@danmoisan/drm-copilot-mcp 0.0.1

package/resources/codex-and-agents-customizations/.agents/skills/policy-compliance-order/SKILL.md

@@ -0,0 +1,49 @@
+# Converted skill
+
+Applied rewrites:
+- Rewrite merged standing-guidance source paths to the native AGENTS.md target.
+- Rewrite merged standing-guidance source paths to the native AGENTS.md target.
+- Rewrite merged standing-guidance source paths to the native AGENTS.md target.
+- Rewrite GitHub Copilot instruction-directory references to the native skill root.
+- Rewrite Claude rule paths to shared skill paths.
+- Rewrite Claude rules-directory references to the native skill root.
+
+---
+name: policy-compliance-order
+description: 'Repository policy compliance order and hard constraints. Use when an agent must read mandatory policy files, apply repo-wide constraints, or restate policy precedence without duplicating blocks across agents.'
+---
+
+# Policy Compliance Order
+
+Shared policy-compliance instructions to avoid duplicating the same policy order across multiple agents.
+
+## When to Use This Skill
+
+Use this skill when:
+- An agent must declare the repository’s mandatory policy reading order.
+- You need to reiterate non-negotiable constraints (e.g., no policy edits, no secrets, no silent skips).
+- Multiple agents share the same compliance preamble.
+
+## Required Policy Reading Order (Baseline)
+
+Claude Code auto-loads rules via path-scoped frontmatter in `.agents/skills/`. This ordering documents precedence when policies conflict:
+
+1) `AGENTS.md` (standing instructions, always loaded)
+2) `AGENTS.md` (cross-language code change policy)
+3) `AGENTS.md` (cross-language unit test policy)
+4) Language- or domain-specific rules based on files in scope:
+   - Python: `.agents/skills/python/SKILL.md`, `.agents/skills/python-suppressions/SKILL.md`
+   - PowerShell: `.agents/skills/powershell/SKILL.md`
+   - TypeScript: `.agents/skills/typescript/SKILL.md`, `.agents/skills/typescript-suppressions/SKILL.md`
+   - C#: `.agents/skills/csharp/SKILL.md`
+
+## Hard Constraints (Baseline)
+
+- Do NOT modify policy documents under `.agents/skills/` or `.agents/skills/`.
+- Do NOT create secrets or `.env` files unless explicitly requested.
+- Prefer repo-defined tasks/commands when running checks.
+- If information is missing, proceed with best-effort assumptions and document them.
+
+## Extensions (Agent-Specific)
+
+Agents may append additional requirements that are unique to their role (e.g., policy audit templates or epic docs), but should not duplicate the baseline order above.

package/resources/codex-and-agents-customizations/.agents/skills/powershell/SKILL.md

@@ -0,0 +1,102 @@
+# Converted skill
+
+Applied rewrites:
+- None
+
+---
+paths:
+  - "**/*.ps1"
+  - "**/*.psm1"
+  - "**/*.psd1"
+description: PowerShell-specific toolchain and coding standards.
+---
+
+# PowerShell Code Standards
+
+This rule file summarizes the PowerShell-specific policies for this repository.
+
+## Toolchain
+
+1. **Formatting — Invoke-Formatter**: Format all PowerShell files via PoshQC. MCP command: `mcp__drmCopilotExtension__run_poshqc_format`
+2. **Linting — PSScriptAnalyzer**: Run PoshQC analyzer with repo settings. MCP command: `mcp__drmCopilotExtension__run_poshqc_analyze`. Optional autofix: `mcp__drmCopilotExtension__run_poshqc_analyze_autofix`
+3. **Type checking**: Not applicable for PowerShell; skip to testing.
+4. **Testing — Pester (v5.x)**: Run tests via MCP. MCP command: `mcp__drmCopilotExtension__run_poshqc_test`. Use repo config at `scripts/powershell/PoshQC/settings/pester.runsettings.psd1`.
+
+Run the toolchain in order: format → analyze → test. Restart from step 1 if any step fails or changes files. Use the MCP server functions; do not substitute VS Code task wrappers.
+
+## Compatibility
+
+- All scripts must be compatible with **PowerShell 7+** (enforced via PSScriptAnalyzer settings).
+
+## Coding Standards
+
+- Prefer **advanced functions** with `CmdletBinding()` and named parameters.
+- Add `[Parameter(Mandatory = $true)]` and validation attributes where appropriate.
+- Implement **ShouldProcess/SupportsShouldProcess** for state-changing actions.
+- Avoid global state and mutable script-scoped variables; pass data explicitly.
+- Avoid `Invoke-Expression`, plaintext secrets, and hard-coded credentials/paths.
+- Use `Write-Error`/`throw` for failures; avoid silent catch-alls.
+- Use approved verbs and descriptive nouns for function names (PSScriptAnalyzer enforces this).
+- Keep scripts cohesive and under 500 lines.
+
+## Change Budget
+
+- Direct-mode overall scope: up to 2 production PowerShell files (plus corresponding tests). Requests exceeding this must be routed to `powershell-orchestrator` per `powershell-change-budget-router`.
+- Per-batch cap in all modes: at most 3 production files and 3 test files unless an explicit override has been approved.
+- If a batch would exceed the cap, split the work into smaller batches.
+
+## Design Seams (Minimal DI)
+
+Introduce the smallest seam that enables reliable mocking. Apply these options in order:
+
+1. **Wrapper function seam (preferred)** — extract external executable calls into a wrapper function:
+   - Signature: `Invoke-<Tool>Exe -<Tool>Args <string[]>` (for example `Invoke-GitExe -GitArgs <string[]>`).
+   - The wrapper accepts a single array parameter and splats into the executable: `git @GitArgs 2>&1`.
+   - Parameter names must not be `Args` (automatic variable collision). Use `GitArgs`, `ToolArgs`, or `Arguments`.
+2. **Injectable delegate / ScriptBlock seam** — only when a wrapper is insufficient, add a narrowly-scoped optional delegate or `ScriptBlock` parameter with a safe default. Do not introduce generic runner frameworks.
+3. **Adapter seams for non-executable boundaries** — for filesystem, environment, or clock dependencies, introduce tiny helpers or narrow injectable parameters rather than threading raw I/O through domain logic.
+
+## Testing Standards
+
+- Use **Pester** (v5.x) as the test framework.
+- Organize tests to mirror code structure (e.g., `tests/scripts/dev-tools/ScriptName.Tests.ps1`).
+- Name test files `*.Tests.ps1`.
+- Use `Describe`/`Context`/`It` blocks; one behavior per `It`.
+- Write focused tests exercising a single function or behavior.
+- Mock sparingly; prefer real code paths.
+- No external dependencies in unit tests.
+- Repository-wide line coverage must remain >= 80%.
+- Any new module, class, or method must reach >= 90% coverage.
+- Coverage regression on changed lines is a blocking finding.
+
+### Deterministic Test Requirements
+
+Tests must not depend on:
+
+- network access,
+- mutable machine PATH or profile state,
+- implicit working-directory assumptions,
+- external services or live executables.
+
+Tests must produce identical results in Terminal and the VS Code Test Explorer. Assume a different PATH, current working directory, profile, and host when tests are run from Test Explorer; do not rely on ambient environment resolution.
+
+### Mocking Rules
+
+1. **External executable mocking** — never mock `git`, `gh`, `actionlint`, or other executables directly. Mock the wrapper function (for example `Invoke-GitExe`) instead.
+2. **Mock signature parity** — mock signatures must match production named parameters exactly. Example:
+   - production: `Invoke-GitExe -GitArgs $gitArgs`
+   - test mock: `param([string[]]$GitArgs)`
+3. **Mock registration order** — register mocks before the code under test can resolve commands, so Test Explorer parity is preserved.
+4. **AST/ScriptBlock import order** — when importing script functions via AST or `ScriptBlock` patterns:
+   - dot-source the returned `ScriptBlock` in the test scope,
+   - import dependencies in the correct order,
+   - import wrapper seams before mocking them when executable calls exist.
+
+## Prohibited Behaviors
+
+- Broad refactors across unrelated scripts or modules.
+- Introducing generic process-runner frameworks to replace the wrapper seam pattern.
+- Creating PSScriptAnalyzer debt and deferring cleanup.
+- Weakening assertions merely to make tests pass.
+- Adding sleeps, retries, or timing hacks to stabilize flaky tests.
+- Claiming success without running the required toolchain.

package/resources/codex-and-agents-customizations/.agents/skills/powershell-change-budget-router/SKILL.md

@@ -0,0 +1,53 @@
+# Converted skill
+
+Applied rewrites:
+- None
+
+---
+name: powershell-change-budget-router
+description: Budget-first routing contract for PowerShell work: estimate production-file scope, choose small vs large path, enforce direct-mode escalation to orchestrator, and use the VS Code extension command surface for promotion lifecycle steps when available.
+---
+
+# PowerShell Change Budget Router
+
+Canonical guidance for deciding whether work should execute directly in `powershell-typed-engineer` or be escalated to `powershell-orchestrator`.
+
+## When to Use This Skill
+
+Use this skill when:
+- Intake starts from a natural-language PowerShell request.
+- An agent must decide execution path before planning or implementation.
+- A direct implementation agent must reject over-budget requests and route to orchestrator.
+
+## Canonical Routing Rules
+
+1) Estimate rough change budget first based on likely **production PowerShell files** touched.
+2) Route:
+- `1-2` production files (+ corresponding tests) → **small path** (`powershell-typed-engineer` direct mode).
+- `>2` production files → **large path** (`powershell-orchestrator`).
+
+## Orchestrated Small-Path Requirements
+
+When routed through `powershell-orchestrator`, small path still requires lifecycle scaffolding before implementation:
+- invoke promotion/folder lifecycle steps through `vscode/runCommand` + extension access per `feature-promotion-lifecycle` when available; use script/CLI fallback only when direct extension command execution is unavailable,
+- promote potential item to GitHub issue with `--work-mode minor-audit`,
+- create active feature folder with `--work-mode minor-audit`,
+- delegate minimal-audit plan creation to `atomic_planner` with `DIRECTIVE: MINIMAL-AUDIT PLAN REQUIRED`,
+- require `atomic_executor` preflight until `PREFLIGHT: ALL CLEAR`,
+- execute Phase 0 only via `atomic_executor` before branching,
+- run reduced small-audit after implementation and QC.
+
+Direct invocation of `powershell-typed-engineer` remains implementation-focused and does not replace orchestrator lifecycle steps.
+
+## Direct-Mode Rejection Rule
+
+If `powershell-typed-engineer` is invoked directly and estimated scope is `>2` production files:
+- Stop before implementation.
+- Return explicit routing instruction to invoke `powershell-orchestrator`.
+
+## Documentation Expectations
+
+Record in response/logs:
+- estimated production file count,
+- chosen path (`small`/`large`),
+- rationale summary (1-3 bullets).

package/resources/codex-and-agents-customizations/.agents/skills/powershell-orchestration-state-machine/SKILL.md

@@ -0,0 +1,64 @@
+# Converted skill
+
+Applied rewrites:
+- None
+
+---
+name: powershell-orchestration-state-machine
+description: Checkpoint schema and resume protocol for long-running PowerShell orchestration workflows.
+---
+
+# PowerShell Orchestration State Machine
+
+Canonical checkpoint and resume behavior for orchestration agents running multi-step PowerShell delivery flows.
+
+## When to Use This Skill
+
+Use this skill when:
+- A workflow spans multiple delegations and commands.
+- Execution may be interrupted and must resume deterministically.
+- An orchestrator must avoid repeating completed steps.
+
+## Canonical Checkpoint Location
+
+- `artifacts/orchestration/powershell-orchestrator-state.json`
+
+Never create sidecar checkpoint files, suffixed variants, or backup files as active state. If checkpoint state is conflicted, stale, or belongs to another mission, stop and report the conflict instead of renaming or backing up the active checkpoint.
+
+## Required Checkpoint Fields
+
+- `objective`
+- `change_budget_estimate`
+- `path_selected` (`small` or `large`)
+- `promotion-type`
+- `short-name`
+- `relativeFile`
+- `long-name`
+- `issue-num`
+- `feature-folder`
+- `work-mode` (`minor-audit`, `full-feature`, or `full-bug`; normalize legacy `full` to `full-feature` before persistence)
+- `plan-path` (minimal or full plan path)
+- `completed_steps`
+- `next_step`
+- `last_updated`
+
+For short-path runs, also persist:
+- `small_path_qc_summary`
+- `small_path_audit_artifacts`
+- `bootstrap_mode` (`manual-bootstrap` or `auto-small-dev`)
+- `phase0_execution_summary`
+- `resume_after_manual_bootstrap` (next step token)
+
+## Update Protocol
+
+- Write checkpoint after every completed orchestration sub-step.
+- Treat checkpoint as source-of-truth for progress state.
+- Never claim mission completion until checkpoint marks final state.
+
+## Resume Protocol
+
+On invocation:
+1) Read checkpoint if it exists.
+2) If incomplete, resume from `next_step` without re-running `completed_steps`.
+3) If missing or completed, start at phase-0 intake.
+4) If user explicitly requests restart, reset checkpoint and start phase-0.

package/resources/codex-and-agents-customizations/.agents/skills/powershell-qa-gate/SKILL.md

@@ -0,0 +1,83 @@
+# Converted skill
+
+Applied rewrites:
+- Rewrite Claude skill paths to shared skill paths.
+- Rewrite Claude rule paths to shared skill paths.
+
+---
+name: powershell-qa-gate
+description: Final QA gate for PowerShell changes. Executes the full PoshQC format -> analyze -> test toolchain (with coverage where enforced), compares against a captured baseline, enforces zero-regression deltas, and produces the required reporting block before the agent declares the change complete.
+---
+
+# PowerShell QA Gate
+
+Canonical procedure for the Phase D final quality gate that every PowerShell change must pass before completion is reported.
+
+## When to Use This Skill
+
+Use this skill when:
+
+- `powershell-typed-engineer` is about to declare a change complete.
+- An executor has finished applying a planned batch and must verify zero regressions against the baseline captured in Phase A.
+- A reviewer needs to confirm the toolchain was actually run and produced a clean pass.
+
+## Required Inputs
+
+Before invoking this gate, the agent must have:
+
+- a baseline record produced in Phase A, containing PSScriptAnalyzer findings, Pester pass/fail status, and per-file coverage status for the in-scope files,
+- the exact list of touched production and test files,
+- a clean working tree (all planned edits committed to the working copy).
+
+## Toolchain Execution Sequence
+
+Run the full toolchain in this exact order. If any step fails or modifies files, fix the issue and restart from step 1. Do not stop the loop until all steps complete without errors in a single pass.
+
+1. `mcp__drmCopilotExtension__run_poshqc_format`
+2. `mcp__drmCopilotExtension__run_poshqc_analyze`
+3. `mcp__drmCopilotExtension__run_poshqc_test`
+4. Coverage check (when enforced by task/repo flow) — use the Pester coverage output from step 3 or the repo coverage task.
+
+If the environment prevents running any tool, stop and report the change as **unverified**. Do not declare completion.
+
+## Delta Requirements (Zero-Regression Hard Gate)
+
+Compare the final results to the Phase A baseline. All of the following must hold:
+
+- **PSScriptAnalyzer delta**: 0 new findings across the repository.
+- **Pester delta**: 0 new failing tests.
+- **Per-file coverage delta**: coverage for every touched file is greater than or equal to the baseline for that file.
+- **Overall coverage delta** (when the repo enforces it): overall coverage is greater than or equal to the baseline.
+- **New modules, classes, or methods**: coverage >= 90% for each new unit introduced in the batch.
+
+If any delta check fails, the agent must revert or fix immediately and rerun the full toolchain. Do not proceed to reporting until all deltas are clean.
+
+## Required Reporting Block
+
+Every completion response must include the following sections:
+
+1. **Scope** — exact file list touched in this change.
+2. **Baseline** — PSScriptAnalyzer, Pester, and coverage status recorded in Phase A.
+3. **Plan** — design and test-strategy summary, referencing the approved plan, including proposed script/module structure, minimal DI seams, Pester scenario-level test strategy, and external executable wrapper mock strategy.
+4. **Diffs** — patch-style or full-file replacements for scoped files only.
+5. **QA Gate Results** — PSScriptAnalyzer delta, failing-tests delta, per-file coverage delta, and overall coverage delta when applicable. If any step could not be run, mark the corresponding line **unverified** and state why.
+
+## Evidence Storage
+
+Persist toolchain output according to `evidence-and-timestamp-conventions`:
+
+- store baseline outputs under `<FEATURE>/evidence/baseline/<timestamp>/`,
+- store post-change outputs under `<FEATURE>/evidence/qa-gates/<timestamp>/`,
+- use ISO-8601 UTC timestamps in folder names.
+
+This location is canonical per evidence-and-timestamp-conventions and is not overridable.
+See `.agents/skills/evidence-and-timestamp-conventions/SKILL.md` for the canonical evidence path authority.
+
+The evidence paths must be referenced in the agent's completion message to satisfy the `SubagentStop` completion-artifact gate.
+
+## Prohibited Shortcuts
+
+- Do not disable, skip, or narrow any step of the toolchain to reach a clean result.
+- Do not add PSScriptAnalyzer rule suppressions (`[Diagnostics.CodeAnalysis.SuppressMessageAttribute]` or `PSScriptAnalyzer` suppression comments) or Pester `-Skip` / `-Pending` to mask new findings introduced by the change.
+- Do not report success based on partial or targeted runs alone. Targeted runs are allowed mid-batch, but the final gate requires a full-repo pass.
+- Do not mock `git`, `gh`, `actionlint`, or other executables directly; mock the wrapper function (for example `Invoke-GitExe`) per `.agents/skills/powershell/SKILL.md`.

package/resources/codex-and-agents-customizations/.agents/skills/pr-author/SKILL.md

@@ -0,0 +1,55 @@
+# Converted skill
+
+Applied rewrites:
+- None
+
+---
+name: pr-author
+description: Write a GitHub-ready pull request body from the canonical PR-context bundle with strict verification and auto-close rules.
+allowed-tools:
+  - Read
+  - "Bash(git log *)"
+---
+
+# PR Author Skill
+
+Produce a GitHub-ready Pull Request description from the standard PR context files. The pull request must be in a copy / paste block so that it can be copied easily to the PR extension.
+
+## Inputs
+
+- `artifacts/pr_context.summary.txt` — PR context summary (primary)
+- `artifacts/pr_context.appendix.txt` — PR context appendix (full baseline diff, commits, changed files)
+- Optional user directives
+
+Only reference files that are listed under "Additional context files" in the context bundle. Do not cite or summarize files outside that enumeration.
+
+## Output Requirements
+
+1. Output only the PR text body in GitHub-flavored Markdown.
+2. Use clear headings, consistent structure, and concise bullets.
+3. Do not invent tests or results; if not in context, state "Not verified in this PR."
+4. If scope is large, include a Review Guide with suggested review order.
+5. The output is a PR body artifact or PR-ready body text only.
+
+## PR Body Structure
+
+Use these sections in this order:
+
+1. **Suggested title** — crisp, prioritizing the primary outcome
+2. **Summary** — 3–7 bullets, most important first; lead with the primary product/feature/architecture change
+3. **Why** — motivation, constraints, root cause; rely on embedded feature-doc excerpts and PR Intent fields only
+4. **What Changed** — grouped by theme (core feature, tooling/CI, tests, docs/templates)
+5. **Architecture / How It Fits Together** — short wiring description with components, entry points, control flow
+6. **Verification** — "Completed" (from context) and "Recommended" (commands to run)
+7. **Backward Compatibility / Migration Notes** — breaking changes, removals, renamed paths
+8. **Risks and Mitigations** — realistic risks with mitigations and rollback notes
+9. **Review Guide** — suggested order, noisy mechanical moves, large diffs
+10. **Follow-ups** — known TODOs, deferred cleanup, next PRs
+11. **GitHub Auto-close** — `- Closes #NNN` only from verified autoclose lists; do not invent issue numbers
+
+## Issue/PR Reference Rules
+
+- Only mention an issue/PR number if it appears verbatim in the provided context.
+- Do not treat PR numbers as issues.
+- Auto-close bullets must use exactly `- Closes #NNN` format, sourced only from "Issues to autoclose" or "Author-asserted autoclose issues."
+- If GitHub validation is unavailable/unverified, do not emit `Closes`; use the fallback `None` bullet.

package/resources/codex-and-agents-customizations/.agents/skills/pr-authoring/SKILL.md

@@ -0,0 +1,124 @@
+---
+name: pr-authoring
+description: 'Write a GitHub-ready pull request body from the canonical PR-context bundle and its enumerated additional context files. Use when Codex or a subagent must produce an evidence-based PR description with strict verification and auto-close rules.'
+---
+
+# PR Authoring
+
+Shared workflow for producing a GitHub-ready pull request body.
+
+## Required Shared Skill
+
+Always use:
+- `pr-context-artifacts`
+
+## Role
+
+- Generate a PR body that is feature-first, accurate, and review-ready.
+- Base every claim on the canonical PR-context bundle and the explicitly enumerated additional context files listed inside that bundle.
+- Keep GitHub issue and PR references precise and non-hallucinatory.
+
+## Allowed Sources
+
+Use only:
+- the canonical PR-context summary and appendix defined by `pr-context-artifacts`
+- files explicitly listed under `Additional context files` inside that context bundle
+- optional user directives supplied with the request
+
+Do not cite or summarize any other repository file.
+
+## Context Priority
+
+Prioritize evidence in this order:
+
+1. `PR Intent`
+2. enumerated `Additional context files`
+3. embedded feature-doc excerpts such as root cause, constraints, proposed fix, acceptance criteria, story statement, problem, or why
+4. comparison range, commits, changed files, and diff statistics
+5. referenced issues and PRs
+6. issues to autoclose
+
+## Core Objectives
+
+1. Accuracy: every statement must be supported by the allowed sources.
+2. Signal: emphasize why and semantic intent, not just changed-file inventory.
+3. GitHub correctness: auto-close syntax must be valid and must not invent issue numbers.
+
+## Required Output Shape
+
+Output exactly one fenced code block using the language tag `markdown`.
+
+Inside that code block, include only the PR body with exactly this section order:
+
+- `Suggested title: ...`
+- `## Summary`
+- `## Why`
+- `## What Changed`
+- `## Architecture / How It Fits Together`
+- `## Verification`
+- `### Completed`
+- `### Recommended`
+- `## Backward Compatibility / Migration Notes`
+- `## Risks and Mitigations`
+- `## Review Guide`
+- `## Follow-ups`
+- `## GitHub Auto-close`
+- `## Related issues / PRs`
+
+## Section Rules
+
+### Suggested title
+
+- one line only
+- lead with the primary outcome, not secondary tooling or docs work
+
+### Summary
+
+- 3 to 7 bullets
+- first bullet must state the primary change
+
+### Why
+
+- use feature-doc excerpts and PR Intent as the main source of motivation
+- if explicit excerpts are missing, infer conservatively from commits and file themes
+
+### What Changed
+
+Group bullets by theme:
+- core behavior or architecture
+- tooling, automation, CI, or developer experience
+- tests
+- docs, templates, or agents
+
+### Verification
+
+- `Completed` may include only evidence-backed verification
+- if verification is not proven, state: `Not verified in this PR (no tool outputs recorded in the PR-context summary).`
+- `Recommended` must include concrete repo-appropriate commands
+
+### GitHub Auto-close
+
+This section must contain only bullets of the form:
+- `Closes #NNN`
+
+Source of truth in order:
+1. verified or pending issues to autoclose
+2. `PR Intent` author-asserted autoclose issues
+
+If GitHub validation is unavailable or no approved source provides issue numbers, include one bullet:
+- `None (...)`
+
+Never use `Related:` in this section.
+
+### Related issues / PRs
+
+- non-closed issues: `Related issue: #NNN`
+- PRs in range: `Related PR: #NNN`
+
+## Hard Prohibitions
+
+- Do not invent issue or PR numbers.
+- Do not treat PR numbers as issues.
+- Do not claim verification unless the context proves it.
+- Do not cite sources outside the allowed-source list.
+- Do not output commentary outside the single fenced Markdown block.

package/resources/codex-and-agents-customizations/.agents/skills/pr-base-branch-merge-base/SKILL.md

@@ -0,0 +1,60 @@
+# Converted skill
+
+Applied rewrites:
+- None
+
+---
+name: pr-base-branch-merge-base
+description: 'Resolve PRBaseBranch for mcp__drmCopilotExtension__collect_pr_context using merge-base ancestry. Use when orchestrators or review workflows need the correct comparison base branch and must select the branch with the most recent common ancestor commit with HEAD.'
+---
+
+# PR Base Branch (Merge-Base)
+
+Deterministic branch-selection rules for PR context collection.
+
+## When to Use This Skill
+
+Use this skill when:
+- running `mcp__drmCopilotExtension__collect_pr_context`,
+- delegating post-implementation review that depends on `PRBaseBranch`,
+- constructing PR context artifacts where the base must not be hard-coded.
+
+## Selection Contract
+
+`PRBaseBranch` MUST be resolved from git ancestry, not guessed.
+
+Definition of correct base:
+- choose the candidate branch whose merge-base with `HEAD` has the most recent commit timestamp,
+- this implements “find the branch with the most recent commit in common.”
+
+## Deterministic Procedure
+
+1. Enumerate candidate branches from local and remotes, excluding `HEAD` and detached refs.
+2. For each candidate `B`, compute merge-base commit `M = git merge-base HEAD B`.
+3. Compute `merge_base_epoch(B)` from `git show -s --format=%ct M`.
+4. Select branch with maximum `merge_base_epoch(B)`.
+5. Tie-breakers (in order):
+   - `development`
+   - `main`
+   - `master`
+   - lexical ascending branch name
+
+## Guardrails
+
+- Do not default to `main` unless merge-base resolution fails for all candidates.
+- If all candidates fail, surface explicit error context and use repository default branch only as last-resort fallback.
+- Persist chosen `PRBaseBranch` in orchestration state and reuse it within the same run.
+
+## Collector Invocation Rule
+
+When invoking PR context collection, pass the resolved base explicitly:
+
+- `mcp__drmCopilotExtension__collect_pr_context` with `base=<resolved-PRBaseBranch>`
+
+## Evidence Recommendation
+
+For auditability, include in logs/checkpoint:
+- selected branch name,
+- selected merge-base SHA,
+- selected merge-base timestamp,
+- top competing candidates with timestamps when available.

package/resources/codex-and-agents-customizations/.agents/skills/pr-context-artifacts/SKILL.md

@@ -0,0 +1,34 @@
+# Converted skill
+
+Applied rewrites:
+- None
+
+---
+name: pr-context-artifacts
+description: 'PR context artifact locations and refresh rules. Use when generating, reading, or inlining pr_context summary/appendix artifacts.'
+---
+
+# PR Context Artifacts
+
+Canonical locations and usage rules for PR context artifacts.
+
+## When to Use This Skill
+
+Use this skill when:
+- You generate or refresh PR context artifacts.
+- You reference PR context summary/appendix as evidence.
+- You inline PR context artifacts into remediation handoffs.
+
+## Canonical Artifact Locations
+
+- Summary: `artifacts/pr_context.summary.txt`
+- Appendix: `artifacts/pr_context.appendix.txt`
+
+## Refresh Rule
+
+If the artifacts are missing or stale relative to the current branch state, re-generate them using the repo’s PR context collector.
+
+- When `PRBaseBranch` is supplied explicitly, use that exact branch for refresh.
+- When `PRBaseBranch` is missing or ambiguous, resolve it first with `pr-base-branch-merge-base` before running the collector.
+- Do not infer the refresh base from the repository default branch unless merge-base resolution fails for all candidates.
+- Treat an already-fresh artifact pair as authoritative; do not refresh solely because no explicit `PRBaseBranch` input was provided.