Browser 环境时使用唯一 proof prefix 和 cleanup assertion，并在生成 derived artifacts 后做 stale/overclaim scan。
+`ty-context composite-long-task compile` 对这三份输入使用严格的 heading-based grammar。Product / Architecture Source 是一个文档级对象，只读固定字段。Technical Realization Plan 里的 PI 只有写成 `## PI-001: ...` 这类 Markdown heading 才是正式定义；Acceptance Checklist 里的 AC 也只有 `## AC-001: ...` 这类 heading 才是正式定义。heading section 内字段必须使用固定 `key: value`、缩进列表或 `key: |` 多行块。正文、表格、mapping preview、`related_acs` / `related_plan_items` 和普通列表里出现的 `PI-001` / `AC-001` 都只是引用；旧式 `- PI-001: ...` 或 `- AC-001: ...` 后面跟字段的写法会在 compile 阶段带文件和行号报错。
 
-生成的 Superpowers prompt 使用 Slice Gate / Epoch Gate / Final Gate 分层节奏，而不是每个 slice 后都跑完整 final gate。Progress Accounting 在 state 和 generated `derived/progress-ledger.*` 中记录 AC acceptance completion、engineering implementation progress、runtime/proof progress、system capability progress、representative sample progress、real object coverage、full population operation progress、artifact budget 和 workflow overhead。每个 slice 需要声明 artifact budget、proof-layer milestone 状态和 cleanup expectation。workflow overhead backpressure 要求 executor 批处理共享的 provider/browser/runtime/security epoch proof environment，清理 stale artifact，并选择 Next 3-5 high-value clusters 来优先关闭最多阻塞 AC / proof-layer gap。
+对于非平凡 slice，生成的 composite workflow prompt 要求使用结构化 `slice-delta.json`。executor 通过 `ty-context composite-long-task apply-slice-delta <workdir> <slice-delta.json>` 应用 delta，然后运行 `ty-context composite-long-task derive` 和 `ty-context composite-long-task slice-gate`。每个 delta 记录 touched plan items / ACs、code changes、closed / remaining proof layers、blockers、cleanup assertions、`progress_value`，以及带有 `proves`、`does_not_prove`、freshness、redaction 和 reviewability 的 canonical evidence records。默认 slice 策略是把同一 AC、runtime 场景、proof 环境或验证路径下的 2-4 个强相关 missing layers 合并处理；单 gap slice 只留给 blocker、contradiction 或小型 metadata cleanup。prompt 还会要求先分类 missing layer、复用 DB/API/Browser 环境时使用唯一 proof prefix 和 cleanup assertion，并在生成 derived artifacts 后做 stale/overclaim scan。
 
-重要使用提示：Minimal Context 有意把 Context 读取顺序、Context / 代码优先级和漂移检查保持为 agent 级软约束，而不是机器强制 edit-order gate。这个取舍适合短任务，但长任务、大上下文、多次交接或多轮验证时预期会漂移。单靠 Superpowers 在这类压力下仍可能漂移：它能增强执行纪律，但本身不负责保留上游 source authority、防止 scope shrinkage、证明完整符合 Technical Realization Plan，或按 Acceptance Checklist 逐 AC 强制证据成立。普通 checklist 准备需要 `/normal-long-task`；已有产品/架构原始意图源、具体技术实现方案和验收清单且需要 Superpowers 时，可直接用 `/superpowers-long-task`。`Product Context Delta` 判断产品逻辑、页面职责、信息架构和验收语义是否需要写入 Context；`Technical Context Delta` 判断 API/schema、模块边界、runtime/state、验证/部署路径和稳定技术取舍是否需要写入 Context。`task-state.json` 是唯一执行状态源，`events.ndjson` 追加记录状态变化，`derived/**` 是生成阅读视图，`task-state.evidence[]` 是 canonical evidence ledger；local audit 只是 generated progress/recovery view，不能裁判完成；审计流程完成也不等于被验收目标完成。使用目标模式执行方案时，目标结束条件对齐 computed `product_goal_complete=true`，只读审计目标才可把 `audit_task_complete` 当元任务结束。最终顺序是 derive all views -> verification-before-completion -> `validate-superpowers-state` -> state-backed `validate-plan-acceptance` -> read-only auditor -> stale/overclaim scan -> `ty-context superpowers final-gate` 计算 completion；若审计后修改 state/evidence，需 rederive 并重跑两个 validator。`validate-plan-contract`、`validate-superpowers-state` 和 `validate-plan-acceptance` 只检查临时 artifact/state 自洽、引用存在、弱证据 complete 行、缺 required proof layer、material/critical drift、sibling substitution 和已声明的 surface/architecture binding 一致性，不证明产品质量。有 subagent 能力时，Superpowers 目标提示会把 subagent 作为只读 auditor 加在主 agent 自证和 validator 之后；auditor 用固定 auditor checklist 找 gap，不是 proof source。Superpowers review 和 verification 仍然有价值，但不能覆盖 Tiny Context gates；通过 Superpowers review 不等于证明 plan conformance 或 checklist acceptance。
+生成的 composite workflow prompt 使用 Slice Gate / Epoch Gate / Final Gate 分层节奏，而不是每个 slice 后都跑完整 final gate。Progress Accounting 在 state 和 generated `derived/progress-ledger.*` 中记录 AC acceptance completion、engineering implementation progress、runtime/proof progress、system capability progress、representative sample progress、real object coverage、full population operation progress、artifact budget 和 workflow overhead。每个 slice 需要声明 artifact budget、proof-layer milestone 状态和 cleanup expectation。workflow overhead backpressure 要求 executor 批处理共享的 provider/browser/runtime/security epoch proof environment，清理 stale artifact，并选择 Next 3-5 high-value clusters 来优先关闭最多阻塞 AC / proof-layer gap。
+
+重要使用提示：Minimal Context 有意把 Context 读取顺序、Context / 代码优先级和漂移检查保持为 agent 级软约束，而不是机器强制 edit-order gate。这个取舍适合短任务，但长任务、大上下文、多次交接或多轮验证时预期会漂移。单靠 Superpowers 在这类压力下仍可能漂移：它能增强执行纪律，但本身不负责保留上游 source authority、防止 scope shrinkage、证明完整符合 Technical Realization Plan，或按 Acceptance Checklist 逐 AC 强制证据成立。普通 checklist 准备需要 `/normal-long-task`；已有产品/架构原始意图源、具体技术实现方案和验收清单且需要 Superpowers-backed execution 时，可直接用 `/composite-long-task-workflow`。`Product Context Delta` 判断产品逻辑、页面职责、信息架构和验收语义是否需要写入 Context；`Technical Context Delta` 判断 API/schema、模块边界、runtime/state、验证/部署路径和稳定技术取舍是否需要写入 Context。`task-state.json` 是唯一执行状态源，`events.ndjson` 追加记录状态变化，`derived/**` 是生成阅读视图，`task-state.evidence[]` 是 canonical evidence ledger；local audit 只是 generated progress/recovery view，不能裁判完成；审计流程完成也不等于被验收目标完成。使用目标模式执行方案时，目标结束条件对齐 computed `product_goal_complete=true`，只读审计目标才可把 `audit_task_complete` 当元任务结束。最终顺序是 derive all views -> verification-before-completion -> `validate-superpowers-state` -> state-backed `validate-plan-acceptance` -> read-only auditor -> stale/overclaim scan -> `ty-context composite-long-task final-gate` 计算 completion；若审计后修改 state/evidence，需 rederive 并重跑两个 validator。`validate-plan-contract`、`validate-superpowers-state` 和 `validate-plan-acceptance` 只检查临时 artifact/state 自洽、引用存在、弱证据 complete 行、缺 required proof layer、material/critical drift、sibling substitution 和已声明的 surface/architecture binding 一致性，不证明产品质量。有 subagent 能力时，composite workflow prompt 会把 subagent 作为只读 auditor 加在主 agent 自证和 validator 之后；auditor 用固定 auditor checklist 找 gap，不是 proof source。Superpowers review 和 verification 仍然有价值，但不能覆盖 Tiny Context gates；通过 Superpowers review 不等于证明 plan conformance 或 checklist acceptance。
+
+错误融合防线：不得把 `workflow-protocol.md` 注册进 `project_context/context.toml`，不得把它当业务 Context，不得让 `derived/**` 反向改写 Product / Plan / Checklist，不得把 local audit 或 Superpowers review 当质量证明，不得把 sample evidence 当 full population proof，不得在 Source-to-Context Coverage 或 Context-to-Implementation Binding 仍有 unresolved required gap 时声称完整对齐，不得手写 `product_goal_complete`，final-gate 未通过前不得把实现 Goal 标成 complete。
 
 ## 当前最佳实践
 
@@ -77,13 +81,13 @@ Superpowers 长程任务 Skill 用 `/superpowers-long-task`。如果下一步明
 ```text
 Web GPT 或其他外部规划模型产出长任务源输入
 -> /normal-long-task 生成完整验收清单和可选普通目标模式文本
--> 需要 Superpowers 专用目标模式文本时，/superpowers-long-task 消费 Product / Architecture Source + Technical Realization Plan + Acceptance Checklist
+-> 需要 Superpowers-backed 多组合长程任务工作流时，/composite-long-task-workflow 消费 Product / Architecture Source + Technical Realization Plan + Acceptance Checklist
 -> Superpowers 得出具体落地执行片段
 -> 执行中维护 plan-conformance-matrix，最后生成 final-acceptance-verdict
 -> 每个执行片段都回到流程契约 + project_context/**
 ```
 
-这里的 Superpowers 指具体的 [obra/Superpowers](https://github.com/obra/superpowers) 插件/开源工作流，不是泛化的执行规划替代品。`/superpowers-long-task` 接受输入包后，有 subagent 支持时优先用 `superpowers:subagent-driven-development`，否则用 `superpowers:executing-plans`；涉及行为变更时用 `superpowers:test-driven-development`；完成声明前先 derive all views，再用 `superpowers:verification-before-completion`、`ty-context validate-superpowers-state <dir>`、`ty-context validate-plan-acceptance <dir>` 和 read-only auditor 检查，最后由 `ty-context superpowers final-gate <dir>` 计算 `product_goal_complete`。
+这里的 Superpowers 指具体的 [obra/Superpowers](https://github.com/obra/superpowers) 插件/开源工作流，不是泛化的执行规划替代品。`/composite-long-task-workflow` 接受输入包后会冻结 `workflow-protocol.md`、写入 `execution-binding.md` 并生成薄 `goal-objective.txt`；有 subagent 支持时优先用 `superpowers:subagent-driven-development`，否则用 `superpowers:executing-plans`；涉及行为变更时用 `superpowers:test-driven-development`；完成声明前先 derive all views，再用 `superpowers:verification-before-completion`、`ty-context validate-superpowers-state <dir>`、`ty-context validate-plan-acceptance <dir>` 和 read-only auditor 检查，最后由 `ty-context composite-long-task final-gate <dir>` 计算 `product_goal_complete`。
 
 原因是漂移控制。流程契约 + Context 层是软约束，短任务里通常能让 agent 按预期执行；长程任务里，Context 仍然能记录符合预期的事实，但 Context 到代码 的实现步骤会随着上下文窗口变大、多次交接、subagent 拆分和多轮验证而漂移。单靠 Superpowers 也仍可能在复杂长程执行压力下漂移：它增强执行纪律，但不天然保留 source authority、防止 scope shrinkage、证明完整符合 Technical Realization Plan，或按 Acceptance Checklist 逐 AC 强制证据成立。产品/架构原始意图源、具体技术实现方案、验收清单、显式长程任务 Skill 调用、目标模式文本、canonical task state、generated derived views 和可选 Superpowers 执行层，把“产品/技术 Context 有没有先对齐”“有没有按图纸实现”和“有没有按验收证据完成”都外化成可恢复、可审计的临时执行标准，同时不恢复阶段式 gate。