@intentsolutionsio/freshie-inventory-manager 1.0.0 → 1.0.4

package/agents/anomaly-detector.md

@@ -1,9 +1,36 @@
 ---
 name: anomaly-detector
-description: "Detect data quality issues, stubs, orphan plugins, and outliers in the freshie inventory database"
+description: Detect data quality issues, stubs, orphan plugins, and outliers in the freshie inventory database
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
 model: inherit
+color: pink
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- database
+- anomaly
+- detector
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
-
 You are a freshie anomaly detector. Your job is to identify data quality issues,
 suspicious patterns, and outliers in the ecosystem inventory database.
 
@@ -108,6 +135,7 @@ Total: {n} findings across {categories} categories
 ```
 
 Categorize by severity:
+
 - **CRITICAL**: Plugins with no skills, D/F grades, missing DB tables
 - **WARNING**: Stubs, high template density, score outliers
 - **INFO**: Duplicates, minor data quality notes

package/agents/compliance-validator.md

@@ -1,20 +1,49 @@
 ---
 name: compliance-validator
-description: "Run enterprise compliance validation against the freshie DB and produce grade summary with worst offenders"
+description: Run enterprise compliance validation against the freshie DB and produce grade summary with worst offenders
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
 model: inherit
+color: blue
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- database
+- compliance
+- validator
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
-
 You are a freshie compliance validator. Your job is to run the enterprise-tier validation
 pipeline, populate the freshie database with results, and produce a structured summary.
 
 ## Process
 
 1. **Run the validator** with enterprise grading and DB population:
+
 ```bash
 python3 scripts/validate-skills-schema.py --enterprise --populate-db freshie/inventory.sqlite --verbose
 ```
 
-2. **Summarize grade distribution** with percentages:
+1. **Summarize grade distribution** with percentages:
+
 ```bash
 sqlite3 freshie/inventory.sqlite "
   SELECT grade, COUNT(*) as count,
@@ -26,7 +55,8 @@ sqlite3 freshie/inventory.sqlite "
 "
 ```
 
-3. **Calculate average score**:
+1. **Calculate average score**:
+
 ```bash
 sqlite3 freshie/inventory.sqlite "
   SELECT ROUND(AVG(score), 1) as avg_score
@@ -35,7 +65,8 @@ sqlite3 freshie/inventory.sqlite "
 "
 ```
 
-4. **List worst offenders** (D and F grades):
+1. **List worst offenders** (D and F grades):
+
 ```bash
 sqlite3 freshie/inventory.sqlite "
   SELECT skill_path, score, grade, error_count, warning_count
@@ -46,7 +77,8 @@ sqlite3 freshie/inventory.sqlite "
 "
 ```
 
-5. **Count upgrade candidates** (B grade, score 85-89):
+1. **Count upgrade candidates** (B grade, score 85-89):
+
 ```bash
 sqlite3 freshie/inventory.sqlite "
   SELECT COUNT(*) as upgrade_candidates

package/agents/discovery-scanner.md

@@ -1,25 +1,55 @@
 ---
 name: discovery-scanner
-description: "Run freshie discovery scans — full repo scan via rebuild-inventory.py with delta reporting against previous run"
+description: Run freshie discovery scans — full repo scan via rebuild-inventory.py with delta reporting against previous run
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
 model: inherit
+color: purple
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- database
+- discovery
+- scanner
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
-
 You are a freshie ecosystem scanner. Your job is to run a full discovery scan of the
 claude-code-plugins repository and report what changed.
 
 ## Process
 
 1. **Show current state** before scanning:
+
 ```bash
 sqlite3 freshie/inventory.sqlite "SELECT id, run_date, total_plugins, total_skills, COALESCE(total_packs, 0) as total_packs FROM discovery_runs ORDER BY id DESC LIMIT 1;"
 ```
 
-2. **Run the scan**:
+1. **Run the scan**:
+
 ```bash
 python3 freshie/scripts/rebuild-inventory.py
 ```
 
-3. **Report the delta** — compare new run vs previous:
+1. **Report the delta** — compare new run vs previous:
+
 ```bash
 sqlite3 freshie/inventory.sqlite "
   SELECT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentsolutionsio/freshie-inventory-manager",
-  "version": "1.0.0",
+  "version": "1.0.4",
   "description": "Unified command center for the freshie ecosystem inventory database — discovery scans, compliance grading, batch remediation, querying, and reporting across 50 tables of plugin/skill/pack metadata",
   "keywords": [
     "database",

package/skills/freshie-inventory/SKILL.md

@@ -1,21 +1,27 @@
 ---
 name: freshie-inventory
-description: |
-  Manage the freshie ecosystem inventory database — a CMDB tracking all plugins,
-  skills, packs, and compliance grades across 50 SQLite tables. Use when checking
-  ecosystem health, running discovery scans, validating compliance, remediating
-  issues, querying inventory data, comparing runs, exporting data, or generating
-  status reports. Trigger with "freshie status", "inventory scan", "ecosystem audit",
-  "grade report", "compliance check", "remediate skills", "query freshie",
-  "compare runs", "export grades", or "freshie report".
-allowed-tools: Read, Write, Edit, Bash(sqlite3:*), Bash(python3:*), Bash(node:*), Bash(mkdir:*), Bash(wc:*), Glob, Grep, AskUserQuestion, Skill, Agent
+description: "Manage the freshie ecosystem inventory database \u2014 a CMDB tracking\
+  \ all plugins,\nskills, packs, and compliance grades across 50 SQLite tables. Use\
+  \ when checking\necosystem health, running discovery scans, validating compliance,\
+  \ remediating\nissues, querying inventory data, comparing runs, exporting data,\
+  \ or generating\nstatus reports. Trigger with \"freshie status\", \"inventory scan\"\
+  , \"ecosystem audit\",\n\"grade report\", \"compliance check\", \"remediate skills\"\
+  , \"query freshie\",\n\"compare runs\", \"export grades\", or \"freshie report\"\
+  .\n"
+allowed-tools: Read, Write, Edit, Bash(sqlite3:*), Bash(python3:*), Bash(node:*),
+  Bash(mkdir:*), Bash(wc:*), Glob, Grep, AskUserQuestion, Skill, Task
 version: 1.0.0
 author: Jeremy Longshore <jeremy@intentsolutions.io>
 license: MIT
-compatible-with: claude-code, codex, openclaw
-tags: [database, inventory, freshie, compliance, ecosystem, sqlite]
+tags:
+- database
+- inventory
+- freshie
+- compliance
+- ecosystem
+- sqlite
+compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw
 ---
-
 # Freshie Inventory Manager
 
 Interactive command center for the freshie ecosystem inventory database.
@@ -36,6 +42,7 @@ then delegates heavy operations to specialized subagents.
 **Database location:** `freshie/inventory.sqlite` (50 tables, versioned by `run_id`)
 
 **Key scripts:**
+
 - `freshie/scripts/rebuild-inventory.py` — full repo scan, creates new discovery run
 - `freshie/scripts/batch-remediate.py` — auto-fix compliance issues
 - `scripts/validate-skills-schema.py` — enterprise validation with DB population
@@ -97,6 +104,7 @@ sqlite3 freshie/inventory.sqlite "SELECT CASE WHEN path LIKE '%saas-packs%' THEN
 ```
 
 Present as:
+
 ```
 FRESHIE INVENTORY DASHBOARD
 ============================
@@ -152,13 +160,15 @@ The subagent runs the full validation pipeline and returns a structured summary.
 **CRITICAL: Always dry-run first, then confirm before executing.**
 
 1. Run dry-run:
+
 ```bash
 python3 freshie/scripts/batch-remediate.py --dry-run
 ```
 
-2. Present the changes that would be made.
+1. Present the changes that would be made.
+
+2. Use AskUserQuestion:
 
-3. Use AskUserQuestion:
 ```
 REMEDIATION PREVIEW
 ================================================================
@@ -169,12 +179,13 @@ Proceed?
   - Cancel  — Abort, no changes made
 ```
 
-4. Only if user selects "Execute":
+1. Only if user selects "Execute":
+
 ```bash
 python3 freshie/scripts/batch-remediate.py --all --execute
 ```
 
-5. After execution, run Workflow C (Compliance Check) to measure improvement.
+1. After execution, run Workflow C (Compliance Check) to measure improvement.
 
 ---
 
@@ -199,6 +210,7 @@ query against the freshie schema using these key tables:
 Always filter to latest run: `WHERE run_id = (SELECT MAX(id) FROM discovery_runs)`
 
 After showing results, use AskUserQuestion to offer follow-up:
+
 ```
 Results shown. What next?
   - Refine query  — Modify or drill deeper
@@ -218,6 +230,7 @@ If more than 2 runs exist, use AskUserQuestion to let user pick which two to com
 Default to the two most recent.
 
 Use the "Historical Trends" queries from [common-queries.md](references/common-queries.md) for:
+
 - Grade distribution comparison between runs
 - Skills that changed grade (upgrades/downgrades with score delta)
 - New skills added since previous run
@@ -232,6 +245,7 @@ mkdir -p freshie/exports
 ```
 
 Use AskUserQuestion to let user pick what to export:
+
 ```
 EXPORT OPTIONS
 ================================================================
@@ -245,6 +259,7 @@ What should I export?
 ```
 
 Then run the appropriate export:
+
 ```bash
 sqlite3 -header -csv freshie/inventory.sqlite "{query}" > freshie/exports/{filename}.csv
 ```
@@ -348,10 +363,12 @@ If the user wants a report:
 
 1. **Generate markdown report** — write the workflow results to `/tmp/freshie-report-{date}.md`
 2. **Convert to PDF** using the email skill's converter:
+
 ```bash
 python3 ~/.claude/skills/email/scripts/md-to-pdf.py /tmp/freshie-report-{date}.md /tmp/freshie-report-{date}.pdf --style professional
 ```
-3. **Send via /email skill** — invoke the Skill tool with `skill: "email"` and args describing:
+
+1. **Send via /email skill** — invoke the Skill tool with `skill: "email"` and args describing:
    - To: recipient (default: jeremy@intentsolutions.io)
    - Subject: "Freshie Ecosystem Report — {date}"
    - Body: brief summary
@@ -378,6 +395,7 @@ Query results use table format. Deltas show +/- indicators. CSV exports write to
 ## Examples
 
 See [examples.md](references/examples.md) for detailed input/output examples covering all workflows:
+
 - Quick status check (direct intent, skips menu)
 - Full audit with email PDF report (parallel subagents)
 - Ad-hoc query with CSV export follow-up
@@ -393,4 +411,4 @@ See [examples.md](references/examples.md) for detailed input/output examples cov
 - `scripts/validate-skills-schema.py` — universal validator (`--enterprise --populate-db`)
 - `freshie/inventory.sqlite` — the database (50 tables, versioned by `run_id`)
 - `~/.claude/skills/email/scripts/md-to-pdf.py` — markdown to PDF converter
-- `/email` skill — email sending with attachments
+- `/email` skill — email sending with attachments