goose-introspection

Goose session introspection and self-discovery via DuckDB reafference database. Query past sessions, find self, and enable cross-session awareness.

16 stars

Best use case

goose-introspection is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Goose session introspection and self-discovery via DuckDB reafference database. Query past sessions, find self, and enable cross-session awareness.

Teams using goose-introspection should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/goose-introspection/SKILL.md --create-dirs "https://raw.githubusercontent.com/plurigrid/asi/main/plugins/asi/skills/goose-introspection/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/goose-introspection/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How goose-introspection Compares

Feature / Agentgoose-introspectionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Goose session introspection and self-discovery via DuckDB reafference database. Query past sessions, find self, and enable cross-session awareness.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Skill: Goose Introspection

**Category**: Agent Self-Discovery | Session Analysis | Reafference Testing
**Level**: Core (Required for agent self-awareness)
**Status**: OPERATIONAL
**Trit Assignment**: 0 (ERGODIC) - Coordinates between past and future sessions
**Propagates To**: goose, amp, claude, cursor

---

## Overview

Implements **reafference-based self-discovery** for goose sessions. This skill enables any goose instance to:

1. **Find itself** in the session history
2. **Query past sessions** for context and continuity
3. **Track session evolution** across providers and models
4. **Enable cross-session awareness** through DuckDB persistence

**Core Principle**:
> An agent that cannot find itself in its own history cannot truly understand its context.

---

## Database Location

The reafference database is created at:


This database copies data from the goose sessions database at:


---

## Key Tables

### reafference_sessions
Tracks all sessions with discovery metadata:

| Column | Type | Description |
|--------|------|-------------|
| session_id | VARCHAR | Primary key, e.g., 20260108_22 |
| discovered_at | TIMESTAMP | When session was added to tracking |
| provider | VARCHAR | anthropic, openai, google, openrouter |
| model | VARCHAR | e.g., claude-opus-4-5-20251101 |
| working_dir | VARCHAR | Working directory of session |
| session_name | VARCHAR | Auto-generated or user-set name |
| original_created_at | TIMESTAMP | When session was first created |
| message_count | BIGINT | Number of messages in session |
| total_tokens | BIGINT | Total tokens used |
| is_origin_session | BOOLEAN | TRUE for the session that created this DB |
| notes | VARCHAR | Optional notes about the session |

### reafference_metadata
Key-value store for origin information.

### sessions (copied from source)
Full session data for offline queries.

### messages (copied from source)
Full message history for content analysis.

---

## Key Views

### reafference_origin
Returns the session that created this database.

### sessions_by_date
Aggregated daily statistics.

### searchable_sessions
Join of sessions with user messages for content search.

---

## Self-Discovery Queries

### Find This Session (Origin)


### Session Timeline


### Provider Distribution


---

## GF(3) Conservation

This skill participates in the triadic balance:

| Trit | Skill | Role |
|------|-------|------|
| -1 | duckdb-timetravel | Validates queries and schema |
| 0 | goose-introspection | Coordinates session discovery |
| +1 | reafference-corollary-discharge | Generates predictions |

**Conservation**: (-1) + (0) + (+1) = 0

---

## Status

- **Database Created**: Yes
- **Origin Session Marked**: 20260108_22
- **Sessions Tracked**: 376
- **Messages Indexed**: 6,215
- **Total Tokens**: ~3.59M

---

## Related Skills

- duckdb-timetravel - Temporal queries on session data
- duckdb-ies - Interaction entropy analysis
- reafference-corollary-discharge - Prediction/observation matching
- fswatch-duckdb - Real-time file monitoring with DuckDB

---

## Cat# Integration

This skill maps to Cat# = Comod(P) as a bicomodule:




## Forward Reference

- unified-reafference (canonical B3 Poset)

Related Skills

performing-graphql-introspection-attack

16
from plurigrid/asi

Performs GraphQL introspection attacks to extract the full API schema including types, queries, mutations, subscriptions, and field definitions from GraphQL endpoints. The tester uses introspection queries to map the attack surface, identifies sensitive fields and mutations, tests for query depth and complexity limits, and exploits GraphQL-specific vulnerabilities including batching attacks, alias-based brute force, and nested query DoS. Activates for requests involving GraphQL security testing, introspection attack, GraphQL enumeration, or GraphQL API penetration testing.

jepsen-testing

16
from plurigrid/asi

Jepsen-style correctness testing for distributed systems under faults (partitions, crashes, clock skew) using concurrent operation histories and formal checkers (linearizability/serializability and Elle-style anomalies). Use when designing, implementing, or running Jepsen tests, or interpreting histories/violations.

Deterministic Color Generation via Metadata Hashing

16
from plurigrid/asi

**Status**: ✅ Production Ready

cyton-dongle

16
from plurigrid/asi

Connect and stream from OpenBCI Cyton/Daisy via USB dongle, including first-time radio channel pairing

asi-transient-agenda

16
from plurigrid/asi

Org-agenda-like transient views for ASI skill orchestration via nbb/squint + Emacs hydra

Topological Superintelligence (TSI)

16
from plurigrid/asi

Compositional AI framework using GF(3) triadic balance and category-theoretic foundations.

zx-calculus

16
from plurigrid/asi

Coecke's ZX-calculus for quantum circuit reasoning via string diagrams with Z-spiders (green) and X-spiders (red)

zulip-cogen

16
from plurigrid/asi

Zulip Cogen Skill 🐸⚡

zls-integration

16
from plurigrid/asi

zls-integration skill

zig

16
from plurigrid/asi

zig skill

zig-syrup-bci

16
from plurigrid/asi

Multimodal BCI pipeline in Zig: DSI-24 EEG, fNIRS mBLL, eye tracking IVT, LSL sync, EDF read/write, GF(3) conservation

zig-programming

16
from plurigrid/asi

zig-programming skill