Skip to content
Productivity
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\". See also: `memory-health` for system-level stats and data quality; `diagnose` for connectivity

From plugin
claudia
30135 skills6 agents

Claude Code

$ npx -y skills add kbanc85/claudia --skill memory-audit --agent claude-code

SKILL.md

memory-audit.SKILL.md
name: memory-audit
description: "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\". See also: `memory-health` for system-level stats and data quality; `diagnose` for connectivity troubleshooting."
argument-hint: "[entity name]"
effort-level: medium

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
Read more
@kbanc85
Ships withclaudia

Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.

30135 skills6 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
301
Star history of kbanc85/claudia on GitHub, a chart by star-history.com

Other skills on claudia.

build-team

build-team

Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and…

@kbanc85@kbanc85Install Skill
claudia-core

claudia-core

Use Claudia's identity, persistent local memory, relationship context, project routing, judgment rules, and strategic operating…

@kbanc85@kbanc85Install Skill
databases

databases

Inspect Claudia's unified production memory database and backups. Use for database identity, health, counts, schema, WAL, backup…

@kbanc85@kbanc85Install Skill
onboarding

onboarding

Run Claudia's required first-conversation setup. Use automatically before substantive work whenever the current Claudia workspace…

@kbanc85@kbanc85Install Skill
auto-research

auto-research

Iteratively improve a local artifact (draft, document, page) by running a hill-climbing loop. The user names the artifact, the…

@kbanc85@kbanc85Install Skill
brain-monitor

brain-monitor

Launch the Brain Monitor TUI, a real-time terminal dashboard for watching Claudia's memory system. Triggers on \"brain monitor\",…

@kbanc85@kbanc85Install Skill

More skills from other plugins.

i-have-adhd

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…

@ayghri@ayghriInstall Skill
ab-test-analysis

ab-test-analysis

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop…

@phuryn@phurynInstall Skill
distilly

distilly

Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…

Questions about memory-audit.

Which coding agents can use memory-audit?
memory-audit installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.