create-agdf 0.14.5 → 0.20.1

package/generated/.opencode/skills/agdf-release-or/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agdf-release-or
-description: Use this skill at the end of every relevant run to produce a compact, auditable Orchestration Report. It summarizes gate status, delivered and intentionally not delivered work, TP coverage, Brownfield fit, solution integrity, open risks, and the next permissible step.
+description: "Use this skill for this scope: auditable closeout for every relevant run. Boundary: not a QA substitute. The requested effect, not discovery, decides AGDF activation."
 ---
 
 # release-or
@@ -26,16 +26,49 @@ It reports:
 - whether further quality follow-up or a separate delivery closeout is useful
 
 ## Runtime Contract
-Use these focused runtime-contract modules:
+Use `continuation.runtime_contracts` after `skill_continuation`. If absent: listed MCP `agdf_inspect` (`operation: contract`, `module: <name>`); else supplied schema-2 executable/argv_prefix[0] `contract --module <name>`; else bundled files below. MCP reads need no hook or shell. Missing module: stop; never infer/search for runtime.
 
 - `../../contracts/closeout.md`
 - `../../contracts/quality.md`
 - `../../contracts/context-graph.md`
 - `../../contracts/control-scaffold.md`
 
+`instruction_only`: first load `../../contracts/task-target-resolution.md` and `../../contracts/interaction.md`.
+
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:START -->
+## Request Activation
+
+- `owner`: `request_activation_contract`
+- `path`: `meta/contracts/request-activation.md`
+- `policy_version`: `1`
+- `guard_fingerprint`: `sha256:af2f01f9e18a3ba1c520faf0691aa1cd4a4299bdfa027cf83651c5d14319bfdc`
+
+Decide effect from loaded instructions before AGDF action.
+
+Abstain silently (no AGDF call) for assessment/explanation/comparison/recommendation/review/diagnosis/advice; hypothetical/example/error/code/quoted/negated delivery language; AGDF as subject; or a read-only constraint absent other delivery. Ambiguity is read-only: answer or ask one neutral question.
+
+Activate for any requested file/code change however small, a binding gate artefact, explicit AGDF/control-lifecycle operation or unambiguous active-run action; delivery wins mixed intent.
+
+Invocation proof: explicit user text/trusted ephemeral action, not discovery/selection, skill load, hooks, cwd, repo/control or prior runs.
+
+Then pick one catalog route; non-authorizing, downstream checks remain.
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:END -->
+
+## Executable Dispatch
+
+Use listed MCP `agdf_dispatch` (load deferred; host prefix allowed): `skill_id` `release-or`, `presentation_language`, `working_directory`, and only bound `target_source`/`primary_target` and `run_id`. Never search unlisted tools.
+If absent/failing: supplied schema-2 executable, child-only environment, immutable argv_prefix, declared arguments; `--skill release-or`, language and working directory.
+For `--language`: Required presentation language for the latest natural-language user request as one well-formed BCP 47 tag. If the request explicitly asks for a response language, use that tag; otherwise use the dominant request language. Use en when mixed or ambiguous. A valid unsupported tag renders through the complete English pack. Missing or invalid input fails before governance evaluation.
+`target_source`: `explicit_target` if request names `primary_target`; `continued_target` if it unambiguously continues confirmed target; `current_repository` if request names this/current repo with one matching repo active. Otherwise omit the pair; cwd has no target authority.
+Quote shell values as data.
+For a result with `terminal: true`, the entire assistant response must consist only of host_action.text, copied verbatim. Add no question, explanation, heading, citation, link or other surrounding text; do not translate or reformat it; invoke no later tool and stop.
+On skill_continuation use only its target/control. Without that tool and a valid binding: `dispatcher_unavailable`; no runtime search, environment repair
+or help retries. Dispatch never authorizes.
+
 OR-specific output must make gate status, delivered and intentionally not delivered content, missing approvals, missing evidence, risks, retained fallbacks, and the next permissible step visible.
 When `.agdf/control/` is present, persist or link the OR under `.agdf/control/artefacts/<key>/OR.md` and reference it from the selected canonical `RUN_STATE.md` or `MASTER_BACKLOG.md` when it is steering-relevant.
 Use the Runtime Contract definition of `Relevant Run` to decide whether OR is mandatory or whether a Quick Task mini-closeout is enough.
+Close a `quick_task` with the validator's `run-step --step closeout --result --evidence --risk --next`.
 
 ## Rules
 1. OR is always allowed and mandatory for relevant runs as defined in the Runtime Contract.
@@ -53,7 +86,7 @@ Use the Runtime Contract definition of `Relevant Run` to decide whether OR is ma
 13. Keep machine status normalization in the CLI; do not write internal snake_case status values into the human-facing backlog.
 14. Reconcile Context Graph impact before clean closeout: report `context_graph_reconciliation: resolved | not_applicable | open_gap`.
 15. If Context Graph work remains unresolved, report it as an explicit open gap and do not describe the run as cleanly handoff-ready.
-16. After writing or updating `MASTER_BACKLOG.md`, run `doctor --json` (or the locally available equivalent) and resolve any `AGDF_BACKLOG_STATUS_UNKNOWN` or `AGDF_BACKLOG_ARTEFACT_LABEL_UNKNOWN` finding before closeout. See the AGDF control scaffold's `MASTER_BACKLOG.md` template Rules section for the canonical status/artefact label vocabulary.
+16. After writing or updating `MASTER_BACKLOG.md`, run `agdf_inspect` with `operation: doctor` when the host lists it, otherwise `doctor --json` (or the locally available equivalent) and resolve any `AGDF_BACKLOG_STATUS_UNKNOWN` or `AGDF_BACKLOG_ARTEFACT_LABEL_UNKNOWN` finding before closeout. See the AGDF control scaffold's `MASTER_BACKLOG.md` template Rules section for the canonical status/artefact label vocabulary.
 17. When Delivery Map exposes `parent_reconciliation`, report that evaluated object without
     rediscovering or reclassifying the relationship. Keep Child completion and Parent coordination
     visibly separate. An `open` result retains exactly one next action and does not invalidate Child
@@ -66,7 +99,7 @@ Use the Runtime Contract definition of `Relevant Run` to decide whether OR is ma
 - after artefact creation
 - when a gate blocks
 - after `CD+Tests`
-- after `agdf-code-review`
+- after `code-review`
 - after QA
 - after UAT
 - whenever a compact audit closeout is needed
@@ -81,10 +114,10 @@ Use what is available:
 - artefacts created in this run
 - intentionally not delivered content
 - Task Plan
-- `agdf-task-plan-review`
-- `agdf-brownfield-analysis`
-- `agdf-clean-implementation-review`
-- `agdf-code-review`
+- `task-plan-review`
+- `brownfield-analysis`
+- `clean-implementation-review`
+- `code-review`
 - QA Report
 - UAT Report
 - documentation impact review
@@ -111,7 +144,7 @@ If information is missing, state the gap instead of guessing.
 11. Name retained fallbacks and exit criteria.
 12. Set exactly one next permissible step.
 13. Set exactly one quality outlook.
-14. State whether `agdf-delivery-closeout` is the next operational handoff step when code changes exist and the delivery state allows it.
+14. State whether `delivery-closeout` is the next operational handoff step when code changes exist and the delivery state allows it.
 
 ## Output
 Use a compact structure:
@@ -138,10 +171,10 @@ Include `context_graph_reconciliation` whenever Context Graph impact is present.
 ## Forbidden
 This skill must not:
 
-- decide QA in place of `agdf-qa-gate`
+- decide QA in place of `qa-gate`
 - call `CD+Tests` complete, QA-ready, or release-ready
 - hide missing approvals
 - provide later-gate content while an earlier gate blocks
-- produce the operative commit/PR handoff owned by `agdf-delivery-closeout`
+- produce the operative commit/PR handoff owned by `delivery-closeout`
 - execute commit, push, or PR actions
 - infer Parentage, scan sibling runs independently or mutate a Parent

package/generated/.opencode/skills/agdf-sd-definition/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: agdf-sd-definition
+description: "Use this skill for this scope: bound SD content. Boundary: content only; preserves approved intent. The requested effect, not discovery, decides AGDF activation."
+---
+
+# sd-definition
+
+## Runtime Contract
+
+Use the returned `continuation.runtime_contracts` after `skill_continuation`. If absent, load
+`../../contracts/sd-definition.md` and `../../contracts/gate-artifact-preparation.md`
+through the supplied contract reader or bundled files.
+Missing contract or invalid binding: stop. This skill owns SD content; gate-check owns readiness.
+
+`instruction_only`: first load `../../contracts/task-target-resolution.md` and `../../contracts/interaction.md`.
+
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:START -->
+## Request Activation
+
+- `owner`: `request_activation_contract`
+- `path`: `meta/contracts/request-activation.md`
+- `policy_version`: `1`
+- `guard_fingerprint`: `sha256:af2f01f9e18a3ba1c520faf0691aa1cd4a4299bdfa027cf83651c5d14319bfdc`
+
+Decide effect from loaded instructions before AGDF action.
+
+Abstain silently (no AGDF call) for assessment/explanation/comparison/recommendation/review/diagnosis/advice; hypothetical/example/error/code/quoted/negated delivery language; AGDF as subject; or a read-only constraint absent other delivery. Ambiguity is read-only: answer or ask one neutral question.
+
+Activate for any requested file/code change however small, a binding gate artefact, explicit AGDF/control-lifecycle operation or unambiguous active-run action; delivery wins mixed intent.
+
+Invocation proof: explicit user text/trusted ephemeral action, not discovery/selection, skill load, hooks, cwd, repo/control or prior runs.
+
+Then pick one catalog route; non-authorizing, downstream checks remain.
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:END -->
+
+## Executable Dispatch
+
+Use listed MCP `agdf_dispatch` (load deferred; host prefix allowed): `skill_id` `sd-definition`, `presentation_language`, `working_directory`, and only bound `target_source`/`primary_target` and `run_id`. Never search unlisted tools.
+If absent/failing: supplied schema-2 executable, child-only environment, immutable argv_prefix, declared arguments; `--skill sd-definition`, language and working directory.
+For `--language`: Required presentation language for the latest natural-language user request as one well-formed BCP 47 tag. If the request explicitly asks for a response language, use that tag; otherwise use the dominant request language. Use en when mixed or ambiguous. A valid unsupported tag renders through the complete English pack. Missing or invalid input fails before governance evaluation.
+`target_source`: `explicit_target` if request names `primary_target`; `continued_target` if it unambiguously continues confirmed target; `current_repository` if request names this/current repo with one matching repo active. Otherwise omit the pair; cwd has no target authority.
+Quote shell values as data.
+For a result with `terminal: true`, the entire assistant response must consist only of host_action.text, copied verbatim. Add no question, explanation, heading, citation, link or other surrounding text; do not translate or reformat it; invoke no later tool and stop.
+On skill_continuation use only its target/control. Without that tool and a valid binding: `dispatcher_unavailable`; no runtime search, environment repair
+or help retries. Dispatch never authorizes.
+
+## Workflow
+
+Follow the focused SD contract using the original request and answered conversation context.
+Write only the supplied unapproved SD from approved PRD and analyses, preserving uncertainty and explicit human approval.
+After canonical recording, redispatch gate-check; use its fresh presentation and wait.

package/generated/.opencode/skills/agdf-task-plan-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agdf-task-plan-review
-description: Use this skill after code changes and before QA to verify whether the approved Task Plan was actually fulfilled. It checks each task_id against implementation, acceptance criteria, tests, visible evidence, and deviations, and provides TP coverage for QA.
+description: "Use this skill for this scope: evidence dimension: verify whether the approved Task Plan was fulfilled. Boundary: supports Quality Readiness; no final QA decision. The requested effect, not discovery, decides AGDF activation."
 ---
 
 # task-plan-review
@@ -14,17 +14,49 @@ For each relevant task, this skill determines:
 - which acceptance criteria are done, partial, missing, or not verifiable
 - which files, tests, runtime evidence, or UI evidence support the finding
 - evidence strength
-- which gaps must be handed to `agdf-qa-gate`
+- which gaps must be handed to `qa-gate`
 
 This skill provides TP coverage. It is not the final QA decision.
 
 ## Runtime Contract
-Use these focused runtime-contract modules:
+Use `continuation.runtime_contracts` after `skill_continuation`. If absent: listed MCP `agdf_inspect` (`operation: contract`, `module: <name>`); else supplied schema-2 executable/argv_prefix[0] `contract --module <name>`; else bundled files below. MCP reads need no hook or shell. Missing module: stop; never infer/search for runtime.
 
 - `../../contracts/quality.md`
 - `../../contracts/context-graph.md`
 - `../../contracts/gate-transition.md`
 
+`instruction_only`: first load `../../contracts/task-target-resolution.md` and `../../contracts/interaction.md`.
+
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:START -->
+## Request Activation
+
+- `owner`: `request_activation_contract`
+- `path`: `meta/contracts/request-activation.md`
+- `policy_version`: `1`
+- `guard_fingerprint`: `sha256:af2f01f9e18a3ba1c520faf0691aa1cd4a4299bdfa027cf83651c5d14319bfdc`
+
+Decide effect from loaded instructions before AGDF action.
+
+Abstain silently (no AGDF call) for assessment/explanation/comparison/recommendation/review/diagnosis/advice; hypothetical/example/error/code/quoted/negated delivery language; AGDF as subject; or a read-only constraint absent other delivery. Ambiguity is read-only: answer or ask one neutral question.
+
+Activate for any requested file/code change however small, a binding gate artefact, explicit AGDF/control-lifecycle operation or unambiguous active-run action; delivery wins mixed intent.
+
+Invocation proof: explicit user text/trusted ephemeral action, not discovery/selection, skill load, hooks, cwd, repo/control or prior runs.
+
+Then pick one catalog route; non-authorizing, downstream checks remain.
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:END -->
+
+## Executable Dispatch
+
+Use listed MCP `agdf_dispatch` (load deferred; host prefix allowed): `skill_id` `task-plan-review`, `presentation_language`, `working_directory`, and only bound `target_source`/`primary_target` and `run_id`. Never search unlisted tools.
+If absent/failing: supplied schema-2 executable, child-only environment, immutable argv_prefix, declared arguments; `--skill task-plan-review`, language and working directory.
+For `--language`: Required presentation language for the latest natural-language user request as one well-formed BCP 47 tag. If the request explicitly asks for a response language, use that tag; otherwise use the dominant request language. Use en when mixed or ambiguous. A valid unsupported tag renders through the complete English pack. Missing or invalid input fails before governance evaluation.
+`target_source`: `explicit_target` if request names `primary_target`; `continued_target` if it unambiguously continues confirmed target; `current_repository` if request names this/current repo with one matching repo active. Otherwise omit the pair; cwd has no target authority.
+Quote shell values as data.
+For a result with `terminal: true`, the entire assistant response must consist only of host_action.text, copied verbatim. Add no question, explanation, heading, citation, link or other surrounding text; do not translate or reformat it; invoke no later tool and stop.
+On skill_continuation use only its target/control. Without that tool and a valid binding: `dispatcher_unavailable`; no runtime search, environment repair
+or help retries. Dispatch never authorizes.
+
 TP-specific output must evaluate every relevant `task_id` with completion status, AC coverage, evidence, missing evidence, and QA-relevant gaps.
 If `context_graph_required_action` is not `none`, the affected task is complete only if follow-up, evidence, or an intentionally open gap is visible.
 Applicable review gaps must use `../../contracts/quality.md` §Normalized Review Gaps. This skill

package/generated/.opencode/skills/agdf-tp-definition/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: agdf-tp-definition
+description: "Use this skill for this scope: bound TP content. Boundary: content only; preserves approved sources. The requested effect, not discovery, decides AGDF activation."
+---
+
+# tp-definition
+
+## Runtime Contract
+
+Use the returned `continuation.runtime_contracts` after `skill_continuation`. If absent, load
+`../../contracts/tp-definition.md` and `../../contracts/gate-artifact-preparation.md`
+through the supplied contract reader or bundled files.
+Missing contract or invalid binding: stop. This skill owns TP content; gate-check owns readiness.
+
+`instruction_only`: first load `../../contracts/task-target-resolution.md` and `../../contracts/interaction.md`.
+
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:START -->
+## Request Activation
+
+- `owner`: `request_activation_contract`
+- `path`: `meta/contracts/request-activation.md`
+- `policy_version`: `1`
+- `guard_fingerprint`: `sha256:af2f01f9e18a3ba1c520faf0691aa1cd4a4299bdfa027cf83651c5d14319bfdc`
+
+Decide effect from loaded instructions before AGDF action.
+
+Abstain silently (no AGDF call) for assessment/explanation/comparison/recommendation/review/diagnosis/advice; hypothetical/example/error/code/quoted/negated delivery language; AGDF as subject; or a read-only constraint absent other delivery. Ambiguity is read-only: answer or ask one neutral question.
+
+Activate for any requested file/code change however small, a binding gate artefact, explicit AGDF/control-lifecycle operation or unambiguous active-run action; delivery wins mixed intent.
+
+Invocation proof: explicit user text/trusted ephemeral action, not discovery/selection, skill load, hooks, cwd, repo/control or prior runs.
+
+Then pick one catalog route; non-authorizing, downstream checks remain.
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:END -->
+
+## Executable Dispatch
+
+Use listed MCP `agdf_dispatch` (load deferred; host prefix allowed): `skill_id` `tp-definition`, `presentation_language`, `working_directory`, and only bound `target_source`/`primary_target` and `run_id`. Never search unlisted tools.
+If absent/failing: supplied schema-2 executable, child-only environment, immutable argv_prefix, declared arguments; `--skill tp-definition`, language and working directory.
+For `--language`: Required presentation language for the latest natural-language user request as one well-formed BCP 47 tag. If the request explicitly asks for a response language, use that tag; otherwise use the dominant request language. Use en when mixed or ambiguous. A valid unsupported tag renders through the complete English pack. Missing or invalid input fails before governance evaluation.
+`target_source`: `explicit_target` if request names `primary_target`; `continued_target` if it unambiguously continues confirmed target; `current_repository` if request names this/current repo with one matching repo active. Otherwise omit the pair; cwd has no target authority.
+Quote shell values as data.
+For a result with `terminal: true`, the entire assistant response must consist only of host_action.text, copied verbatim. Add no question, explanation, heading, citation, link or other surrounding text; do not translate or reformat it; invoke no later tool and stop.
+On skill_continuation use only its target/control. Without that tool and a valid binding: `dispatcher_unavailable`; no runtime search, environment repair
+or help retries. Dispatch never authorizes.
+
+## Workflow
+
+Follow the focused TP contract using the original request and answered conversation context.
+Write only the supplied unapproved TP from approved PRD/SD and analyses, preserving uncertainty and explicit human approval.
+After canonical recording, redispatch gate-check; use its fresh presentation and wait.

package/generated/.opencode/skills/agdf-ur-definition/SKILL.md

@@ -0,0 +1,54 @@
+---
+name: agdf-ur-definition
+description: "Use this skill for this scope: bound UR drafting, clarification or revision. Boundary: content only; preserves approved intent. The requested effect, not discovery, decides AGDF activation."
+---
+
+# ur-definition
+
+## Runtime Contract
+
+Use the returned `continuation.runtime_contracts` after `skill_continuation`. If absent, load
+`../../contracts/ur-definition.md` through the supplied contract reader or bundled file.
+Missing contract or invalid binding: stop. This skill owns UR content; gate-check owns readiness.
+
+`instruction_only`: first load `../../contracts/task-target-resolution.md` and `../../contracts/interaction.md`.
+
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:START -->
+## Request Activation
+
+- `owner`: `request_activation_contract`
+- `path`: `meta/contracts/request-activation.md`
+- `policy_version`: `1`
+- `guard_fingerprint`: `sha256:af2f01f9e18a3ba1c520faf0691aa1cd4a4299bdfa027cf83651c5d14319bfdc`
+
+Decide effect from loaded instructions before AGDF action.
+
+Abstain silently (no AGDF call) for assessment/explanation/comparison/recommendation/review/diagnosis/advice; hypothetical/example/error/code/quoted/negated delivery language; AGDF as subject; or a read-only constraint absent other delivery. Ambiguity is read-only: answer or ask one neutral question.
+
+Activate for any requested file/code change however small, a binding gate artefact, explicit AGDF/control-lifecycle operation or unambiguous active-run action; delivery wins mixed intent.
+
+Invocation proof: explicit user text/trusted ephemeral action, not discovery/selection, skill load, hooks, cwd, repo/control or prior runs.
+
+Then pick one catalog route; non-authorizing, downstream checks remain.
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:END -->
+
+## Executable Dispatch
+
+Use listed MCP `agdf_dispatch` (load deferred; host prefix allowed): `skill_id` `ur-definition`, `presentation_language`, `working_directory`, and only bound `target_source`/`primary_target` and `run_id`. Never search unlisted tools.
+If absent/failing: supplied schema-2 executable, child-only environment, immutable argv_prefix, declared arguments; `--skill ur-definition`, language and working directory.
+For `--language`: Required presentation language for the latest natural-language user request as one well-formed BCP 47 tag. If the request explicitly asks for a response language, use that tag; otherwise use the dominant request language. Use en when mixed or ambiguous. A valid unsupported tag renders through the complete English pack. Missing or invalid input fails before governance evaluation.
+`target_source`: `explicit_target` if request names `primary_target`; `continued_target` if it unambiguously continues confirmed target; `current_repository` if request names this/current repo with one matching repo active. Otherwise omit the pair; cwd has no target authority.
+Quote shell values as data.
+For a result with `terminal: true`, the entire assistant response must consist only of host_action.text, copied verbatim. Add no question, explanation, heading, citation, link or other surrounding text; do not translate or reformat it; invoke no later tool and stop.
+On skill_continuation use only its target/control. Without that tool and a valid binding: `dispatcher_unavailable`; no runtime search, environment repair
+or help retries. Dispatch never authorizes.
+
+## Workflow
+
+Follow the focused UR contract using the original request and answered conversation context.
+Preserve explicitly requested previews and other clarification deliverables, their purpose and
+review timing in the UR; creation belongs to the later bound analytical step.
+Set the initial `Preview requirement` metadata according to the UR contract; a required
+interactive before-PRD preview uses `before_prd_interactive`, otherwise `none`.
+Write only the supplied unapproved UR, preserving uncertainty and explicit human approval.
+After canonical recording, redispatch gate-check; use its fresh presentation and wait.

package/generated/.opencode/skills/agdf-ux-intent-definition/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agdf-ux-intent-definition
-description: Use this skill after approved UR and post-UR routing when UI/UX impact is medium or high, or low with ambiguous product semantics, to define user intent, success, working modes, effective state, visible state ownership, activation, blockers, recovery and transitions as structured PRD input; fail closed when evidence or product decisions are unresolved. This internal analysis never grants gate permission or replaces the approved PRD.
+description: "Use this skill for this scope: approved UR with routed medium/high UX impact or ambiguous low-impact semantics before PRD. Boundary: analytical PRD input only; no intent, gate, design or parallel product authority. The requested effect, not discovery, decides AGDF activation."
 ---
 
 # ux-intent-definition
@@ -12,11 +12,43 @@ approved product promise instead of inventing requirements after code exists.
 
 ## Runtime Contract
 
-Use:
+Use `continuation.runtime_contracts` after `skill_continuation`. If absent: listed MCP `agdf_inspect` (`operation: contract`, `module: <name>`); else supplied schema-2 executable/argv_prefix[0] `contract --module <name>`; else bundled files below. MCP reads need no hook or shell. Missing module: stop; never infer/search for runtime.
 
 - `../../contracts/gate-transition.md` for impact routing, authority and revision behavior;
 - `../../contracts/quality.md` for evidence and fail-closed output discipline.
 
+`instruction_only`: first load `../../contracts/task-target-resolution.md` and `../../contracts/interaction.md`.
+
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:START -->
+## Request Activation
+
+- `owner`: `request_activation_contract`
+- `path`: `meta/contracts/request-activation.md`
+- `policy_version`: `1`
+- `guard_fingerprint`: `sha256:af2f01f9e18a3ba1c520faf0691aa1cd4a4299bdfa027cf83651c5d14319bfdc`
+
+Decide effect from loaded instructions before AGDF action.
+
+Abstain silently (no AGDF call) for assessment/explanation/comparison/recommendation/review/diagnosis/advice; hypothetical/example/error/code/quoted/negated delivery language; AGDF as subject; or a read-only constraint absent other delivery. Ambiguity is read-only: answer or ask one neutral question.
+
+Activate for any requested file/code change however small, a binding gate artefact, explicit AGDF/control-lifecycle operation or unambiguous active-run action; delivery wins mixed intent.
+
+Invocation proof: explicit user text/trusted ephemeral action, not discovery/selection, skill load, hooks, cwd, repo/control or prior runs.
+
+Then pick one catalog route; non-authorizing, downstream checks remain.
+<!-- AGDF-REQUEST-ACTIVATION-GUARD:END -->
+
+## Executable Dispatch
+
+Use listed MCP `agdf_dispatch` (load deferred; host prefix allowed): `skill_id` `ux-intent-definition`, `presentation_language`, `working_directory`, and only bound `target_source`/`primary_target` and `run_id`. Never search unlisted tools.
+If absent/failing: supplied schema-2 executable, child-only environment, immutable argv_prefix, declared arguments; `--skill ux-intent-definition`, language and working directory.
+For `--language`: Required presentation language for the latest natural-language user request as one well-formed BCP 47 tag. If the request explicitly asks for a response language, use that tag; otherwise use the dominant request language. Use en when mixed or ambiguous. A valid unsupported tag renders through the complete English pack. Missing or invalid input fails before governance evaluation.
+`target_source`: `explicit_target` if request names `primary_target`; `continued_target` if it unambiguously continues confirmed target; `current_repository` if request names this/current repo with one matching repo active. Otherwise omit the pair; cwd has no target authority.
+Quote shell values as data.
+For a result with `terminal: true`, the entire assistant response must consist only of host_action.text, copied verbatim. Add no question, explanation, heading, citation, link or other surrounding text; do not translate or reformat it; invoke no later tool and stop.
+On skill_continuation use only its target/control. Without that tool and a valid binding: `dispatcher_unavailable`; no runtime search, environment repair
+or help retries. Dispatch never authorizes.
+
 ## Authority
 
 This is an internal analytical skill, not a user gate. It cannot approve artefacts, grant
@@ -27,6 +59,7 @@ and approved as PRD content. Technical storage, derivation and component ownersh
 ## Inputs
 
 - approved UR and its intent, success signal, primary action and persona/context;
+- requested clarification deliverables, preview scenarios, interaction needs and timing in UR scope;
 - post-UR `delivery_context`, `ui_ux_impact`, reason and required flag;
 - existing behavior/ownership evidence for Brownfield work;
 - known working modes, state semantics, activation, blockers, recovery and transitions.
@@ -40,14 +73,73 @@ and approved as PRD content. Technical storage, derivation and component ownersh
    `primary_state_presentation_owner_by_mode`; do not turn either into technical ownership.
 5. Define activation/deactivation, blockers with visible next actions, actionable recovery (including
    visible retry for recoverable transient failure) and relevant state transitions.
-6. Propose observable PRD acceptance criteria and identify open product questions.
+6. Use UI previews as described below when seeing or trying the proposed behavior materially helps
+   resolve a product question. Propose observable PRD acceptance criteria and identify open questions.
 7. Return exactly one decision: `ready | blocked | not_applicable`.
 
+### UI previews for clarification
+
+Use a focused preview during UX intent clarification and reuse its findings during PRD alignment.
+Start with the user's task and unresolved decision, not a decorative dashboard. Show the relevant
+starting state, primary action, visible outcome and, where relevant, a blocker or recovery path.
+For example: can the user find what was checked, identify an open risk and decide whether to approve?
+Match known product context; identify illustrative data and unconfirmed assumptions explicitly.
+
+First preserve any preview explicitly required by approved UR scope, including its interaction,
+format and timing. Use an available visualization capability such as `visualize` when suitable.
+For an optional aid, a wireframe or written scenario walkthrough may answer the same question.
+For an explicitly requested interactive preview, unavailable tooling requires concrete recovery or
+an explicit scope revision; do not silently downgrade it or report the obligation fulfilled.
+Do not invent a preview requirement for already clear semantics, add a gate or install a dependency.
+Keep prototype interactions local; they cannot submit real approvals, modify delivery state or start
+implementation. A requested change to the actual product still follows its existing delivery path.
+
+#### Retain a run-bound preview
+
+For a preview used in this bound analysis, save a durable, reopenable copy under
+`.agdf/control/artefacts/<run_id>/previews/<short-name>-v<N>/index.html`, relative to the supplied
+governance target. Derive the run from the valid assignment, not cwd, recency or another run.
+Resolve containment and reject symlink escapes before writing; never put preview content in
+`runs/<run_id>/RUN_STATE.md`. Use a new unused version for revisions and preserve reviewed versions.
+Store a standalone document, preferably self-contained; bundle any local assets with relative
+references. For an inline visualization, keep its editable source in the host's permitted location
+and export a standalone copy to the run directory using that capability's supported flow. Remove
+host-only dependencies from the durable copy. Reopen it from its saved location and exercise the
+relevant interaction before claiming portability; an export or screenshot alone is insufficient.
+For required interactive PRD review, make that durable copy offline with local classic scripts,
+styles and images, without modules, remote resources or host calls. The PRD author owns the
+`Preview Review` descriptor and final criterion mapping; UX supplies the exact files and findings.
+
+Record the target run, source UR revision/digest, preview version, relative entry path, SHA-256 of
+the saved file (and local assets), covered scenarios and actual validation limits in the existing
+analysis `evidence` field. Keep observations tied to that version; a changed preview needs fresh
+inspection and affected user feedback. The UX report and PRD link the same evidence, not divergent
+copies. Use existing canonical recording/revision owners for their updates; preview bytes are
+supporting evidence, not a new approval authority or an automatically sealed artefact type.
+An unbound conversation preview remains advisory; do not create or select a run just to attach it.
+
+For PRD alignment, hand off a concise user review task, the readable versioned preview reference,
+covered scenarios and proposed criterion IDs alongside the observations. The existing presentation
+owner uses this material under interaction.md PRD Preview Review At Approval. Distinguish the
+proposed experience from delivered functionality and record any unavailable review access explicitly.
+
+Walk through the concrete task with the user and record observed behavior, feedback, unresolved
+assumptions and resulting proposed criteria in the existing `evidence`, `open_product_questions`
+and `proposed_prd_acceptance_criteria` fields. Distinguish agent inspection from user observation;
+check rendering and the relevant interaction before claiming they work. If no inspection or user
+observation occurred, say so. Retain the scenario and findings as well as the durable preview
+reference; chat-only or missing preview evidence cannot fulfill an explicit preview requirement.
+Preview feedback is analytical
+input, not PRD approval, implementation evidence or host qualification. Layout and component choices
+remain illustrative; only explicitly adopted product behavior becomes approved PRD content.
+
 ## Decision Rules
 
-- `ready`: every required output is reliable enough for PRD drafting.
+- `ready`: every required output is reliable enough for PRD drafting, including a requested preview
+  at the agreed fidelity, its durable evidence and resolution of material product questions.
 - `blocked`: user intent, modes, effective state, authority, activation, blockers, recovery, transitions
-  or Brownfield evidence is missing, contradictory or materially ambiguous.
+  or Brownfield evidence is missing, contradictory or materially ambiguous; or an explicitly required
+  preview, requested interaction, durable copy or decision-relevant observation remains missing.
 - `not_applicable`: routing proves that no relevant user-facing intent, state or recovery behavior changes.
 
 A conflict with approved UR routes to UR revision. A material product change discovered after PRD
@@ -83,7 +175,7 @@ Populate each field or use an explicit, justified `not_applicable`:
 
 For `blocked`, `blocking_reason`, `open_product_questions`, `affected_outputs`, `evidence`,
 `missing_evidence` and `required_next_step` are mandatory. When durable control state exists, write
-the result to `.agdf/control/artefacts/<key>/UX_INTENT_DEFINITION.md` without a Gate or approval field.
+the result to `.agdf/control/artefacts/<run_id>/UX_INTENT_DEFINITION.md` without a Gate or approval field.
 
 ## Forbidden
 
@@ -92,3 +184,5 @@ the result to `.agdf/control/artefacts/<key>/UX_INTENT_DEFINITION.md` without a
 - add a gate, approval value or implementation permission;
 - prescribe components, persistence, endpoints, styles or other technical design;
 - treat supporting analysis as authoritative beside the approved PRD.
+
+Apply interaction.md Bounded internal recovery and prepared observation for eligible bound follow-up. It adds no gate or approval authority.

package/generated/plugins/agdf/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agdf",
-  "version": "0.14.5",
+  "version": "0.20.1",
   "description": "AI Governance & Delivery Framework (AGDF) is a governance framework for agentic work. Its first implementation provides a control layer for governed AI-assisted software delivery. It combines workflow skills, explicit gates, control templates and machine-readable repository checks to keep work aligned with approved scope and make evidence a prerequisite for consequential gate transitions. Supported workflows include brownfield analysis, task-plan review, QA decisions, durable run state and auditable delivery closeout. AGDF is an independent open-source project, not a security sandbox, compliance certification or autonomous release system.",
   "keywords": [
     "agentic",
@@ -15,5 +15,6 @@
   "author": {
     "name": "Arndt Gold",
     "url": "https://agdf.iself.eu"
-  }
+  },
+  "mcpServers": "./mcp/claude.mcp.json"
 }

package/generated/plugins/agdf/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agdf",
-  "version": "0.14.5",
+  "version": "0.20.1",
   "description": "Control layer for governed AI-assisted delivery.",
   "author": {
     "name": "Arndt Gold",
@@ -17,6 +17,8 @@
     "brownfield"
   ],
   "skills": "./skills/",
+  "hooks": "./hooks/hooks.json",
+  "mcpServers": "./mcp.json",
   "interface": {
     "displayName": "AI Governance & Delivery Framework",
     "shortDescription": "Control layer for governed AI-assisted delivery.",

package/generated/plugins/agdf/control/README.md

@@ -77,10 +77,28 @@ agdf gate-check --json
 ## Operating Rules
 
 - Canonical mutable state is isolated per run at `runs/<run_id>/RUN_STATE.md`. Run discovery is
-  derived; do not maintain a writable active-run index. Select explicitly with `--run` or
-  `AGDF_RUN_ID` when more than one run is active.
+  derived; do not maintain a writable active-run index. When several runs are active, discovery
+  presents the most recently updated run first and lists the others, but requires an explicit run
+  selection for read-only status or explicit run-selection requests. Implementation intake first
+  provides canonical UR evidence to the coding agent for scope assignment, even with one active
+  run: resume one same-scope continuation, start a new UR run for an independent scope, or clarify
+  genuinely overlapping work. If no active run exists during a status request, ask whether to start
+  one or do something else. Status never creates a run. `updated_at` is recorded with
+  every canonical run write; older runs use file modification time until their next recorded update.
 - Migrate legacy state explicitly with `run-migrate`; read-only commands never migrate. A retained
   `AGDF_RUN.md` is migration input or a non-authoritative projection, not a second writable owner.
+- A run created by `run-create` is sealed. Record every change to it or to a listed artefact with
+  `run-update`, and record exact gate replies only with `run-approve`; an unrecorded edit blocks
+  `doctor` and `gate-check` until it is recorded.
+  If a run lists its own `RUN_STATE.md`, the seal covers its body directly and uses a self-reference
+  marker for that artefact entry. This avoids circular on-disk hashing; references to other runs
+  remain fully hashed. Old self-reference failures require a verified restoration, never a blind re-seal.
+- Record the standard small-path steps with one `run-step` call each instead of editing the run state
+  and `MASTER_BACKLOG.md` by hand: `--step ur --title` after writing `artefacts/<run_id>/UR.md`;
+  `--step route --route <mode> --reason --evidence` after writing `BROWNFIELD_REVIEW.md`;
+  `--step evidence` for test or check results; `--step review --decision --evidence` for Code Review;
+  and `--step closeout --result --evidence --risk --next` to close a `quick_task` with OR-lite. Each
+  call maintains the tables, the backlog pointer and the next allowed action and prints the next step.
 
 - The selected `runs/<run_id>/RUN_STATE.md` is the current run dashboard.
 - `config.json` stores the project preference for artefact and chat language; runtime rules stay English.
@@ -96,3 +114,12 @@ agdf gate-check --json
   merge or pull, rerun `doctor` and `gate-check` for the selected run.
 
 Do not duplicate full product documentation in this scaffold. Link to the authoritative artefact instead.
+
+## Planned outputs during recovery
+
+A missing file explicitly declared `missing` or `pending` under the selected run's own
+`.agdf/control/artefacts/<run_id>/` directory is a planned output, not lost completed evidence.
+Recovery retains its path and absence in the integrity snapshot and leaves its status pending.
+It does not create evidence or approve a gate. Completed or ready evidence, unsafe paths and
+descriptive placeholders still require repair. Creating a planned file after a recovery preview
+invalidates that preview; creating it after recovery changes the seal until a canonical update.

package/generated/plugins/agdf/control/templates/MASTER_BACKLOG.md

@@ -15,12 +15,14 @@ This file is the living control pointer for active AGDF delivery work. Detailed
 9. Historical artefacts remain linkable but do not override the current pointer.
 10. If an item is superseded, mark the replacement.
 11. If active work grows beyond roughly ten items, triage the backlog.
-12. `Status` must be one of the human-readable labels normalized by `create-agdf/lib/control-evaluation/shared.js`: Needs UR, Awaiting Brownfield Review, Awaiting PRD, Awaiting PRD Approval, Awaiting SD, Awaiting SD Approval, Awaiting TP, Awaiting TP Approval, In Progress, Blocked, Awaiting QA, Awaiting UAT, Awaiting OR, Completed, Superseded, Abandoned. The parser module is authoritative; this list only mirrors it for readability.
+12. `Status` must be one of the human-readable labels normalized by `packages/core/lib/control-evaluation/shared.js`: Needs UR, Awaiting Brownfield Review, Awaiting PRD, Awaiting PRD Approval, Awaiting SD, Awaiting SD Approval, Awaiting TP, Awaiting TP Approval, In Progress, Blocked, Awaiting QA, Awaiting UAT, Awaiting OR, Completed, Superseded, Abandoned. Generated observations also use Work pending, Approval pending, QA report pending, QA evidence open, QA correction open, QA source decision required, QA blocked, Source unconfirmed, Closeout pending, Unconfirmed, and phase-specific Brownfield Analysis/CD+Tests/CR/Quick Task Execution/Verified Change Execution/Mode/Slice Decision work pending. The parser module is authoritative; this list only mirrors it for readability.
 13. `Artefacts` link labels must be one of the labels normalized by the same parser module: `ur`, `brownfield`, `prd`, `sd`, `tp`, `qa`, `or` (case-insensitive). Do not invent other labels such as a raw artefact filename.
 14. After writing or updating this file, run `doctor --json` (or the locally available equivalent) and resolve any `AGDF_BACKLOG_STATUS_UNKNOWN` or `AGDF_BACKLOG_ARTEFACT_LABEL_UNKNOWN` finding before treating the edit as done.
-15. A `Work item` cell may optionally start with a bracketed scope tag, one of `[framework-maintenance]` or `[external-delivery]`, so the split between AGDF's own maintenance work and external product delivery stays visible at a glance. The tag is never required retroactively on `Completed / Superseded Pointers` rows. `create-agdf/lib/control-evaluation/shared.js` is authoritative for the accepted values.
+15. A `Work item` cell may optionally start with a bracketed scope tag, one of `[framework-maintenance]` or `[external-delivery]`, so the split between AGDF's own maintenance work and external product delivery stays visible at a glance. The tag is never required retroactively on `Completed / Superseded Pointers` rows. `packages/core/lib/control-evaluation/shared.js` is authoritative for the accepted values.
 16. After writing or updating this file, also resolve any `AGDF_BACKLOG_SCOPE_LABEL_UNKNOWN` finding, which fires only for a present-but-unrecognized bracketed tag, never for an absent one.
 
+17. Core writers may place a bounded `agdf-backlog-summary-v1` comment after a complete table, separated by a blank line. It records the addressed row, target, actual Run revision, observation time and consumed source digests; it never authorizes. Preserve it with its row. Older rows remain readable without it. Invalid/foreign/ambiguous observations remain visibly unconfirmed; reading does not synchronize or scan all Runs.
+
 ## Active Backlog
 
 | Priority | Key | Work item | Status | Artefacts | Current spec | Next step |

package/generated/plugins/agdf/control/templates/RUN_STATE.md

@@ -7,6 +7,7 @@
 - lifecycle: active
 - revision: 1
 - revision_id:
+- updated_at:
 - mode: structured_delivery
 - current_gate: UR
 - decision: in_progress