@danmoisan/drm-copilot-mcp 1.1.18 → 1.1.20

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

@@ -18,6 +18,7 @@ Use the following repo-local skills as the canonical workflow source:
 - pr-context-artifacts
 - pr-base-branch-merge-base
 - evidence-and-timestamp-conventions
+- execution-environment
 
 ## Startup Protocol
 
@@ -60,8 +61,10 @@ entry path with `EPIC_INVOCATION_ORIGIN_BLOCKED`.
 
 When the parent prompt carries the literal `Preparation mode: true` marker, select only
 `route_id: preparation`. Perform promotion through the MCP surface, research, `spec.md`,
-`user-story.md`, atomic planning, and atomic-executor preflight. Iterate the same plan until
-`PREFLIGHT: ALL CLEAR`, commit the prepared feature folder and plan, then stop with
+`user-story.md`, atomic planning, and atomic-executor preflight. Run single-pass preflight on the
+same plan (trivial defects fixed in place, at most one return to the planner, a second substantive
+result halts with `blocked_reason: "validator_failed"`), commit the prepared feature folder and
+plan after `PREFLIGHT: ALL CLEAR`, then stop with
 `completed_steps` containing `S3_promotion` and `S4_atomic_planning`,
 `next_step: "S5_atomic_execution"`, execution-through-CI statuses exactly `not-applicable`, and
 `blocked_reason: "none"`. Do not implement, create a PR, run feature review, monitor CI, or claim
@@ -188,9 +191,9 @@ Do not report completion until:
 5. The checkpoint file reflects the final completed state.
 6. The checkpoint proves the selected routing matrix entry: all required agents have delegation receipts, all required skills have skill receipts, all required MCP tools have successful MCP receipts, and no local bypass list is populated.
 7. The deterministic MCP validator passes: `validate_orchestration_artifacts` with `artifact_type = "orchestrator-state"`, `artifact_path = "artifacts/orchestration/orchestrator-state.json"`, `require_complete = true`, `require_codex_topology = true`, and `require_codex_model_routing = true`.
-8. Required GitHub checks are green for the current PR head SHA before any PR/DONE transition.
+8. Every GitHub check on the current PR head SHA passed or was skipped before any PR/DONE transition.
 
-The MCP validator and required CI checks are the hard completion boundary. There is no fallback. If the MCP server or validation tool is unavailable, stop and persist blocked state. Codex lifecycle hooks may provide local feedback, but they are not the authoritative completion gate.
+The MCP validator and every CI check on the current PR head SHA are the hard completion boundary. There is no fallback. If the MCP server or validation tool is unavailable, stop and persist blocked state. Codex lifecycle hooks may provide local feedback, but they are not the authoritative completion gate.
 
 Do not claim mission completion unless all required delegations completed with receipts and the required orchestration artifacts exist on disk.
 '''

package/resources/codex-and-agents-customizations/.codex/agents/powershell-atomic-planning.toml

@@ -14,7 +14,7 @@ Core behavior:
 - Delegate validation-only preflight to `atomic-executor`.
 - Require the exact directive `DIRECTIVE: PREFLIGHT VALIDATION ONLY` in the delegated preflight handoff.
 - Require explicit PowerShell baseline and final-QA tasks, including format, analyzer, test, and coverage steps where policy requires coverage.
-- Reuse the same target plan file for every preflight revision iteration.
+- Reuse the same target plan file for the single permitted preflight revision.
 - Do not create timestamped sibling plan files when an authoritative `plan-path` already exists.
 - Stop and report blocked state if the required `atomic-executor` handoff cannot be started, resumed, or completed.
 

package/resources/codex-and-agents-customizations/.codex/agents/python-atomic-planning.toml

@@ -14,7 +14,7 @@ Core behavior:
 - Delegate validation-only preflight to `atomic-executor`.
 - Require the exact directive `DIRECTIVE: PREFLIGHT VALIDATION ONLY` in the delegated preflight handoff.
 - Require explicit Python baseline and final-QA tasks, including Ruff, Pyright, pytest, and coverage where policy requires coverage.
-- Reuse the same target plan file for every preflight revision iteration.
+- Reuse the same target plan file for the single permitted preflight revision.
 - Do not create timestamped sibling plan files when an authoritative `plan-path` already exists.
 - Stop and report blocked state if the required `atomic-executor` handoff cannot be started, resumed, or completed.
 

package/resources/codex-and-agents-customizations/.codex/agents/task-researcher-c1.toml

@@ -13,6 +13,10 @@ Do not weaken validation-only preflight loops, QA gates, remediation triggers, r
 Applied rewrites:
 - Rewrite Claude skill paths to shared skill paths.
 
+Use the following repo-local skills as the canonical workflow source:
+- evidence-and-timestamp-conventions
+- execution-environment
+
 Canonical migration source:
 - .github/agents/task-researcher.agent.md
 
@@ -33,7 +37,9 @@ tools:
   - Glob
   - WebFetch
   - "Write(/artifacts/research/**)"
+skills:
   - evidence-and-timestamp-conventions
+  - execution-environment
 memory: project
 hooks:
   Stop:

package/resources/codex-and-agents-customizations/.codex/agents/task-researcher-c2.toml

@@ -13,6 +13,10 @@ Do not weaken validation-only preflight loops, QA gates, remediation triggers, r
 Applied rewrites:
 - Rewrite Claude skill paths to shared skill paths.
 
+Use the following repo-local skills as the canonical workflow source:
+- evidence-and-timestamp-conventions
+- execution-environment
+
 Canonical migration source:
 - .github/agents/task-researcher.agent.md
 
@@ -33,7 +37,9 @@ tools:
   - Glob
   - WebFetch
   - "Write(/artifacts/research/**)"
+skills:
   - evidence-and-timestamp-conventions
+  - execution-environment
 memory: project
 hooks:
   Stop:

package/resources/codex-and-agents-customizations/.codex/agents/task-researcher-c3-elevated.toml

@@ -13,6 +13,10 @@ Do not weaken validation-only preflight loops, QA gates, remediation triggers, r
 Applied rewrites:
 - Rewrite Claude skill paths to shared skill paths.
 
+Use the following repo-local skills as the canonical workflow source:
+- evidence-and-timestamp-conventions
+- execution-environment
+
 Canonical migration source:
 - .github/agents/task-researcher.agent.md
 
@@ -33,7 +37,9 @@ tools:
   - Glob
   - WebFetch
   - "Write(/artifacts/research/**)"
+skills:
   - evidence-and-timestamp-conventions
+  - execution-environment
 memory: project
 hooks:
   Stop:

package/resources/codex-and-agents-customizations/.codex/agents/task-researcher-c3.toml

@@ -13,6 +13,10 @@ Do not weaken validation-only preflight loops, QA gates, remediation triggers, r
 Applied rewrites:
 - Rewrite Claude skill paths to shared skill paths.
 
+Use the following repo-local skills as the canonical workflow source:
+- evidence-and-timestamp-conventions
+- execution-environment
+
 Canonical migration source:
 - .github/agents/task-researcher.agent.md
 
@@ -33,7 +37,9 @@ tools:
   - Glob
   - WebFetch
   - "Write(/artifacts/research/**)"
+skills:
   - evidence-and-timestamp-conventions
+  - execution-environment
 memory: project
 hooks:
   Stop:

package/resources/codex-and-agents-customizations/.codex/agents/task-researcher-c4.toml

@@ -13,6 +13,10 @@ Do not weaken validation-only preflight loops, QA gates, remediation triggers, r
 Applied rewrites:
 - Rewrite Claude skill paths to shared skill paths.
 
+Use the following repo-local skills as the canonical workflow source:
+- evidence-and-timestamp-conventions
+- execution-environment
+
 Canonical migration source:
 - .github/agents/task-researcher.agent.md
 
@@ -33,7 +37,9 @@ tools:
   - Glob
   - WebFetch
   - "Write(/artifacts/research/**)"
+skills:
   - evidence-and-timestamp-conventions
+  - execution-environment
 memory: project
 hooks:
   Stop:

package/resources/codex-and-agents-customizations/.codex/agents/task-researcher.toml

@@ -13,6 +13,10 @@ Do not weaken validation-only preflight loops, QA gates, remediation triggers, r
 Applied rewrites:
 - Rewrite Claude skill paths to shared skill paths.
 
+Use the following repo-local skills as the canonical workflow source:
+- evidence-and-timestamp-conventions
+- execution-environment
+
 Canonical migration source:
 - .github/agents/task-researcher.agent.md
 
@@ -33,7 +37,9 @@ tools:
   - Glob
   - WebFetch
   - "Write(/artifacts/research/**)"
+skills:
   - evidence-and-timestamp-conventions
+  - execution-environment
 memory: project
 hooks:
   Stop: