arcane-cli 0.39.0 → 1.1.0

package/README.md

@@ -109,7 +109,7 @@ Plus session and operational spells — `/spell-open-session`, `/spell-close-ses
 
 ## What's in the box
 
-Arcane isn't a prompt snippet — it's a full framework. Everything installs into your repo as plain, reviewable markdown.
+Arcane isn't a prompt snippet — it's a full framework. Everything installs into your repo as plain, reviewable markdown. Each spell is authored once, in `.arcane/spells/`, and reaches Copilot, Claude Code and Codex through thin generated shims — one source of truth, no per-client copies to drift apart.
 
 | Layer | What you get |
 | --- | --- |
@@ -220,6 +220,19 @@ spell init --profile full
 spell add agent-policies   # or install any component à la carte
 ```
 
+### Once per machine
+
+Working across many Arcane repositories at once? Install the spells a single time at the **user tier**, instead of (or as well as) per repository:
+
+```bash
+spell init --user       # ~/.arcane/spells/<id>.md, plus one Codex/Copilot skill and one Claude Code command per spell in your home directory
+spell status --user     # what the tier holds, and whether any client file is missing or customized
+spell update --user     # after upgrading the CLI
+spell uninstall --user  # removes only what it wrote; an edited client file is kept and named
+```
+
+Codex, VS Code Copilot and Claude Code each discover the user tier from their own home-directory locations (`~/.agents/skills` and `~/.claude/commands`), so no VS Code setting is needed. Claude Code runs a personal command over a project command of the same name, so in a repository that still carries its own spells `/spell-*` runs the user tier's copy. Governance stays per repository — only spell delivery moves up a level.
+
 ---
 
 ## Philosophy

package/dist/assets/.agents/skills/spell-address-review/SKILL.md

@@ -3,4 +3,4 @@ name: spell-address-review
 description: Use PROACTIVELY whenever responding to PR review comments — fetch threads, triage, fix or reply, resolve.
 ---
 
-This skill is the Arcane `spell-address-review` spell. Read `.github/prompts/spell-address-review.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-address-review` spell. Read `.arcane/spells/spell-address-review.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-adopt-docs/SKILL.md

@@ -3,4 +3,4 @@ name: spell-adopt-docs
 description: Use PROACTIVELY when bringing an existing, ungoverned doc tree under Arcane governance.
 ---
 
-This skill is the Arcane `spell-adopt-docs` spell. Read `.github/prompts/spell-adopt-docs.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-adopt-docs` spell. Read `.arcane/spells/spell-adopt-docs.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-arcane-version/SKILL.md

@@ -3,4 +3,4 @@ name: spell-arcane-version
 description: Use PROACTIVELY when asked about the installed Arcane version, profile, or whether an update is available.
 ---
 
-This skill is the Arcane `spell-arcane-version` spell. Read `.github/prompts/spell-arcane-version.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-arcane-version` spell. Read `.arcane/spells/spell-arcane-version.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-architect/SKILL.md

@@ -3,4 +3,4 @@ name: spell-architect
 description: Use PROACTIVELY once a PRD exists and needs architecture decisions and a story breakdown before implementation starts.
 ---
 
-This skill is the Arcane `spell-architect` spell. Read `.github/prompts/spell-architect.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-architect` spell. Read `.arcane/spells/spell-architect.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-brainstorm/SKILL.md

@@ -3,4 +3,4 @@ name: spell-brainstorm
 description: Use PROACTIVELY when exploring multiple solutions to a problem before committing to one.
 ---
 
-This skill is the Arcane `spell-brainstorm` spell. Read `.github/prompts/spell-brainstorm.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-brainstorm` spell. Read `.arcane/spells/spell-brainstorm.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-bug/SKILL.md

@@ -3,4 +3,4 @@ name: spell-bug
 description: Use PROACTIVELY whenever diagnosing and fixing a bug, even if the user just describes broken behavior.
 ---
 
-This skill is the Arcane `spell-bug` spell. Read `.github/prompts/spell-bug.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-bug` spell. Read `.arcane/spells/spell-bug.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-bump/SKILL.md

@@ -3,4 +3,4 @@ name: spell-bump
 description: Use PROACTIVELY before shipping any change that touches distributable content, to determine and apply the correct version bump.
 ---
 
-This skill is the Arcane `spell-bump` spell. Read `.github/prompts/spell-bump.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-bump` spell. Read `.arcane/spells/spell-bump.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-check-drift/SKILL.md

@@ -3,4 +3,4 @@ name: spell-check-drift
 description: Use PROACTIVELY to detect contradictions and stale statements across core docs, periodically or after major changes.
 ---
 
-This skill is the Arcane `spell-check-drift` spell. Read `.github/prompts/spell-check-drift.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-check-drift` spell. Read `.arcane/spells/spell-check-drift.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-close-session/SKILL.md

@@ -3,4 +3,4 @@ name: spell-close-session
 description: Use PROACTIVELY at the end of any significant work session, even if the user just says 'wrap up' or 'done for now'.
 ---
 
-This skill is the Arcane `spell-close-session` spell. Read `.github/prompts/spell-close-session.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-close-session` spell. Read `.arcane/spells/spell-close-session.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-commit-work/SKILL.md

@@ -3,4 +3,4 @@ name: spell-commit-work
 description: Use PROACTIVELY whenever committing work during a session, even if the user just says 'commit this'.
 ---
 
-This skill is the Arcane `spell-commit-work` spell. Read `.github/prompts/spell-commit-work.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-commit-work` spell. Read `.arcane/spells/spell-commit-work.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-compliance/SKILL.md

@@ -3,4 +3,4 @@ name: spell-compliance
 description: Use PROACTIVELY before a launch, an enterprise sales cycle, or a security questionnaire that raises GDPR/CCPA/SOC 2/HIPAA questions.
 ---
 
-This skill is the Arcane `spell-compliance` spell. Read `.github/prompts/spell-compliance.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-compliance` spell. Read `.arcane/spells/spell-compliance.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-create-pull-request/SKILL.md

@@ -3,4 +3,4 @@ name: spell-create-pull-request
 description: Use PROACTIVELY whenever opening a pull request for the current branch, even if the user just says 'open a PR'.
 ---
 
-This skill is the Arcane `spell-create-pull-request` spell. Read `.github/prompts/spell-create-pull-request.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-create-pull-request` spell. Read `.arcane/spells/spell-create-pull-request.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-document/SKILL.md

@@ -3,4 +3,4 @@ name: spell-document
 description: Use PROACTIVELY when conversation content (an analysis, a decision, an investigation) should become a permanent reference doc.
 ---
 
-This skill is the Arcane `spell-document` spell. Read `.github/prompts/spell-document.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-document` spell. Read `.arcane/spells/spell-document.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-dotnet-expert/SKILL.md

@@ -3,4 +3,4 @@ name: spell-dotnet-expert
 description: Use PROACTIVELY when working on a .NET project and best-practice guidance is needed.
 ---
 
-This skill is the Arcane `spell-dotnet-expert` spell. Read `.github/prompts/spell-dotnet-expert.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-dotnet-expert` spell. Read `.arcane/spells/spell-dotnet-expert.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-eas-store-deploy/SKILL.md

@@ -3,4 +3,4 @@ name: spell-eas-store-deploy
 description: Use PROACTIVELY when deploying an Expo app to the App Store or Google Play via EAS.
 ---
 
-This skill is the Arcane `spell-eas-store-deploy` spell. Read `.github/prompts/spell-eas-store-deploy.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-eas-store-deploy` spell. Read `.arcane/spells/spell-eas-store-deploy.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-enchant/SKILL.md

@@ -3,4 +3,4 @@ name: spell-enchant
 description: Use PROACTIVELY when a PRD should be enhanced — UX, accessibility, security, performance — before implementation.
 ---
 
-This skill is the Arcane `spell-enchant` spell. Read `.github/prompts/spell-enchant.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-enchant` spell. Read `.arcane/spells/spell-enchant.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-explain-concept/SKILL.md

@@ -3,4 +3,4 @@ name: spell-explain-concept
 description: Use PROACTIVELY when the user needs a concept, architecture, or system behavior explained before deciding or building.
 ---
 
-This skill is the Arcane `spell-explain-concept` spell. Read `.github/prompts/spell-explain-concept.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-explain-concept` spell. Read `.arcane/spells/spell-explain-concept.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-feedback/SKILL.md

@@ -3,4 +3,4 @@ name: spell-feedback
 description: Use PROACTIVELY when the user reports friction with AI assistance or the workflow itself, not the product being built.
 ---
 
-This skill is the Arcane `spell-feedback` spell. Read `.github/prompts/spell-feedback.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-feedback` spell. Read `.arcane/spells/spell-feedback.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-full-cycle/SKILL.md

@@ -3,4 +3,4 @@ name: spell-full-cycle
 description: Use PROACTIVELY for an end-to-end feature request that should chain plan, architect, implement, test, review, and ship.
 ---
 
-This skill is the Arcane `spell-full-cycle` spell. Read `.github/prompts/spell-full-cycle.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-full-cycle` spell. Read `.arcane/spells/spell-full-cycle.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-generate-bot-icons/SKILL.md

@@ -3,4 +3,4 @@ name: spell-generate-bot-icons
 description: Use PROACTIVELY when a bot/agent needs a Teams-ready avatar and icon set generated.
 ---
 
-This skill is the Arcane `spell-generate-bot-icons` spell. Read `.github/prompts/spell-generate-bot-icons.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-generate-bot-icons` spell. Read `.arcane/spells/spell-generate-bot-icons.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-implement/SKILL.md

@@ -3,4 +3,4 @@ name: spell-implement
 description: Use PROACTIVELY to work through stories.json autonomously once architecture and stories exist.
 ---
 
-This skill is the Arcane `spell-implement` spell. Read `.github/prompts/spell-implement.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-implement` spell. Read `.arcane/spells/spell-implement.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-make-discoverable/SKILL.md

@@ -3,4 +3,4 @@ name: spell-make-discoverable
 description: Use PROACTIVELY when auditing a web property's search/AI-assistant discoverability (metadata, robots, sitemap, indexing).
 ---
 
-This skill is the Arcane `spell-make-discoverable` spell. Read `.github/prompts/spell-make-discoverable.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-make-discoverable` spell. Read `.arcane/spells/spell-make-discoverable.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-manifest/SKILL.md

@@ -3,4 +3,4 @@ name: spell-manifest
 description: Use PROACTIVELY in a hub repo to triage idea-book/todo-book entries downstream.
 ---
 
-This skill is the Arcane `spell-manifest` spell. Read `.github/prompts/spell-manifest.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-manifest` spell. Read `.arcane/spells/spell-manifest.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-open-session/SKILL.md

@@ -3,4 +3,4 @@ name: spell-open-session
 description: Use PROACTIVELY at the start of any new session, even if the user just says 'let's start' or asks 'what's next'.
 ---
 
-This skill is the Arcane `spell-open-session` spell. Read `.github/prompts/spell-open-session.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-open-session` spell. Read `.arcane/spells/spell-open-session.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-plan/SKILL.md

@@ -3,4 +3,4 @@ name: spell-plan
 description: Use PROACTIVELY when a feature description needs to become a PRD before architecture or implementation.
 ---
 
-This skill is the Arcane `spell-plan` spell. Read `.github/prompts/spell-plan.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-plan` spell. Read `.arcane/spells/spell-plan.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-present-arcane/SKILL.md

@@ -3,4 +3,4 @@ name: spell-present-arcane
 description: Use PROACTIVELY when asked to present, demo, or explain Arcane itself to an audience.
 ---
 
-This skill is the Arcane `spell-present-arcane` spell. Read `.github/prompts/spell-present-arcane.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-present-arcane` spell. Read `.arcane/spells/spell-present-arcane.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-product-review/SKILL.md

@@ -3,4 +3,4 @@ name: spell-product-review
 description: Use PROACTIVELY when evaluating a shipped feature's real-world performance and deciding next actions.
 ---
 
-This skill is the Arcane `spell-product-review` spell. Read `.github/prompts/spell-product-review.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-product-review` spell. Read `.arcane/spells/spell-product-review.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-review/SKILL.md

@@ -3,4 +3,4 @@ name: spell-review
 description: Use PROACTIVELY before merging any nontrivial change, even if the user doesn't explicitly ask for review.
 ---
 
-This skill is the Arcane `spell-review` spell. Read `.github/prompts/spell-review.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-review` spell. Read `.arcane/spells/spell-review.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-review-batch/SKILL.md

@@ -3,4 +3,4 @@ name: spell-review-batch
 description: Use PROACTIVELY when multiple open PRs need an adversarial review pass and a consolidated go/no-go verdict.
 ---
 
-This skill is the Arcane `spell-review-batch` spell. Read `.github/prompts/spell-review-batch.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-review-batch` spell. Read `.arcane/spells/spell-review-batch.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-save-idea/SKILL.md

@@ -3,4 +3,4 @@ name: spell-save-idea
 description: Use PROACTIVELY to capture a fleeting idea immediately, even if the user just says 'note that' or 'don't forget'.
 ---
 
-This skill is the Arcane `spell-save-idea` spell. Read `.github/prompts/spell-save-idea.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-save-idea` spell. Read `.arcane/spells/spell-save-idea.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-scope/SKILL.md

@@ -3,4 +3,4 @@ name: spell-scope
 description: Use PROACTIVELY when a PRD is too large for one Spell Loop cycle and needs epic-splitting before architecture.
 ---
 
-This skill is the Arcane `spell-scope` spell. Read `.github/prompts/spell-scope.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-scope` spell. Read `.arcane/spells/spell-scope.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-scry/SKILL.md

@@ -3,4 +3,4 @@ name: spell-scry
 description: Use PROACTIVELY when naming anything new (a spell, a field, a product, an internal concept) before committing to it — clears a candidate name against both the outside world and this repository itself.
 ---
 
-This skill is the Arcane `spell-scry` spell. Read `.github/prompts/spell-scry.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-scry` spell. Read `.arcane/spells/spell-scry.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-security-review/SKILL.md

@@ -3,4 +3,4 @@ name: spell-security-review
 description: Use PROACTIVELY before shipping any change that introduces new attack surface, handles sensitive data, or changes trust boundaries.
 ---
 
-This skill is the Arcane `spell-security-review` spell. Read `.github/prompts/spell-security-review.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-security-review` spell. Read `.arcane/spells/spell-security-review.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-ship/SKILL.md

@@ -3,4 +3,4 @@ name: spell-ship
 description: Use PROACTIVELY before any deploy, even if the user just says 'ship it'.
 ---
 
-This skill is the Arcane `spell-ship` spell. Read `.github/prompts/spell-ship.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-ship` spell. Read `.arcane/spells/spell-ship.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-status/SKILL.md

@@ -3,4 +3,4 @@ name: spell-status
 description: Use PROACTIVELY when asked for a quick snapshot of session/repo state — branch, TODOs, decisions, last journal.
 ---
 
-This skill is the Arcane `spell-status` spell. Read `.github/prompts/spell-status.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-status` spell. Read `.arcane/spells/spell-status.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-suggest-feature/SKILL.md

@@ -3,4 +3,4 @@ name: spell-suggest-feature
 description: Use PROACTIVELY when smoke testing or usage surfaces a feature gap worth tracking.
 ---
 
-This skill is the Arcane `spell-suggest-feature` spell. Read `.github/prompts/spell-suggest-feature.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-suggest-feature` spell. Read `.arcane/spells/spell-suggest-feature.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-summon-venture/SKILL.md

@@ -3,4 +3,4 @@ name: spell-summon-venture
 description: Use PROACTIVELY in a hub repo when creating a new venture from scratch.
 ---
 
-This skill is the Arcane `spell-summon-venture` spell. Read `.github/prompts/spell-summon-venture.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-summon-venture` spell. Read `.arcane/spells/spell-summon-venture.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-sync-pull-request/SKILL.md

@@ -3,4 +3,4 @@ name: spell-sync-pull-request
 description: Use PROACTIVELY whenever an open PR has fallen behind its target branch and needs a safe rebase/sync, or when spell-create-pull-request/spell-ship stop on a conflict they route here.
 ---
 
-This skill is the Arcane `spell-sync-pull-request` spell. Read `.github/prompts/spell-sync-pull-request.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-sync-pull-request` spell. Read `.arcane/spells/spell-sync-pull-request.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-test/SKILL.md

@@ -3,4 +3,4 @@ name: spell-test
 description: Use PROACTIVELY to validate a completed story or feature against coverage thresholds before marking it done.
 ---
 
-This skill is the Arcane `spell-test` spell. Read `.github/prompts/spell-test.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-test` spell. Read `.arcane/spells/spell-test.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-todo/SKILL.md

@@ -3,4 +3,4 @@ name: spell-todo
 description: Use PROACTIVELY whenever a raw idea needs to become one or more well-scoped TODO items, even if the user just says 'add a todo'.
 ---
 
-This skill is the Arcane `spell-todo` spell. Read `.github/prompts/spell-todo.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-todo` spell. Read `.arcane/spells/spell-todo.md` and follow it as the complete workflow.

package/dist/assets/.agents/skills/spell-verification-ledger/SKILL.md

@@ -3,4 +3,4 @@ name: spell-verification-ledger
 description: Use PROACTIVELY when a session had real verification events worth a structured record — especially a claim that didn't survive a check.
 ---
 
-This skill is the Arcane `spell-verification-ledger` spell. Read `.github/prompts/spell-verification-ledger.prompt.md` and follow it as the complete workflow.
+This skill is the Arcane `spell-verification-ledger` spell. Read `.arcane/spells/spell-verification-ledger.md` and follow it as the complete workflow.

package/dist/assets/.arcane/governance/development-methodology.md

@@ -196,7 +196,7 @@ Without this chain, agents make conflicting decisions across stories (e.g., one
 3. Check for missing test coverage, architecture violations, security issues
 4. Defer unrelated findings to a backlog (don't derail the current change)
 
-**Enforcement: explicitly advisory prose (ARC-023) — no script counts or verifies lens coverage; this text now matches `spell-review.prompt.md`'s own current Rules section (coverage of effort, not a count of findings) rather than the superseded "minimum of 3" framing an earlier version of this rule stated.**
+**Enforcement: explicitly advisory prose (ARC-023) — no script counts or verifies lens coverage; this text now matches `spell-review.md`'s own current Rules section (coverage of effort, not a count of findings) rather than the superseded "minimum of 3" framing an earlier version of this rule stated.**
 
 ### Append-Only Progress
 
@@ -281,9 +281,9 @@ For features that should run end-to-end with minimal human intervention, use `sp
 spell-full-cycle = spell-plan → [spell-enchant] → spell-architect → [spell-implement → spell-test → spell-review]* → spell-ship
 ```
 
-The entire pipeline runs autonomously with a single human gate at PR approval. Includes optional PRD enchantment between Plan and Architect (runs automatically if any quality dimension scores Bronze, or if `--enchant` is specified). Requires three inputs: feature description, tracking configuration (`tracking_mode` and optional `external_provider`), and target repo. In ADO mode, include the ADO work item ID; in GitHub mode, include the issue number if one already exists. **Each phase has built-in quality gates that halt the pipeline on failure rather than producing garbage for downstream phases. Enforcement: structured spell gate (ARC-023) — `spell-full-cycle.prompt.md` encodes explicit per-phase `Gate:` steps (e.g., Phase 4: "If coverage is below threshold or any acceptance criterion lacks a test, loop back to Phase 3... Maximum 2 coverage-fix loops before halting"; Phase 5: "If any HIGH severity finding exists, loop back to Phase 3... Maximum 2 review-fix loops before halting") plus a human/authority gate before merge.**
+The entire pipeline runs autonomously with a single human gate at PR approval. Includes optional PRD enchantment between Plan and Architect (runs automatically if any quality dimension scores Bronze, or if `--enchant` is specified). Requires three inputs: feature description, tracking configuration (`tracking_mode` and optional `external_provider`), and target repo. In ADO mode, include the ADO work item ID; in GitHub mode, include the issue number if one already exists. **Each phase has built-in quality gates that halt the pipeline on failure rather than producing garbage for downstream phases. Enforcement: structured spell gate (ARC-023) — `spell-full-cycle.md` encodes explicit per-phase `Gate:` steps (e.g., Phase 4: "If coverage is below threshold or any acceptance criterion lacks a test, loop back to Phase 3... Maximum 2 coverage-fix loops before halting"; Phase 5: "If any HIGH severity finding exists, loop back to Phase 3... Maximum 2 review-fix loops before halting") plus a human/authority gate before merge.**
 
-See [.github/prompts/spell-full-cycle.prompt.md](../.github/prompts/spell-full-cycle.prompt.md) for the complete prompt.
+See [.arcane/spells/spell-full-cycle.md](../spells/spell-full-cycle.md) for the complete prompt.
 
 ---
 
@@ -305,9 +305,9 @@ spell-plan → [spell-enchant] → spell-scope → [spell-architect → spell-im
 
 Each epic then runs through its own Spell Loop cycle (architect → implement → test → review → ship).
 
-**Before starting the next epic after a major output checkpoint (execution plan, architecture + stories, full test evidence, or ship recommendation), run `spell-commit-work` to preserve progress and checkpoint branch state. Enforcement: explicitly advisory prose (ARC-023) — `spell-full-cycle.prompt.md`'s Rules section frames this as a recommendation ("recommend running `spell-commit-work` before starting the next epic"), and nothing blocks epic-start if it is skipped.**
+**Before starting the next epic after a major output checkpoint (execution plan, architecture + stories, full test evidence, or ship recommendation), run `spell-commit-work` to preserve progress and checkpoint branch state. Enforcement: explicitly advisory prose (ARC-023) — `spell-full-cycle.md`'s Rules section frames this as a recommendation ("recommend running `spell-commit-work` before starting the next epic"), and nothing blocks epic-start if it is skipped.**
 
-See [.github/prompts/spell-scope.prompt.md](../.github/prompts/spell-scope.prompt.md) for the complete prompt.
+See [.arcane/spells/spell-scope.md](../spells/spell-scope.md) for the complete prompt.
 
 ---
 
@@ -413,4 +413,4 @@ The Spell Loop is a candidate for open-source release as a productized automatio
 2. **Power-level governance** — agents have scoped autonomy per repo
 3. **Git attribution** — every commit traces back to the agent that produced it
 4. **Progressive context chain** — structured planning phases feed each successive phase with richer context
-5. **Spell prompt packaging** — portable `.prompt.md` files that work across AI IDEs
+5. **Spell packaging** — one portable spell file per workflow (`.arcane/spells/*.md`), reaching Copilot, Claude Code and Codex through thin generated shims rather than per-client copies (ARC-045)

package/dist/assets/.arcane/governance/git-conventions.md

@@ -55,7 +55,7 @@ Scope indicates what part of the repo changed. Use singular, lowercase.
 
 | Scope            | Area                                              |
 | ---------------- | ------------------------------------------------- |
-| `prompts`        | `.github/prompts/*.prompt.md`                     |
+| `prompts`        | `.arcane/spells/*.md` (canonical spells) and their generated client shims |
 | `agents`         | `agents/` directory, agent config, policies       |
 | `security`       | `security/` directory, threat model, hardening    |
 | `infrastructure` | `infrastructure/` directory, hardware, OS setup   |
@@ -116,7 +116,7 @@ messages with proper type and scope.
 Implements ADR-019 spell- naming convention.
 
 Changes:
-- Created .github/prompts/spell-commit-work.prompt.md
+- Created .arcane/spells/spell-commit-work.md
 - Created governance/git-conventions.md as reference doc
 - Updated TODO.md to mark git conventions doc complete
 ```

package/dist/assets/.arcane/governance/portable-bootstrap.md

@@ -52,6 +52,7 @@ Paste this entire file into any AI client (Claude web, ChatGPT, etc.) to give it
 ## Where Documents Live
 
 - **Framework-managed standards:** `.arcane/governance/`. Spells reference this single installed layer; **do not create a duplicate root `governance/` tree. Enforcement: explicitly advisory prose (ARC-023) — no check scans a repo for a duplicate root-level `governance/` directory.**
+- **Framework-managed spells:** `.arcane/spells/<id>.md` is each spell's one authored source (ARC-045). The files each AI client discovers — `.github/prompts/<id>.prompt.md` for Copilot, `.claude/commands/<id>.md` for Claude Code, `.agents/skills/<id>/SKILL.md` for Codex — are thin generated shims that point back at it; edit the canonical file, never a shim. **Enforcement: executable check (ARC-023) — `npm run check:self-host-parity` re-renders every shim from its canonical file and fails on any difference; `spell update` keeps a hand-edited shim untouched and names it rather than merging into it.** The same canonical spells can also be installed once per machine — `spell init --user` puts them at `~/.arcane/spells/<id>.md` with one Codex/Copilot skill under `~/.agents/skills/` and one Claude Code command under `~/.claude/commands/` per spell (ARC-045 decision 3); governance never moves up a tier.
 - **Project-owned orientation and continuity:** `README.md`, `project.md`, `TODO.md`, `DECISIONS.md`, `ai-context/`, and `journal/`. Arcane creates missing files once and preserves existing content.
 - **Project/domain documents:** use explicit descriptive paths such as `docs/`, `security/`, `infrastructure/`, or a configured business root. These add project context alongside framework standards.
 - **Overrides survive `arcane update`:** editing a managed `.arcane/governance/` standard no longer risks silent loss. Additive project documents were always safe; a hand-edit to a shipped standard now is too. **Enforcement: executable check (ARC-038, shipped BC-31)** — `spell update` compares each file's on-disk content against its recorded hash at install time: unchanged, it refreshes normally; edited, it fetches the exact previously-installed published version as a three-way merge base against your edit and the new vendor content, auto-merging non-overlapping changes and leaving standard conflict markers only on genuine collisions. If the prior published version can't be fetched, your edit is left untouched with a warning rather than replaced.

package/dist/assets/.arcane/governance/product-excellence-standards.md

@@ -11,7 +11,7 @@ tags:
 
 ## Purpose
 
-Define what "the best version of an app" means across every dimension — UX, accessibility, performance, security, and polish. This document provides the **PRD Quality Scorecard** that [[.github/prompts/spell-enchant.prompt|spell-enchant]] evaluates against when enchanting a PRD from functional to exceptional.
+Define what "the best version of an app" means across every dimension — UX, accessibility, performance, security, and polish. This document provides the **PRD Quality Scorecard** that [[.arcane/spells/spell-enchant|spell-enchant]] evaluates against when enchanting a PRD from functional to exceptional.
 
 ## Quality Dimensions
 

package/dist/assets/.arcane/governance/spell-authoring-standards.md

@@ -48,7 +48,7 @@ this broader ≥ Silver gate is not fully verified by any coded scorer or workfl
 
 | Tier | Bar |
 | --- | --- |
-| Bronze | No real organization, person, venture, or machine names. Org-specific values use `{UPPER_SNAKE}` placeholders. Enforcement: executable check (ARC-023) — `scripts/org-token-lint.ts` scans `.github/prompts/*.prompt.md` against the `ARCANE_ORG_TOKENS` denylist and runs automatically as part of `npm run build`, failing the build on a match; `spell ward --gate` (`src/commands/ward.ts`) runs the same denylist-scanning engine standalone but is not currently wired into CI as its own gate. |
+| Bronze | No real organization, person, venture, or machine names. Org-specific values use `{UPPER_SNAKE}` placeholders. Enforcement: executable check (ARC-023) — `scripts/org-token-lint.ts` scans `.arcane/spells/*.md` (and every generated client shim) against the `ARCANE_ORG_TOKENS` denylist and runs automatically as part of `npm run build`, failing the build on a match; `spell ward --gate` (`src/commands/ward.ts`) runs the same denylist-scanning engine standalone but is not currently wired into CI as its own gate. |
 | Silver | + every placeholder has an inline resolution note: *"resolve from `.arcane.json` / frontmatter; ask if unset."* Enforcement: explicitly advisory prose (ARC-023) — part of the D2 hard gate by name, but this specific bar is self-graded; no check verifies a placeholder carries an inline resolution note. |
 | Gold | + no hard assumption of a specific tracker, CI/CD platform, cloud/deployment vendor, agent roster, or directory layout — the spell works in a vanilla consuming repo with no Arcane context files present. |
 
@@ -118,6 +118,14 @@ this broader ≥ Silver gate is not fully verified by any coded scorer or workfl
 
 Arcane spells ship to other repositories and, eventually, open source. Keep them portable:
 
+- **Author in one place (ARC-045):** a spell's body lives only in `.arcane/spells/<id>.md`. The
+  Copilot prompt (`.github/prompts/<id>.prompt.md`), the Claude Code command
+  (`.claude/commands/<id>.md`) and the Codex skill (`.agents/skills/<id>/SKILL.md`) are generated
+  from it by `npm run fix:self-host-parity` and carry no prose of their own — never edit one by
+  hand. Relative links inside a spell resolve from `.arcane/spells/`, two levels below the repo
+  root (`../../.arcane/governance/…`, `../../README.md`); refer to a sibling spell as
+  `spell-x.md`. Enforcement: executable check (ARC-023) — `npm run check:self-host-parity`
+  re-renders every shim from its canonical file and fails CI on any byte of difference.
 - **Never hard-code** an org name, person, venture, product, or machine name. Use a documented
   `{UPPER_SNAKE}` placeholder: `{ADO_ORG}`, `{ADO_PROJECT}`, `{BUSINESS_NAME}`, `{OPERATOR_NAME}`.
   Enforcement: executable check (ARC-023) — same mechanism as D2 Bronze above: the `org-token-lint`

package/dist/assets/.arcane/governance/universal-agent-rules.md

@@ -156,6 +156,8 @@ See also: [[README]], [[DECISIONS]], [[governance/git-conventions|Git Convention
 | Any new tool | This file | Read this, then follow links above |
 
 This table covers standing repository instructions only, not spell discovery. Spells reach each
-client through a separate mechanism: `.github/prompts/*.prompt.md` for Copilot,
-`.claude/commands/*.md` for Claude Code, and `.agents/skills/*/SKILL.md` for Codex (CS-01) — all
-three generated from one canonical source (ARC-039), never hand-authored per client.
+client through a separate mechanism: one canonical source per spell at `.arcane/spells/<id>.md`
+(ARC-045), from which three thin shims are generated — `.github/prompts/*.prompt.md` for Copilot,
+`.claude/commands/*.md` for Claude Code, and `.agents/skills/*/SKILL.md` for Codex (CS-01) — never
+hand-authored per client. A shim carries no workflow of its own: when a spell must be read in full,
+read the canonical file.

package/dist/assets/.arcane/spells/spell-address-review.md

@@ -0,0 +1,115 @@
+---
+name: Spell — Address Review
+description: Respond to code-review feedback on a pull request — fetch comment threads, triage each, implement fixes or reply with rationale, and resolve every thread.
+claude_description: Use PROACTIVELY whenever responding to PR review comments — fetch threads, triage, fix or reply, resolve.
+argument-hint: --pr <number> (required) [--fix-all] — the PR to address; --fix-all treats all suggestions/nitpicks as fix-now
+agent: agent
+---
+
+## Executive Summary
+
+- This spell handles inbound code-review feedback: read comments, act on them, and resolve the threads.
+- Each comment is triaged — must-fix / suggestion / question / nitpick — and given a disposition.
+- Must-fix items are implemented, committed, and pushed; others are implemented or answered with rationale.
+- Every thread is resolved at the end (many providers require all threads resolved before merge).
+- This is the author-side counterpart to `spell-review` (the reviewer side). Provider-agnostic.
+
+---
+
+Respond to review feedback for the specified pull request.
+
+Context to consult:
+
+- `.arcane/governance/git-conventions.md` — commit format, agent attribution trailers, PR policy, and the interactive-session commit gate.
+- `.arcane/governance/development-methodology.md` — workflow phases.
+
+Related spells:
+
+- `spell-review` — the reviewer side. If review was run here, its findings carry stable IDs (`R1`, `R2`, …); reference those IDs when replying so each thread maps to the original finding.
+- `spell-create-pull-request` — opens the PR this spell responds to. Run it first if no PR exists yet.
+
+## Arguments
+
+- `--pr <number>` — **required.** The PR to address. If omitted, check the current branch for an associated PR or ask the user.
+- `--fix-all` — optional. Treat all suggestions and nitpicks as fix-now (no deferrals).
+
+## Step 0 — Setup
+
+1. **Resolve the PR.** If `--pr` is given, use it. If omitted, look up the PR for the current branch (`gh pr view --json number` / `az repos pr list --source-branch <branch>`). If still none, **stop** and ask the user for the PR number — do not guess.
+2. **Working tree must be clean.** Run `git status`. If dirty, **stop** and ask the user to commit or stash first — never stash silently, since uncommitted work can get tangled into the review-fix commits below.
+3. **Detect the provider** from the git remote:
+
+   | Remote URL contains | Provider |
+   | --- | --- |
+   | `github.com` | GitHub (`gh`) |
+   | `dev.azure.com` / `visualstudio.com` | Azure DevOps (`az repos`) |
+   | anything else | unknown — **stop** and ask the user |
+
+4. **Fetch the PR plus all comment threads:**
+   - **GitHub:** `gh pr view <PR> --comments`
+   - **Azure DevOps:** `az repos pr thread list --id <PR>`
+
+## Step 1 — Parse threads
+
+For each thread extract: thread ID, author, file + line (if inline), comment text, status, existing replies. Keep only **active** threads; ignore already-resolved ones. If a comment references a `spell-review` finding ID (`R1`, …), carry it through so the reply can cite it.
+
+**If zero active threads remain:** report "No active review threads to address — nothing to do" and stop. Do not create commits or push.
+
+## Step 2 — Categorize each comment
+
+| Category | Criteria | Action |
+| --- | --- | --- |
+| must-fix | bug, security issue, logic error, broken behavior, standards violation | implement, commit, push |
+| suggestion | better approach, refactor, optional improvement | implement OR reply with rationale |
+| question | clarification / "why did you…?" | answer in the thread |
+| nitpick | minor style / naming preference | implement OR reply with rationale |
+
+Heuristics: "must"/"should"/"required"/"blocking" → must-fix; ends with "?" or starts "why/how/what" → question; "nit"/"minor"/"optional"/"consider" → nitpick; alternative offered without requiring → suggestion. When unsure, escalate to suggestion (not nitpick).
+
+## Step 3 — Disposition
+
+| Disposition | When |
+| --- | --- |
+| Fix Now | all must-fix; suggestions/nitpicks < ~30 min effort AND within files the PR already touches |
+| Defer | scope-expanding items: new features, infra/tooling, cross-file refactors, > ~1 hr effort |
+| Decline | the current approach is intentional — reply with rationale |
+
+`--fix-all` forces all suggestions/nitpicks to Fix Now. Deferred items get a `TODO.md` entry with a `(PR #<n> feedback)` note **and** a reply on the thread pointing to that TODO before the thread is resolved — never resolve a deferred thread silently, or the reviewer cannot tell it was tracked vs. ignored.
+
+## Step 4 — Present the plan, then wait
+
+Show a table (`# | category | disposition | author | file:line | summary | planned action`) plus counts. Wait for confirmation; let the user reclassify any item before proceeding.
+
+## Step 5 — Execute
+
+Commits in this spell follow `.arcane/governance/git-conventions.md`: Conventional Commits format, agent attribution (`--author` + required `Agent`/`Model`/`Model-Source`/`Provider` trailers, plus `Persona`/`Role` when a roster exists and one was assigned) when an agent authors the change, and — because this is an **interactive session** — present each proposed commit message and **wait for the human's approval before committing** (the Step 4 plan approval covers *what* to do, not the commit itself). Never squash.
+
+For **must-fix** (one thread at a time): read the code → implement → run the relevant tests.
+- **If tests pass:** commit (e.g. `fix(scope): address review — <desc>`) → reply `Fixed in <hash>. <what changed>` (cite the `R#` finding ID if one exists) → resolve the thread immediately.
+- **If tests fail:** do **not** commit. Either fix the regression and re-run, or — if the fix is wrong or larger than expected — revert the change, reply on the thread explaining what blocked it, and reclassify to Defer (TODO + thread note). A broken must-fix must never land.
+
+For **suggestions/nitpicks**: if implementing, make the change, run tests, and batch into one commit; reply and resolve. If declining, reply with specific, respectful rationale (reference an ADR or convention if relevant) and resolve as won't-fix.
+
+For **questions**: answer clearly in the thread; if the question reveals a real issue, reclassify and handle it; resolve after answering.
+
+Resolve threads via the provider:
+- **GitHub:** resolve the review thread (`gh` / GitHub MCP resolve-thread).
+- **Azure DevOps:** update the thread status (`Fixed` or `WontFix`).
+- **If a thread cannot be auto-resolved** (provider API error, insufficient permissions, or the reviewer must resolve it themselves): leave the reply in place, list the thread in the Step 6 report under "needs manual resolution," and do not treat the sweep as complete.
+
+## Step 6 — Sweep, push, report
+
+1. Re-fetch threads; resolve any still-active ones (this is the merge gate on many providers). Any thread that genuinely cannot be auto-resolved (see Step 5) is reported as "needs manual resolution," not silently left open.
+2. `git push` all commits.
+3. Print a summary table of actions taken (category, file, action, commit), thread status (resolved / deferred-with-TODO / needs manual resolution), commits pushed, and next steps (CI, notify reviewer, ready for re-review).
+4. Optionally post the summary back to the PR as a top-level comment for a durable record.
+
+## Rules
+
+- Always present the plan and wait for confirmation before changing code.
+- This is an interactive session: get human approval for each commit message before committing (per git-conventions Commit Governance).
+- Never commit a change whose tests fail — fix, revert, or defer instead.
+- Resolve each thread immediately after addressing it — do not batch resolution to the very end (except the final sweep).
+- Never dismiss feedback without reasoning, and never resolve a deferred thread without leaving a TODO pointer on it.
+- Follow `.arcane/governance/git-conventions.md` for commit format and attribution; do not squash.
+- Never include secrets or tokens in replies or commits.