ReddRadar
Agent skill
memory-audit
Show everything Claudia knows with provenance tracing and entity counts. Triggers on "what do you know?", "show memories", "memory audit", "what do you remember about".
Install this agent skill to your Project
npx add-skill https://github.com/kbanc85/claudia/tree/main/template-v2/.claude/skills/memory-audit
SKILL.md
Memory Audit
Show what Claudia knows. Verify claims trace to sources. Surface gaps.
Usage
/memory-audit-- Full system audit/memory-audit [entity name]-- Audit everything about a specific person, project, or entity
Full Audit
When run without arguments, produce a system-level overview of everything in memory.
1. Summary Counts
Query the memory system for aggregate counts:
claudia memory entities search --query "*" --project-dir "$PWD"
claudia memory recall "*" --compact --limit 1 --project-dir "$PWD"
claudia memory document search --project-dir "$PWD"
Parse the JSON output from each command to get counts.
Display:
## Memory Audit - [Date]
| Category | Count |
|----------------|-------|
| Entities | N |
| Memories | N |
| Commitments | N |
| Documents | N |
| Relationships | N |
2. People (Top 10 by Importance)
claudia memory entities search --types "person" --limit 10 --project-dir "$PWD"
For each person:
claudia memory about "[person name]" --project-dir "$PWD"
Display as a table:
### People
| Name | Memories | Last Mentioned | Key Fact |
|------|----------|----------------|----------|
| ... | ... | ... | ... |
3. Projects (Top 10)
Same pattern with types=["project"]:
claudia memory entities search --types "project" --limit 10 --project-dir "$PWD"
4. Active Patterns
claudia memory session context --project-dir "$PWD"
5. Provenance Sample
Pick the 3 most recent high-importance memories and trace them:
claudia memory recall "*" --compact --limit 3 --project-dir "$PWD"
For each result, run:
claudia memory provenance trace --memory-id "[id]" --project-dir "$PWD"
Display:
### Provenance Check (3 recent memories)
**Memory:** "[content snippet]"
- Source: [episode/document/user_input]
- Document: [filename] (if linked)
- Entities: [linked entities]
- Verified: [yes/no/pending]
Entity Audit
When run with an entity name (e.g., /memory-audit Sarah Chen):
1. Profile
claudia memory about "[entity name]" --project-dir "$PWD"
Display:
## Audit: [Entity Name]
**Type:** person/project/organization
**Description:** [from entity record]
**Importance:** [score]
**First seen:** [created_at]
**Last mentioned:** [updated_at]
2. All Memories (grouped by type)
From the claudia memory about JSON response, group memories:
### Facts (N)
- [content] (importance: X, created: date)
### Commitments (N)
- [content] (importance: X, created: date)
### Observations (N)
- [content] (importance: X, created: date)
3. Relationships
### Relationships (N)
- [relationship_type] with [other_entity] (strength: X)
4. Linked Documents
claudia memory document search --entity "[entity name]" --project-dir "$PWD"
Display:
### Documents (N)
- [filename] ([source_type], [date]) - [summary snippet]
5. Provenance Chains
For each commitment or high-importance memory (importance > 0.7):
claudia memory provenance trace --memory-id "[memory ID]" --project-dir "$PWD"
Display:
### Provenance
**"[memory content]"** (commitment, importance: 0.9)
|- Source: session_summary (episode 42)
|- Episode: "Discussed Q2 goals with Sarah..."
|- Document: meeting-sarah-q2.md (transcript)
|- Verified: yes (2026-01-15)
Output Rules
- Use the structured output format with emoji headers
- End structured output blocks with a markdown horizontal rule
- If the memory system is not available, say so clearly
- Keep entity audit focused: no padding, no speculation
- Provenance chains are the most important part: if a memory has no source, flag it
Tone
- Factual and clean
- Like a database report, not a narrative
- Flag gaps honestly: "No source document linked" is useful information
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
kbanc85/claudia
map-connections
Scan context files to extract entities and relationships into the memory system. Triggers on "who knows who?", "network graph", "map my connections", "extract relationships".
kbanc85/claudia
inbox-check
Lightweight inbox triage across all configured email accounts. Dispatches fast subagent to fetch, then reviews with judgment. Use when user says "check my inbox", "any new emails?", "check email".
kbanc85/claudia
growth-check
Periodic reflection on development, skills, learning, and progress toward goals. Triggers on "am I growing?", "development check", "personal growth review".
kbanc85/claudia
feedback
Send feedback, ideas, or bug reports about Claudia. Opens a pre-filled GitHub Discussion with system context. Use when user says "feedback", "suggestion", "report a bug", "feature request", or "I have an idea".
kbanc85/claudia
draft-reply
Draft an email response with tone matching the relationship context. Shows draft for approval before sending. Use when user says "draft a reply", "respond to this email", "write a response to [person]", or shares an email and asks for help replying.
kbanc85/claudia
brain
Launch the Brain Visualizer, a real-time 3D view of memory and relationships. Triggers on "show your brain", "visualize memory", "open the brain", "memory graph".
Didn't find tool you were looking for?