@softspark/ai-toolkit 3.2.0 → 3.3.0

package/CHANGELOG.md

@@ -7,6 +7,39 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v3.3.0 — External-source visibility & skill-listing budget default (2026-05-06)
+
+Minor release. Two coordinated install-time additions: `ai-toolkit status` now surfaces every registered external rule and hook, and fresh installs / updates set a sane `skillListingBudgetFraction` so all 112 skill descriptions stay loadable in Claude Code.
+
+### Added
+
+- **`ai-toolkit status` shows external sources** — `scripts/install_steps/install_state.py` reads `~/.softspark/ai-toolkit/rules/sources.json` and `~/.softspark/ai-toolkit/hooks/external/sources.json` and prints an `External sources:` section listing each registered rule/hook with its source URL and last-fetched timestamp. The section is omitted entirely when no external sources are registered. Closes the long-standing gap where `add-rule`/`inject-hook` had no read-side counterpart.
+- **`skillListingBudgetFraction` default in `~/.claude/settings.json`** — new `_install_skill_listing_budget()` step in `scripts/install_steps/hooks.py` writes `"skillListingBudgetFraction": 0.02` on install/update, but only when the key is absent. Existing user values are never overwritten. Prevents Claude Code's default 1% budget from truncating ~60 of the toolkit's 112 skill descriptions.
+
+### Changed
+
+- **`ai-toolkit status` help text** — updated in `bin/ai-toolkit.js` to mention external rules/hooks alongside modules, version, and profile.
+
+
+
+Patch release. Lint-only fix in the default status line hook — no behavior change.
+
+### Fixed
+
+- **`app/hooks/ai-toolkit-statusline.sh` shellcheck warnings** — removed the unused `C_GRAY` color variable (SC2034) and replaced the deprecated `[ p -o q ]` form with `{ [ p ] || [ q ]; }` (SC2166). CI shellcheck gate at `--severity=warning` now passes clean across `app/hooks/*.sh`.
+
+---
+
+## v3.2.1 — Statusline shellcheck cleanup (2026-05-04)
+
+Patch release. Lint-only fix in the default status line hook — no behavior change.
+
+### Fixed
+
+- **`app/hooks/ai-toolkit-statusline.sh` shellcheck warnings** — removed the unused `C_GRAY` color variable (SC2034) and replaced the deprecated `[ p -o q ]` form with `{ [ p ] || [ q ]; }` (SC2166). CI shellcheck gate at `--severity=warning` now passes clean across `app/hooks/*.sh`.
+
+---
+
 ## v3.2.0 — Output discipline & token-aware status line (2026-05-04)
 
 Minor release. Two coordinated additions: per-response output discipline and a real-token status line installed by default.

package/README.md

@@ -6,7 +6,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Skills](https://img.shields.io/badge/skills-112-brightgreen)](app/skills/)
 [![Agents](https://img.shields.io/badge/agents-44-blue)](app/agents/)
-[![Tests](https://img.shields.io/badge/tests-1038%20passing-success)](tests/)
+[![Tests](https://img.shields.io/badge/tests-1042%20passing-success)](tests/)
 
 <p align="center">
   <img src="assets/ai-toolkit-readme-hero.png" alt="ai-toolkit 3 README hero showing one toolkit for 12 AI editors" width="900">
@@ -14,14 +14,13 @@
 
 ---
 
-## What's New in v3.2.0
+## What's New in v3.3.0
 
-Minor release adding response-length governance and a token-aware status line installed by default.
+Minor release. Two install-time additions: visibility for external rules/hooks and a sane default for Claude Code's skill listing budget.
 
-- **Output modes for `brand-voice`** — `concise` (≤60% tokens) and `strict` (≤40%) modes governing conversational responses, with rule files in `app/skills/brand-voice/modes/` and a `measure.py` evaluator that runs against fixtures with load-bearing-fact assertions.
-- **Default comprehensive status line** — `ai-toolkit install` now wires `~/.claude/settings.json` to a single line showing cwd, git, a 10-cell context-window progress bar (green <70% / orange 70–89% / red ≥90%), `↑input ↓output` token arrows, effort level, and model. All data read directly from Claude Code's statusLine stdin — no JSONL parsing, ~50 ms cold start. User-customized statusLine entries are preserved untouched. Cost segment opt-in via `AI_TOOLKIT_STATUSLINE_SHOW_COST=1`.
-- **Real token telemetry** — `scripts/session_token_stats.py` parses Claude Code session JSONL for `/briefing --tokens` reporting and baseline capture. Stdlib-only.
-- **Opt-outs via env vars** — `AI_TOOLKIT_STATUSLINE_DISABLE`, `_NO_TOKENS`, `_NO_GIT`, `_NO_EFFORT`, `_NO_COLOR`, `_SHOW_COST` (opt-in), `_DUMP` (debug).
+- **`ai-toolkit status` lists external sources** — every rule and hook registered via `add-rule` / `inject-hook` is now visible in `status` output with its source URL and last-fetched timestamp. No more grepping `~/.softspark/ai-toolkit/*/sources.json` by hand.
+- **`skillListingBudgetFraction = 0.02` set by default** — install/update writes the key into `~/.claude/settings.json` only when missing, so all 112 skill descriptions stay loadable in Claude Code without truncation. User-set values are preserved.
+- **Updated `status` help text** — `bin/ai-toolkit.js` now mentions external rules/hooks alongside modules, version, and profile.
 
 See [CHANGELOG.md](CHANGELOG.md) for full history.
 
@@ -154,7 +153,7 @@ ai-toolkit/
 │   └── ARCHITECTURE.md  # Full system design
 ├── kb/                  # Reference docs, procedures, plans
 ├── scripts/             # Validation, install, evaluation scripts
-├── tests/               # Bats test suite (1038 tests)
+├── tests/               # Bats test suite (1042 tests)
 └── CHANGELOG.md
 ```
 

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

@@ -1,7 +1,7 @@
 {
   "name": "ai-toolkit",
   "description": "Professional-grade Claude Code toolkit with persona presets, skill security auditor, expanded lifecycle hooks, experimental opt-in plugin packs, benchmark harvesting, and multi-tool support.",
-  "version": "3.2.0",
+  "version": "3.3.0",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/hooks/ai-toolkit-statusline.sh

@@ -39,7 +39,7 @@ set -u
 # renders the statusline. So always emit colors unless explicitly disabled.
 if [ "${AI_TOOLKIT_STATUSLINE_NO_COLOR:-0}" = "1" ]; then
     C_RESET="" C_GREEN="" C_BOLD_GREEN="" C_CYAN="" C_BLUE="" C_RED=""
-    C_YELLOW="" C_MAGENTA="" C_DIM="" C_GRAY="" C_BOLD_YELLOW="" C_ORANGE=""
+    C_YELLOW="" C_MAGENTA="" C_DIM="" C_BOLD_YELLOW="" C_ORANGE=""
 else
     C_RESET=$'\033[0m'
     C_GREEN=$'\033[0;32m'
@@ -51,7 +51,6 @@ else
     C_BOLD_YELLOW=$'\033[1;33m'
     C_MAGENTA=$'\033[0;35m'
     C_DIM=$'\033[2m'
-    C_GRAY=$'\033[0;37m'
     C_ORANGE=$'\033[38;5;208m'
 fi
 
@@ -160,8 +159,8 @@ fi
 # ↑ green = upload (input tokens sent to model)
 # ↓ red   = download (output tokens received from model)
 SEG_TOKENS=""
-if [ "${AI_TOOLKIT_STATUSLINE_NO_TOKENS:-0}" != "1" ] && \
-   [ -n "$IN_TOK" ] && [ "$IN_TOK" != "0" -o "$OUT_TOK" != "0" ]; then
+if [ "${AI_TOOLKIT_STATUSLINE_NO_TOKENS:-0}" != "1" ] && [ -n "$IN_TOK" ] && \
+   { [ "$IN_TOK" != "0" ] || [ "$OUT_TOK" != "0" ]; }; then
     SEG_TOKENS="  ${C_BOLD_GREEN}\xe2\x86\x91${IN_TOK}${C_RESET} ${C_RED}\xe2\x86\x93${OUT_TOK}${C_RESET}"
     if [ "${AI_TOOLKIT_STATUSLINE_SHOW_COST:-0}" = "1" ] && [ -n "$COST" ]; then
         SEG_TOKENS+=" ${C_BOLD_GREEN}\$${COST}${C_RESET}"

package/benchmarks/ecosystem-doctor-snapshot.json

@@ -1,5 +1,5 @@
 {
-  "last_run": "2026-05-04T08:36:05Z",
+  "last_run": "2026-05-06T08:17:20Z",
   "schema_version": 1,
   "tools": {
     "aider": {
@@ -24,13 +24,12 @@
       }
     },
     "augment": {
-      "docs_hash": "f6b4c7fd64936879",
+      "docs_hash": "ac138d99235e1f3e",
       "headings": [
         "Agent",
         "Code Completions",
         "Documentation Index",
         "Introduction",
-        "Next Edit",
         "\u200bAuggie CLI",
         "\u200bGet started in minutes",
         "\u200bJetBrains IDEs",
@@ -43,7 +42,7 @@
         "Agent mode": false,
         "Auggie CLI": true,
         "MCP": true,
-        "Next Edit": true,
+        "Next Edit": false,
         "PostToolUse": false,
         "PreToolUse": false,
         "SKILL.md": false,
@@ -58,7 +57,7 @@
       }
     },
     "claude-code": {
-      "docs_hash": "7d2930e5f97e4126",
+      "docs_hash": "789113e1bc4cd34c",
       "headings": [
         "Claude Code overview",
         "Documentation Index",
@@ -104,10 +103,10 @@
         "slash command": true,
         "sub-agent": true
       },
-      "version": "2.1.126 (Claude Code)"
+      "version": "2.1.131 (Claude Code)"
     },
     "cline": {
-      "docs_hash": "eec0384d180243aa",
+      "docs_hash": "b4009dc8e6d40af9",
       "headings": [
         "Cline CLI",
         "Cline Documentation",
@@ -138,7 +137,7 @@
       }
     },
     "codex-cli": {
-      "docs_hash": "5a4b2d4eeee1d675",
+      "docs_hash": "c6b51936294d38e7",
       "headings": [
         "About",
         "Contributing",
@@ -157,7 +156,7 @@
         "Packages 0",
         "Provide feedback",
         "Quickstart",
-        "Releases 757",
+        "Releases 765",
         "Repository files navigation",
         "Resources",
         "Saved searches",
@@ -187,10 +186,10 @@
         "mcp_servers": false,
         "sandbox": true
       },
-      "version": "codex-cli 0.125.0"
+      "version": "codex-cli 0.128.0"
     },
     "cursor": {
-      "docs_hash": "4c3678f1353e012f",
+      "docs_hash": "8ed1f5cf7441b6c0",
       "headings": [],
       "markers": {
         ".cursor/rules": false,
@@ -206,7 +205,7 @@
       }
     },
     "gemini-cli": {
-      "docs_hash": "20c254199b42f18c",
+      "docs_hash": "21a2f14121ff27fa",
       "headings": [
         "Breadcrumbs",
         "Directory actions",
@@ -245,7 +244,7 @@
       }
     },
     "github-copilot": {
-      "docs_hash": "6467b14babd06b26",
+      "docs_hash": "99a5ab7bd5f7556f",
       "headings": [
         "About Copilot auto model selection",
         "About Copilot integrations",
@@ -293,7 +292,7 @@
       }
     },
     "opencode": {
-      "docs_hash": "c8c233106f166444",
+      "docs_hash": "fe845a4bffb6371b",
       "headings": [
         "Add features",
         "Ask questions",
@@ -354,7 +353,7 @@
       }
     },
     "windsurf": {
-      "docs_hash": "167ee1fc000f03d9",
+      "docs_hash": "9b2879646f041aea",
       "headings": [
         "Advanced",
         "App Deploys",

package/bin/ai-toolkit.js

@@ -62,7 +62,7 @@ const SCRIPT_COMMANDS = {
 const COMMANDS = {
   install: 'First-time global install into ~/.claude/ (use --local for project-local configs only)',
   update: 'Re-apply toolkit with saved modules from state.json (use --local for project-local only)',
-  status: 'Show installed modules, version, and profile from state.json',
+  status: 'Show installed modules, version, profile, and registered external rules/hooks',
   reset: 'Wipe and recreate project-local configs from scratch (requires --local)',
   uninstall: 'Remove ai-toolkit from ~/.claude/',
   'add-rule': 'Register a rule file or URL in ~/.softspark/ai-toolkit/rules/ (URL rules auto-refresh on update)',

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.2.0",
+  "version": "3.3.0",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "3.2.0",
+  "version": "3.3.0",
   "description": "AI coding toolkit: 112 skills, 44 agents, 12-editor write-through (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo, Aider, Augment, Antigravity, Codex, opencode), machine-enforced safety constitution, SARIF audit, signed npm provenance.",
   "keywords": [
     "claude",

package/scripts/install_steps/hooks.py

@@ -26,6 +26,7 @@ def install_hooks(claude_dir: Path, hooks_scripts_dir: Path,
         if output_styles_dir.is_dir():
             print("  Would install: output styles to ~/.claude/output-styles/ + set outputStyle in settings.json")
         print("  Would set: env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json")
+        print("  Would set: skillListingBudgetFraction=0.02 in settings.json (only if absent)")
         return
 
     _copy_hook_scripts(claude_dir, hooks_scripts_dir)
@@ -44,6 +45,7 @@ def install_hooks(claude_dir: Path, hooks_scripts_dir: Path,
 
     _install_output_styles(claude_dir)
     _install_env_vars(claude_dir)
+    _install_skill_listing_budget(claude_dir)
 
 
 def _copy_hook_scripts(claude_dir: Path, hooks_scripts_dir: Path) -> None:
@@ -151,3 +153,27 @@ def _install_env_vars(claude_dir: Path) -> None:
         with open(settings_path, "w", encoding="utf-8") as f:
             json.dump(settings_data, f, indent=4)
         print("  Set: env vars in settings.json (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1)")
+
+
+# Default for skill listing budget. 0.02 (~2% of context) keeps all 112+ skill
+# descriptions loadable without truncation. Only applied if the user has not
+# already set the key — explicit user overrides are preserved.
+SKILL_LISTING_BUDGET_DEFAULT = 0.02
+
+
+def _install_skill_listing_budget(claude_dir: Path) -> None:
+    """Set skillListingBudgetFraction default if user has not configured one."""
+    settings_path = claude_dir / "settings.json"
+    if settings_path.is_file():
+        with open(settings_path, encoding="utf-8") as f:
+            settings_data = json.load(f)
+    else:
+        settings_data = {}
+
+    if "skillListingBudgetFraction" in settings_data:
+        return
+
+    settings_data["skillListingBudgetFraction"] = SKILL_LISTING_BUDGET_DEFAULT
+    with open(settings_path, "w", encoding="utf-8") as f:
+        json.dump(settings_data, f, indent=4)
+    print(f"  Set: skillListingBudgetFraction = {SKILL_LISTING_BUDGET_DEFAULT} in settings.json")

package/scripts/install_steps/install_state.py

@@ -7,7 +7,27 @@ from datetime import datetime, timezone
 from pathlib import Path
 
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
-from paths import TOOLKIT_DATA_DIR, STATE_FILE
+from paths import TOOLKIT_DATA_DIR, STATE_FILE, RULES_DIR, EXTERNAL_HOOKS_DIR
+
+
+def _load_sources(sources_file: Path, key: str) -> list[tuple[str, str, str]]:
+    """Read a sources.json registry and return (name, url, fetched_at) tuples."""
+    if not sources_file.is_file():
+        return []
+    try:
+        with open(sources_file, encoding="utf-8") as f:
+            data = json.load(f)
+    except (json.JSONDecodeError, OSError):
+        return []
+    entries = data.get(key, {}) if isinstance(data, dict) else {}
+    if not isinstance(entries, dict):
+        return []
+    out: list[tuple[str, str, str]] = []
+    for name, meta in sorted(entries.items()):
+        if not isinstance(meta, dict):
+            continue
+        out.append((name, str(meta.get("url", "")), str(meta.get("fetched_at", ""))))
+    return out
 
 
 def _state_path() -> Path:
@@ -204,6 +224,18 @@ def print_status() -> None:
     if mcp:
         print(f"  MCP:        {', '.join(mcp)}")
 
+    ext_rules = _load_sources(RULES_DIR / "sources.json", "rules")
+    ext_hooks = _load_sources(EXTERNAL_HOOKS_DIR / "sources.json", "hooks")
+    if ext_rules or ext_hooks:
+        print()
+        print("  External sources:")
+        for name, url, fetched_at in ext_rules:
+            stamp = f" ({fetched_at})" if fetched_at else ""
+            print(f"    rule  {name}  <- {url}{stamp}")
+        for name, url, fetched_at in ext_hooks:
+            stamp = f" ({fetched_at})" if fetched_at else ""
+            print(f"    hook  {name}  <- {url}{stamp}")
+
     extends = state.get("extends")
     if extends:
         print(f"  Extends:    {extends.get('source', 'unknown')}")