@danmoisan/drm-copilot-mcp 1.1.6 → 1.1.8

package/resources/claude-customizations/.claude/skills/epic-orchestrate/SKILL.md

@@ -292,10 +292,10 @@ Every field needed to re-derive state durably on resume (`worktree_path`, `branc
 and `gh pr view --json state,mergedAt,headRefOid` — the checkpoint is a cache of that durable
 state, not the source of truth.
 
-Validate the checkpoint via
-`python -m scripts.dev_tools.validate_orchestration_artifacts epic-orchestrator-state <path> --require-complete`
-(or the equivalent `mcp__drm-copilot__validate_orchestration_artifacts` call with
-`artifact_type: "epic-orchestrator-state"`), implemented in
+Validate the checkpoint through the
+`mcp__drm-copilot__validate_orchestration_artifacts` call with
+`artifact_type: "epic-orchestrator-state"`, supplying the `require_complete` argument on
+that same call at the completion gate. The validation is implemented in
 `scripts/dev_tools/validate_epic_orchestrator_state.py`.
 
 ## Completion Requirements

package/resources/claude-customizations/.claude/skills/fill-feature-docs/SKILL.md

@@ -12,6 +12,8 @@ This direct-use wrapper delegates feature-document work to the `prd-feature` wor
 - Feature folder issue and research context
 - Existing spec and user-story files when present
 
+For a numeric `spec.md` acceptance criterion, the research context must contain complete `## Numeric Derivation Evidence` with `Complete Family`, `Exhaustive Search Scope`, `Inclusion Rules`, `Exclusion Rules`, `Primary Search Strategy or Query Expression`, `Primary Member Set`, `Primary Count`, `Cross-check Search Strategy or Query Expression`, `Cross-check Member Set`, `Cross-check Count`, and `Member-set Comparison`. The two derivations must be non-empty, independently constructed, distinct in strategy or query expression, exhaustive across the complete family, independently enumerated, and explicitly compared. The worker must withhold a numeric assertion for missing, copied, incomplete, non-exhaustive, narrow, or disagreeing evidence; a single grep, a named-pattern-only query, matching totals, distinct query text, or equal member sets alone does not approve a number.
+
 ## Output Paths
 
 - `docs/features/active/<feature>/spec.md`
@@ -20,3 +22,4 @@ This direct-use wrapper delegates feature-document work to the `prd-feature` wor
 ## Worker Routing
 
 - Worker: `prd-feature`
+- Require the worker to report the authoritative `research-path` when a numeric acceptance criterion is written.

package/resources/claude-customizations/.claude/skills/parallel-add/SKILL.md

@@ -21,6 +21,8 @@ this operation may and may not disturb. Read that section before applying anythi
 
 ## Prerequisites
 
+- Reject a pending or not-started run with guidance to consolidate the initial set through `/parallel-plan`. Admit exactly one item only after execution has started in an open run; closed runs are not eligible.
+
 - A parallel run is in progress and `artifacts/orchestration/parallel-orchestrator-state.json`
   tracks its `parallel_slug`. This skill does not start a run; use `/parallel-plan` and
   `/parallel-run` for that.
@@ -59,15 +61,18 @@ re-derivation is mandatory and is not an optimization to skip when the checkpoin
 3. **Compute conflict edges over ALL items, including in-flight ones.** Invoke the contention
    relation `Test-BlastRadiusConflict` from the destination-runtime PowerShell port
    `.claude/lib/blast-radius/BlastRadius.psm1`, which is published by push-down and needs no Python
-   interpreter (`Import-Module .claude/lib/blast-radius/BlastRadius.psm1 -Force`). Its two radius
-   arguments are the two items' radius hashtables, not strings, and the third argument is the
-   required parsed `config/blast-radius.json` mapping, which push-down publishes into the
-   destination workspace. `conflicts(a, b, config)` in `scripts/dev_tools/compute_blast_radius.py`
-   (defined in `scripts/dev_tools/_blast_radius_conflicts.py`) remains the repository authority and
-   the parity reference. Read the verdict from the conflict key of the returned hashtable.
-   The hashtable itself is always truthy, so a bare boolean test on the result treats every pair as
-   conflicting. Map each conflicting pair onto an `(int, int)` conflict edge
-   of `items[].issue_num` values, normalized so `a < b`. Do not reimplement the relation and do not
+   interpreter (the default PowerShell 5.1 execution policy blocks `Import-Module` of a `.psm1`
+   file, so `pwsh` is mandatory: run as `$repoRoot = git rev-parse --show-toplevel; Import-Module
+   (Join-Path $repoRoot '.claude/lib/blast-radius/BlastRadius.psm1') -Force -ErrorAction Stop`).
+   Its two radius arguments are the two items' radius hashtables, not strings, and the third
+   argument is the required parsed `config/blast-radius.json` mapping, which push-down publishes
+   into the destination workspace. `conflicts(a, b, config)` in
+   `scripts/dev_tools/compute_blast_radius.py` (defined in
+   `scripts/dev_tools/_blast_radius_conflicts.py`) remains the repository authority and the parity
+   reference. Read the verdict from `$result['conflict']`; do not test the returned hashtable
+   itself, since it is always truthy under PowerShell boolean coercion, so a bare `if ($result)`
+   check treats every pair as conflicting. Map each conflicting pair onto an `(int, int)` conflict
+   edge of `items[].issue_num` values, normalized so `a < b`. Do not reimplement the relation and do not
    compute edges over the unstarted subset only: an in-flight conflict is precisely what the
    admission decision turns on.
 

package/resources/claude-customizations/.claude/skills/parallel-orchestrate/SKILL.md

@@ -478,9 +478,9 @@ pull-request state, merge time, and merge commit. Where the checkpoint disagrees
 commands, the commands win and the checkpoint is rewritten from them.
 
 Validate through `mcp__drm-copilot__validate_orchestration_artifacts` with
-`artifact_type: "parallel-orchestrator-state"`, or the equivalent CLI invocation
-`poetry run python -m scripts.dev_tools.validate_orchestration_artifacts parallel-orchestrator-state <path>`,
-adding `--require-complete` at the completion gate.
+`artifact_type: "parallel-orchestrator-state"`. At the completion gate, pass the
+`require_complete` argument on that same MCP call; no repository-local Python
+interpreter is required at a destination runtime.
 
 ## Completion Requirements
 

package/resources/claude-customizations/.claude/skills/parallel-plan/SKILL.md

@@ -32,6 +32,8 @@ Before proceeding, `parallel-planner` must:
 
 ## Item Intake
 
+Initial intake must provide the complete item set in one `/parallel-plan <slug> <item> [<item> ...]` invocation before waves are calculated. `/parallel-add` is not an initial-intake path.
+
 Invocation shape: `/parallel-plan <slug> <item> [<item> ...]`, where each `<item>` is either a
 GitHub issue number (already-promoted work) or a potential-entry path (unpromoted work). This is
 the same intake domain as `/parallel-add`, so initial intake here and F6's add operation accept
@@ -180,9 +182,13 @@ PowerShell port** under `.claude/lib/blast-radius/`, which is published by push-
 Python interpreter:
 
 ```powershell
-Import-Module .claude/lib/blast-radius/BlastRadius.psm1 -Force
+$repoRoot = git rev-parse --show-toplevel
+Import-Module (Join-Path $repoRoot '.claude/lib/blast-radius/BlastRadius.psm1') -Force -ErrorAction Stop
 ```
 
+The default PowerShell 5.1 execution policy blocks `Import-Module` of a `.psm1` file, so `pwsh` is
+mandatory here.
+
 The facade re-exports the five functions this skill needs: `Get-PlanPaths` (port of
 `extract_plan_paths`), `Get-BlastRadius` (port of `derive_blast_radius`),
 `Get-BlastRadiusFromObservedPaths` (port of `radius_from_observed_paths`), `Test-BlastRadius`
@@ -312,8 +318,9 @@ The library returns the partition; the planner supplies the record fields.
    emptiness is falsy, while this one returns a hashtable whose emptiness is not expressible at all.
 2. Immediately after the conflict-edge set is derived and before anything consumes it, run the
    lane-assertion diagnostic:
-   `poetry run python -m scripts.dev_tools.parallel_lane_assertion --manifest docs/features/parallel/<slug>/parallel.md --edges "<a>:<b> ..."`
-   (covered by the planner's existing `Bash(poetry run *)` grant). It compares the manifest's
+   `bash .claude/lib/bash/report-lane-assertion.sh --manifest docs/features/parallel/<slug>/parallel.md --edges "<a>:<b> ..."`
+   (a bash invocation against the published payload; it requires no Python interpreter at the
+   destination runtime). It compares the manifest's
    optional `expected_conflict_components` assertion (invariant M8) against the connected
    components of the DERIVED conflict graph and prints one `ADVISORY` line per finding in four
    classes: expected-together-but-derived-apart, expected-apart-but-derived-together, a member

package/resources/claude-customizations/.claude/skills/remediation-handoff-atomic-planner/SKILL.md

@@ -106,6 +106,8 @@ After the plan is authored, `atomic-executor` runs preflight under the directive
 
 The orchestrator records the preflight outcome in `remediation_loop.cycles[current_cycle].preflight` with `iterations` (counter) and `final_status` (`clear|changes_requested|pending`).
 
+For a well-scoped item where `preflight.iterations > 1`, record a process-defect investigation that identifies the incomplete planner internal-review dimension. Treat excess rounds as a process signal, not routine iteration.
+
 The exhaustive-pass, defect-enumeration, and delta-self-check rules that govern how `atomic-executor` conducts preflight are defined in the `## Preflight Validation (Planner ↔ Executor)` section of `.claude/skills/atomic-plan-contract/SKILL.md` and are not restated here.
 
 Alongside `iterations` and `final_status`, the orchestrator also records in `remediation_loop.cycles[current_cycle].preflight` the convergence line `atomic-executor` returned on that round, which is one of `CONVERGENCE: NO FURTHER ROUNDS EXPECTED` or `CONVERGENCE: FURTHER ROUNDS LIKELY`. This convergence field extends the field set already recorded at `remediation_loop.cycles[current_cycle].preflight` rather than replacing it: `iterations` and `final_status` continue to be recorded exactly as stated above, and the convergence field is written in addition to them.

package/resources/claude-customizations/.claude/skills/research-issue/SKILL.md

@@ -55,6 +55,8 @@ Create or update a single research file at one of the two tracked research roots
 
 - Map acceptance criteria into a concrete design.
 - Propose state model, transitions, internal API boundaries, and required file changes.
+- For every numeric count, enumeration, or population proposed for an approved `spec.md` acceptance criterion, add complete `## Numeric Derivation Evidence`. Each record must identify `Complete Family`, `Exhaustive Search Scope`, `Inclusion Rules`, `Exclusion Rules`, `Primary Search Strategy or Query Expression`, `Primary Member Set`, `Primary Count`, `Cross-check Search Strategy or Query Expression`, `Cross-check Member Set`, `Cross-check Count`, and `Member-set Comparison`.
+- Both derivations must be non-empty and independently constructed. They must use distinct search strategies or query expressions, independently enumerate the member sets, and explicitly compare normalized member sets. The scope must cover the entire declared family, including all relevant overloads and members; reject a single grep, a narrow named-pattern search, or a query that covers only one family member even when totals and member sets appear equal. Withhold the numeric assertion if the records are incomplete, duplicated, non-exhaustive, narrow, or disagree.
 
 ### 5. Testing Implications
 
@@ -67,3 +69,4 @@ Create or update a single research file at one of the two tracked research roots
 - Ground all findings in verified evidence from the codebase and authoritative external sources.
 - Keep discussion of non-selected approaches brief.
 - Do not claim or perform nested worker delegation.
+- Omit numeric acceptance-criterion facts when the numeric derivation record is absent, incomplete, or disagrees.

package/resources/claude-customizations/pack-manifests/core.json

@@ -53,6 +53,7 @@
     ".claude/hooks/validate-feature-review-coverage.ps1",
     ".claude/hooks/validate-orchestrator-output.ps1",
     ".claude/hooks/validate-planner-output.ps1",
+    ".claude/hooks/validate-prd-feature-output.ps1",
     ".claude/hooks/validate-required-artifact-output.ps1",
     ".claude/hooks/validate-task-researcher-output.ps1",
     ".claude/rules/architecture-boundaries.md",
@@ -110,6 +111,7 @@
     ".claude/skills/translate-copilot-to-claude/SKILL.md",
     ".claude/skills/update-status/SKILL.md",
     ".claude/lib/hook-payload/HookPayload.psm1",
+    ".claude/lib/requirements/GeneratedDocumentCounters.psm1",
     ".claude/lib/model-routing/ModelRouting.psm1",
     ".claude/lib/orchestrator-state/OrchestratorState.psm1",
     ".claude/lib/orchestrator-state/OrchestratorStateCompletion.psm1",
@@ -139,9 +141,11 @@
     ".claude/lib/bash/parallel-cohorts.sh",
     ".claude/lib/bash/parallel-common.sh",
     ".claude/lib/bash/parallel-items-validate.sh",
+    ".claude/lib/bash/parallel-lane-assertion.sh",
     ".claude/lib/bash/parallel-manifest-validate.sh",
     ".claude/lib/bash/parallel-yaml-emit.sh",
     ".claude/lib/bash/parallel-yaml-scan.sh",
+    ".claude/lib/bash/report-lane-assertion.sh",
     ".claude/lib/bash/validate-parallel-manifest.sh",
     "config/orchestration-routing.json",
     "config/blast-radius.json",

package/resources/codex-and-agents-customizations/.codex/config.toml

@@ -2,7 +2,7 @@ default_permissions = ":danger-full-access"
 
 [mcp_servers.drm-copilot]
 command = "npx"
-args = ["-y", "@danmoisan/drm-copilot-mcp@1.1.6"]
+args = ["-y", "@danmoisan/drm-copilot-mcp@1.1.8"]
 required = true
 enabled_tools = [
     "collect_commit_context",