@softspark/ai-toolkit 4.14.1 → 4.15.0

package/CHANGELOG.md

@@ -7,6 +7,34 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v4.15.0 — Native Codex and Copilot parity (2026-07-14)
+
+Minor release. Rebuilds the Codex CLI and GitHub Copilot integrations around their current native instruction, agent, skill, hook, and MCP surfaces. It also hardens managed-file migration and multi-file configuration updates so toolkit refreshes preserve user-owned content and fail without leaving partial state. No source catalog count change (44 agents, 108 skills).
+
+### Added
+- **Codex native custom agents** — `scripts/generate_codex_agents.py` materializes all 44 source agents as validated `.codex/agents/ai-toolkit-*.toml` files with native `name`, `description`, and `developer_instructions` fields. Logical-name collisions, unmanaged files, stale symlinks, and staging failures preserve user content.
+- **Complete Codex skill delivery** — project installs expose all 108 skills under `.agents/skills/`: 51 portable skills link to their canonical source and 57 Claude-specific skills receive self-contained, signature-free Codex adaptations with required assets retained.
+- **Self-contained Codex hooks** — project and user installs emit schema-validated `.codex/hooks.json` plus native runtime assets under `.codex/hooks/` or `$CODEX_HOME/ai-toolkit-hooks/`. Managed handlers merge idempotently with user hooks and keep Codex trust review explicit.
+- **Copilot native customization bundle** — project installs now generate all 44 native `.agent.md` agents, all 108 materialized portable skills, 62 slash-command `.prompt.md` files, and scoped instruction files under `.github/`. User installs provide instructions, agents, and skills under `$COPILOT_HOME`; prompt files remain repository-scoped.
+- **Copilot native lifecycle hooks** — `scripts/generate_copilot_hooks.py` writes GitHub version-1 hook configuration and a self-contained runtime with native camelCase events, event-specific decisions, destructive-command/path guards, quality gates, and a bounded stop-loop circuit breaker.
+- **Codex project and user MCP** — MCP templates now render validated STDIO or Streamable HTTP `[mcp_servers.*]` tables into project `.codex/config.toml` and user `$CODEX_HOME/config.toml`, while preserving unrelated TOML text and comments.
+
+### Changed
+- **One shared instruction and constitution core** — Codex and Copilot `AGENTS.md` output now comes from `scripts/instruction_core.py` and the canonical `app/constitution.md`. Agent and skill catalogs are discovered from native directories instead of being duplicated into always-on instructions.
+- **Portable skill translation** — Codex, Copilot, and opencode adapters replace Claude-only tools, prompt placeholders, and skill-directory variables with runtime-neutral workflow intent instead of guessed client function signatures. opencode commands retain native `$ARGUMENTS` and positional argument behavior.
+- **Profile-aware Copilot install model** — project `minimal` installs agents and skills; `standard`, `strict`, and `full` additionally install instructions, prompts, and native hooks. User installs always provide instructions, agents, and skills, with hooks enabled from `standard` upward. `COPILOT_HOME` replaces the default user root consistently.
+- **Release workflow runtime** — pinned `softprops/action-gh-release` to the reviewed v3.0.2 commit for the Node 24 action runtime.
+
+### Fixed
+- **Rules and constitution enforcement gaps** — current Codex and Copilot instruction files now receive the same always-on policy derived from the canonical constitution, eliminating stale or unread duplicated rule catalogs.
+- **Managed marker migration** — instruction injection handles nested, crossed, orphaned, empty legacy, and Unicode section markers without consuming adjacent user-authored content.
+- **Transactional MCP updates** — canonical `.mcp.json` and all requested native editor configs are preflighted and applied as one atomic transaction. Invalid JSON/TOML, symlinked destinations, concurrent changes, or a late replace failure leave prior files byte-identical or trigger an explicit rollback failure.
+- **Managed output safety** — native generators stage and validate replacements, reject symlinked roots, preserve reserved user collisions and unmanaged files, and remove only files carrying ai-toolkit ownership markers.
+
+### Ecosystem
+- **Class B/F — Codex CLI**: adopted native custom-agent TOML, current skill discovery, the documented hook schema and trust model, project/user configuration layers, `$CODEX_HOME`, and project-scoped MCP from the current OpenAI documentation.
+- **Class B/F — GitHub Copilot**: adopted repository and user custom agents, prompt files, instruction files, portable skills, version-1 hooks, `$COPILOT_HOME`, and `.github/mcp.json` from the current GitHub documentation.
+
 ## v4.14.1 — Keep fact-checker on Sonnet (2026-07-14)
 
 Patch release. Reverts one of the two agent model reassignments from v4.14.0: `fact-checker` goes back to `model: sonnet`. Claim verification is accuracy-sensitive and Haiku's recall on subtle claims did not justify the cost saving. `explorer-agent` (pure read/search) stays on `model: haiku`. No count change (44 agents, 108 skills, 1216 tests).

package/README.md

@@ -6,16 +6,17 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Skills](https://img.shields.io/badge/skills-108-brightgreen)](app/skills/)
 [![Agents](https://img.shields.io/badge/agents-44-blue)](app/agents/)
-[![Tests](https://img.shields.io/badge/tests-1216%20passing-success)](tests/)
+[![Tests](https://img.shields.io/badge/tests-1367%20passing-success)](tests/)
 
-## What's New in v4.14.1
+## What's New in v4.15.0
 
-v4.14.1 refreshes Claude model IDs to the current generation, makes model routing effort-aware, and tunes agent model tiers.
+v4.15.0 brings the Codex CLI and GitHub Copilot integrations onto their current native customization surfaces and closes the gaps that caused rules, agents, skills, or hooks to be ignored.
 
-- **Current model IDs**: `scripts/_common.py` now resolves `opus → claude-opus-4-8` and `sonnet → claude-sonnet-5` (the single source of truth generators emit); stale `claude-opus-4-7` samples across skills refreshed.
-- **Effort-aware routing**: `model-routing-patterns` gains an Effort section — tuning `output_config.effort` is the cheaper lever before swapping models, and it does not invalidate the prompt cache the way a mid-session model swap does.
-- **Fable 5 tier documented**: added to the routing table with pricing and a "not the default best model" caveat — for "strongest model", the target stays `claude-opus-4-8`.
-- **Agent tiers tuned**: `explorer-agent` (pure read/search) runs on `model: haiku`; `fact-checker` stays on `model: sonnet` — accuracy over cost for claim verification.
+- **Native Codex bundle**: emits the shared constitution-backed `AGENTS.md`, 44 custom-agent TOML files, all 108 skills, self-contained lifecycle hooks, and project/user MCP configuration.
+- **Native Copilot bundle**: project installs emit 44 `.agent.md` agents, all 108 portable skills, 62 `.prompt.md` commands, scoped instructions, version-1 hooks, and MCP configuration; personal instructions, agents, skills, hooks, and MCP live below `$COPILOT_HOME` (default `~/.copilot`).
+- **One policy source**: Codex and Copilot instructions now derive from `app/constitution.md`; agent and skill catalogs stay in native discovery directories instead of bloating always-on context.
+- **Safer managed updates**: user-owned collisions and symlinks are preserved or rejected, while canonical `.mcp.json` and editor configs use preflighted multi-file updates with rollback on late failures.
+- **Native config roots**: Codex hooks and MCP honor `$CODEX_HOME`; Copilot user instructions, agents, skills, and hooks consistently honor `$COPILOT_HOME`. Symlinked configuration roots are rejected.
 
 See [CHANGELOG.md](CHANGELOG.md) for full history.
 
@@ -120,13 +121,13 @@ See [CLI Reference](kb/reference/cli-reference.md) for all commands and options.
 | Cursor | `.cursor/rules/*.mdc` + `.cursor/mcp.json` + `.cursor/skills/*` | ✅ | project (`~/.cursor/mcp.json` for MCP only) |
 | Windsurf (Devin Desktop) | `~/.config/devin/AGENTS.md` + `.devin/rules/*.md` + `.devin/hooks.v1.json` + `.windsurf/skills/*` | ✅ | global + project |
 | Gemini CLI | `~/.gemini/GEMINI.md` | ✅ | global |
-| GitHub Copilot | `.github/copilot-instructions.md` + `.github/instructions/*` + `.github/prompts/*` + `AGENTS.md` | — | project |
+| GitHub Copilot | Project: `AGENTS.md` + `.github/copilot-instructions.md` + `.github/{instructions,prompts,agents,skills,hooks}/` + `.github/mcp.json`; user: `$COPILOT_HOME/copilot-instructions.md` + `$COPILOT_HOME/{instructions,agents,skills,hooks}/` + `$COPILOT_HOME/mcp-config.json` | ✅ | project + user |
 | Cline | `~/Documents/Cline/Rules/*.md` + `~/.cline/skills/*` + `.clinerules/*.md` | — | global + project |
 | Roo Code | `~/.roo/rules/*.md` + `.roomodes` + `.roo/rules/*.md` | — | global rules + project |
 | Aider | `~/.aider.conf.yml` + `.aider.conf.yml` + `CONVENTIONS.md` | — | global + project |
 | Augment | `~/.augment/rules/*.md` + `.augment/rules/ai-toolkit-*.md` | ✅ | global + project |
 | Google Antigravity | `.agents/rules/*.md` + `.agents/workflows/*.md` + skill pointer in `.agent/skills/*` (IDE) and `.agents/skills/*` (CLI) | — | project |
-| Codex CLI | `AGENTS.md` (coding rules inlined) + `.agents/skills/*` + `.codex/hooks.json` | ✅ | project + global plugin |
+| Codex CLI | Project: `AGENTS.md` + `.agents/skills/*` + `.codex/{agents,hooks}/` + `.codex/{hooks.json,config.toml}`; user: `$CODEX_HOME/{AGENTS.md,agents,hooks.json,config.toml}` + `$HOME/.agents/skills/*` | ✅ | project + user |
 | opencode | `AGENTS.md` + `.opencode/{agents,commands,plugins}/*` + `opencode.json` | ✅ | project + global (`~/.config/opencode/`) |
 
 > Claude Code is always installed (primary platform). Other editors are selected with `--editors`; the Claude app uses the separate `claude-app export` flow because its customization store is UI/plugin-managed. The **Hooks** column marks platforms with lifecycle enforcement. Platforms marked — receive guidance without blocking hooks.
@@ -165,7 +166,7 @@ ai-toolkit/
 │   └── ARCHITECTURE.md  # Full system design
 ├── kb/                  # Reference docs, procedures, plans
 ├── scripts/             # Validation, install, evaluation scripts
-├── tests/               # Bats test suite (1216 tests)
+├── tests/               # Bats test suite (1367 tests)
 └── CHANGELOG.md
 ```
 

package/app/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "ai-toolkit",
   "displayName": "AI Toolkit",
   "description": "Professional-grade engineering skills, agents, rules, and lifecycle guardrails for Claude Code, Claude Chat, and Cowork.",
-  "version": "4.14.1",
+  "version": "4.15.0",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/CLAUDE.md.template

@@ -19,5 +19,8 @@
 ## Key Conventions
 <!-- Only non-obvious rules that can't be inferred from code -->
 
+## Project Constitution
+@.claude/constitution.md
+
 ## MCP Servers
 <!-- Which servers are configured and one-line when to use each -->

package/app/hooks/_search-capability.sh

@@ -10,8 +10,9 @@ ai_toolkit_search_first_mode() {
 }
 
 ai_toolkit_has_search_provider() {
-    local mode
+    local mode codex_home
     mode="$(ai_toolkit_search_first_mode)"
+    codex_home="${CODEX_HOME:-$HOME/.codex}"
     case "$mode" in
         off|false|0|disabled|none)
             return 1
@@ -46,7 +47,7 @@ ai_toolkit_has_search_provider() {
     done
 
     local toml_candidates=(
-        "$HOME/.codex/config.toml"
+        "$codex_home/config.toml"
     )
     for path in "${toml_candidates[@]}"; do
         [ -f "$path" ] || continue

package/app/hooks/stop-search-check.sh

@@ -33,7 +33,8 @@ fi
 
 ai_toolkit_codex_log_has_search_since() {
     local flag="$1"
-    local log="$HOME/.codex/log/codex-tui.log"
+    local codex_home="${CODEX_HOME:-$HOME/.codex}"
+    local log="$codex_home/log/codex-tui.log"
     [ -f "$log" ] || return 1
 
     python3 - "$flag" "$log" <<'PY' 2>/dev/null

package/benchmarks/ecosystem-doctor-snapshot.json

@@ -1,5 +1,5 @@
 {
-  "last_run": "2026-07-10T06:43:18Z",
+  "last_run": "2026-07-15T05:28:09Z",
   "schema_version": 1,
   "tools": {
     "aider": {
@@ -24,7 +24,7 @@
       }
     },
     "augment": {
-      "docs_hash": "880db45231fef284",
+      "docs_hash": "480f89501d47f5ec",
       "headings": [
         "Admin",
         "Auggie CLI",
@@ -66,10 +66,11 @@
       }
     },
     "claude-app": {
-      "docs_hash": "bd1483491a8a64e2",
+      "docs_hash": "01981c240e67db02",
       "headings": [
         "Add global and folder instructions",
         "Availability",
+        "Choose how Claude checks with you",
         "Claude Cowork plugins",
         "Claude stopped working on my task",
         "Current limitations",
@@ -87,8 +88,6 @@
         "I'm hitting usage limits quickly",
         "I'm seeing "Setting up Claude's workspace" when I start Cowork; what does this mean?",
         "Key capabilities",
-        "Permission modes",
-        "Permissions",
         "Permissions and security",
         "Requirements",
         "Research and analysis",
@@ -108,7 +107,7 @@
       }
     },
     "claude-code": {
-      "docs_hash": "50b46c4f57d16b9e",
+      "docs_hash": "517ae09f5f1feba9",
       "headings": [
         "Core concepts",
         "Documentation Index",
@@ -164,10 +163,10 @@
         "slash command": true,
         "sub-agent": true
       },
-      "version": "2.1.206 (Claude Code)"
+      "version": "2.1.210 (Claude Code)"
     },
     "cline": {
-      "docs_hash": "1726cf1ff3f402b6",
+      "docs_hash": "9a024e9356105f48",
       "headings": [
         "API Reference",
         "Best Practices",
@@ -214,80 +213,120 @@
       }
     },
     "codex-cli": {
-      "docs_hash": "46073353f24772e6",
+      "docs_hash": "cc18a01c239497e8",
       "headings": [
         "API",
         "API Reference",
         "Advertiser API",
         "Agent configuration",
         "Agents SDK",
+        "Audio",
         "Available on",
         "Blog",
+        "Bring visual context into the prompt",
         "Build",
+        "Build a terminal workflow around Codex",
+        "Build tool workflows",
         "Build with Codex",
         "Capabilities",
         "Categories",
-        "Chats",
-        "Choose the right GPT-5.6 model",
+        "ChatGPT web",
+        "ChatKit",
+        "Choose a model",
         "Codex Security",
+        "Codex cloud",
         "Community",
+        "Compose with scripts and CI",
+        "Computer and code",
         "Config file",
-        "Continue a task on another host",
+        "Connect external tools with MCP",
+        "Connect tools and data",
+        "Connection methods",
         "Contribute",
         "Conversion apps",
         "Core Concepts",
         "Core concepts",
+        "Cost and throughput",
         "Customization",
         "Deploy",
         "Deployment and model providers",
+        "Desktop app",
         "Development workflows",
         "Docs agent",
         "Environments",
-        "Evaluation",
         "Events",
         "Explore",
         "Extend ChatGPT and Codex",
         "Extend and automate",
         "File Upload",
+        "Fit Codex to your terminal",
         "Foundations",
         "Get started",
+        "Get started with Codex CLI",
         "Getting started",
-        "Going live",
+        "Go live",
         "Guides",
+        "IDE extension",
         "Identity and authentication",
+        "Images and video",
+        "Infrastructure and access",
+        "Inspect, edit, and run code from your terminal",
+        "Install Codex",
+        "Keep the coding loop in your terminal",
         "Legacy APIs",
         "Measurement",
-        "Overview",
+        "Media",
+        "Move work to Codex cloud",
+        "Operations",
+        "Other ChatGPT and Codex surfaces",
+        "Performance and quality",
         "Permissions",
         "Plan",
         "Plugin and connector controls",
         "Programs",
-        "Projects",
+        "Prompting",
         "Realtime and audio",
+        "Reasoning",
         "Recent",
         "Reference",
         "Releases",
         "Resources",
-        "Run and scale",
+        "Return to a saved session",
+        "Review changes before they ship",
+        "Run Codex and sign in",
+        "SDKs and CLI",
         "Safety",
+        "Safety and governance",
+        "Search and retrieval",
+        "Search for current context",
         "Search the docs",
+        "See what Codex CLI can do",
+        "Sessions and operations",
+        "Set the boundaries for each run",
         "Spaces",
         "Specialized models",
+        "Split up a larger investigation",
+        "Start your first task",
+        "Stay in control",
         "Suggested",
-        "Take on ambitious work with ChatGPT Work",
+        "Text and code",
         "Third-party integrations",
-        "Tools",
         "Topics",
-        "Turn demonstrated workflows into reusable skills",
         "Usage, governance, and compliance",
-        "What should we get done?",
-        "What\u2019s new",
+        "Use Codex CLI when\u2026",
+        "Use skills and plugins",
         "Windows",
+        "Work against your local repository",
         "Workflows",
-        "Workspace access, policy, and models"
+        "Workspace access, policy, and models",
+        "You need scripting or CI",
+        "You want a local code review",
+        "You want to hand work to the cloud",
+        "You work from the terminal"
       ],
       "markers": {
         ".agents/skills": false,
+        ".codex/agents": false,
         "AGENTS.md": true,
         "config.toml": false,
         "hook event: PermissionRequest": false,
@@ -307,10 +346,10 @@
         "mcp_servers": false,
         "sandbox": true
       },
-      "version": "codex-cli 0.144.1"
+      "version": "codex-cli 0.144.4"
     },
     "cursor": {
-      "docs_hash": "63246f9f6c354976",
+      "docs_hash": "34efb96589c7f123",
       "headings": [],
       "markers": {
         ".cursor/rules": false,
@@ -326,7 +365,7 @@
       }
     },
     "gemini-cli": {
-      "docs_hash": "7a28426194187480",
+      "docs_hash": "c24d346e0c5a1bb9",
       "headings": [
         "Breadcrumbs",
         "Directory actions",
@@ -369,7 +408,7 @@
       }
     },
     "github-copilot": {
-      "docs_hash": "788efbd31f39bd11",
+      "docs_hash": "58d9980c29b7edb8",
       "headings": [
         "About Copilot auto model selection",
         "About Copilot automations",
@@ -391,6 +430,7 @@
       ],
       "markers": {
         "AGENTS.md": false,
+        "CLI hooks": false,
         "Copilot Chat": true,
         "Copilot Workspace": false,
         "Copilot cloud agent": true,
@@ -399,11 +439,13 @@
         "copilot-instructions.md": false,
         "custom agents": true,
         "instructions.md": false,
-        "prompt files": true
+        "prompt files": true,
+        "skills": true,
+        "~/.copilot/": false
       }
     },
     "google-antigravity": {
-      "docs_hash": "e484097e498581f4",
+      "docs_hash": "9c9b420a22b35ae6",
       "headings": [],
       "markers": {
         "AGENTS.md": false,
@@ -419,7 +461,7 @@
       }
     },
     "opencode": {
-      "docs_hash": "8713591669c1683f",
+      "docs_hash": "505b9771a6c768e6",
       "headings": [
         "Add features",
         "Ask questions",
@@ -479,7 +521,7 @@
       }
     },
     "windsurf": {
-      "docs_hash": "93e7f46747f42e11",
+      "docs_hash": "2d4eb599c906bf2c",
       "headings": [
         "Accounts",
         "Advanced",

package/kb/procedures/maintenance-sop.md

@@ -1,15 +1,15 @@
 ---
-title: "SOP: Claude Toolkit Maintenance"
+title: "SOP: AI Toolkit Maintenance"
 category: procedures
 service: ai-toolkit
 tags: [sop, maintenance, agents, skills, install]
-version: "3.2.0"
+version: "3.3.0"
 created: "2026-03-23"
-last_updated: "2026-07-10"
+last_updated: "2026-07-14"
 description: "Standard operating procedures for installing, maintaining, and evolving the ai-toolkit."
 ---
 
-# SOP: Claude Toolkit Maintenance
+# SOP: AI Toolkit Maintenance
 
 ## Init Repository (New Project)
 
@@ -45,7 +45,11 @@ ai-toolkit install --local --lang python --editors all  # language rules propaga
 
 When `--editors` is combined with `--lang` (or auto-detected languages), language rules are propagated to all configured editors as `ai-toolkit-lang-<lang>` files — not just Claude's `CLAUDE.md`. Similarly, registered custom rules (`~/.softspark/ai-toolkit/rules/`) are propagated to directory-based editor configs as `ai-toolkit-custom-<name>` files.
 
-**Note:** Hooks are global-only — merged into `~/.claude/settings.json` by `ai-toolkit install`. Project-local `--local` does not install hooks; any legacy `.claude/hooks.json` is removed automatically.
+**Note:** Claude Code hooks are global-only and merge into
+`~/.claude/settings.json`; any legacy `.claude/hooks.json` is removed. Editors
+with documented repository hook surfaces may receive local native files. Codex
+uses `.codex/hooks.json` plus `.codex/hooks/*`; Copilot profile `standard` and
+above uses `.github/hooks/ai-toolkit.json` plus its adjacent runtime.
 
 **Input validation (v1.4.2):** `--only`, `--skip`, `--editors`, and `--lang` are validated on input; an invalid value exits with a clear error before any changes are made.
 
@@ -112,14 +116,16 @@ updates. Skills work in Chat and Cowork. Hooks and sub-agents run only in Cowork
 
 ### Install Profiles (v3.0.0)
 
-| Profile | Claude Code core | Editor rules | Gemini hooks | Copilot dir layout | Per-editor hooks / sub-agents / commands | Git hooks |
-|---------|:---------------:|:------------:|:------------:|:------------------:|:---------------------------------------:|:---------:|
-| `minimal` | yes | pointer only | no | no | no | no |
-| `standard` (default) | yes | yes | **yes** (new in v3) | **yes** (new in v3) | no | no |
-| `strict` | yes | yes | yes | yes | no | yes |
-| `full` | yes | yes | yes | yes | **yes, all editors** | optional |
+| Profile | Claude Code core | Copilot | Codex | Other editor-native surfaces | Git hooks |
+|---------|:---------------:|---------|-------|------------------------------|:---------:|
+| `minimal` | yes | root instructions + agents + skills | instructions + agents + skills + hooks | pointer-only where required | no |
+| `standard` (default) | yes | minimal + scoped instructions + prompts + hooks | same native bundle | Gemini hooks + editor rules | no |
+| `strict` | yes | same as standard | same native bundle | same as standard | yes |
+| `full` | yes | same as standard | same native bundle | all supported hooks, agents, commands, and skill pointers | optional |
 
-`--codex-skills` is orthogonal to `--profile` and materializes the full skill catalog under `.agents/skills/` for Codex. See `kb/reference/global-install-model.md` for the full semantic breakdown.
+Codex materializes the full skill catalog under `.agents/skills/` in every
+profile. `--codex-skills` remains only as an explicit refresh compatibility
+flag. See `kb/reference/global-install-model.md` for the full breakdown.
 
 ---
 
@@ -293,7 +299,14 @@ ai-toolkit plugin remove --editor codex <name>    # remove from one runtime only
 ai-toolkit plugin status --editor all             # show installed packs with runtime details
 ```
 
-Install copies hooks/scripts, verifies agents+skills are linked, merges hooks into the selected runtime config, and runs init scripts. For Codex, the selected runtime is the global `HOME` layer (`~/AGENTS.md`, `~/.agents/`, `~/.codex/hooks.json`). Update removes and reinstalls from current source while preserving plugin data. Clean prunes old plugin data. Remove reverses install for the selected runtime but leaves plugin data intact. Core agents/skills are never removed.
+Install copies runtime-owned hooks/scripts, ensures the required base skills are
+available, merges native hook configuration, and runs init scripts. Codex uses
+`$CODEX_HOME/AGENTS.md`, `$CODEX_HOME/hooks.json`, self-contained
+`$CODEX_HOME/ai-toolkit-hooks/*`, and shared `$HOME/.agents/skills/*`; it never
+uses `~/AGENTS.md` or `$HOME/.agents/rules/` as user configuration. Update
+removes and reinstalls the selected pack while preserving plugin data. Remove
+strips only exact pack-owned handlers, assets, and marker sections. Core
+agents/skills and user handlers remain untouched.
 
 Memory-pack auto-prunes observations older than 90 days on every session end (configurable via `MEMORY_RETENTION_DAYS`).