From grimoire
Queries personal grimoire and project spellbook for sigils, detectors, and knowledge artifacts. Lists, describes, stats, and searches by keyword, vuln class, language, severity.
npx claudepluginhub joranhonig/grimoireThis skill uses the workspace's default tool permissions.
Query and explore the contents of the personal grimoire and project spellbook.
Scans personal grimoire or project spellbook for duplicate or overlapping sigils, inventories them by frontmatter, detects overlap clusters, and proposes merges, deduplications, or keeping both.
Scans Claude Code plugins and skills for security risks like malicious code and natural language instructions. Invoke /security-scanner for user/project/all audits or GitHub URLs.
Performs read-only static security audits of Claude Code skills, commands, and plugins. Analyzes SKILL.md frontmatter, content, scripts, hooks for risks. Supports GitHub/URL fetches via WebFetch. Use for 'audit a skill' or safety reviews.
Share bugs, ideas, or general feedback.
Query and explore the contents of the personal grimoire and project spellbook.
When this skill is activated, create a todo list from the following steps. Mark each task in_progress before starting it and completed when done.
- [ ] 1. Determine operation
- [ ] 2. Determine scope
- [ ] 3. Execute query
- [ ] 4. Present results
Identify what the user wants to know. Four operations are available:
Ask or infer which collections to query:
~/.grimoire/sigils/ and ~/.grimoire/knowledge/)grimoire/spells/checks/ and grimoire/spells/knowledge/)If ~/.grimoire/sigils/ is empty, note that the personal grimoire has no sigils yet and
explain that it is populated through end-of-audit merges (/scribe-distill → end-of-audit
merge via scribe Mode 2a).
If project-local directories do not exist, note that no project spellbook exists yet and suggest running [[summon]] to initialize the workspace.
List: Run bash skills/checks/scripts/index-checks.sh <path> for each directory in
scope. Also scan any knowledge/ directories for knowledge artifacts (these have
frontmatter with name, description, vulnerability-class, languages).
Describe: Read the specified sigil file. Extract and format: all frontmatter fields, search patterns, assessment criteria (for checks), or guidance content (for knowledge artifacts).
Stats: Count sigils across all directories in scope, grouped by:
Search: Grep across all sigil and knowledge artifact files in scope for the search term. Match against name, description, tags, and body content. Present matching results with name, description, and location.
Format output using the Query output format from agents/scribe.md:
| Name | Type | Severity | Languages | Description |
|---|
For knowledge artifacts, show "n/a" for Severity since they are not automated detectors.
If no results are found, confirm the scope was correct and suggest creating detection
modules via /scribe-distill from confirmed findings.