Index of every page on this site: llms.txt
All skills
domesticmouse avatar

/agy-brain-explorer

@606a5d5
Run it yourself

Discover, list, inspect, compare, audit, export, and safely delete Google Antigravity session trajectories, transcripts, disk paths, tool invocations, and execution steps across all brain storage directories under ~/.gemini. Use whenever asked to list recent/past sessions, review session histories, export per-conversation Markdown logs (e.g. into a prompts/ folder), compare sessions, inspect disk locations, debug trajectory steps, or delete sessions and projects.

Requires /asciinema
Use this Skill: https://skilld.dev/gh/domesticmouse/skills/agy-brain-explorer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈122 tokens for metadata: the name and description. ≈2.8k when used: this file.

Description uses 6.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈488 characters, or 6.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Antigravity Brain Explorer Skill

This skill provides procedures and commands to discover, inspect, and audit Antigravity session trajectories and conversation logs using the helper script agy-brain-explorer.py.

Execution Environment & Prerequisites

1. Always Run via uv

Run Python scripts using uv so PEP 723 inline script dependencies (typer>=0.12.0) are automatically resolved and cached without manual virtual environment management.

From the workspace root:

uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py [OPTIONS] [COMMAND]

Or from the skill folder:

uv run scripts/agy-brain-explorer.py [OPTIONS] [COMMAND]

2. Mandatory Bypass Sandbox (BypassSandbox: true)

[!IMPORTANT] Always set BypassSandbox: true when executing run_command.

  1. Running uv run inside Antigravity's standard sandbox fails with Operation not permitted (os error 1) when attempting to spawn the Python process.
  2. Discovering and inspecting session trajectories requires reading directory structures and JSONL transcripts located in user storage at ~/.gemini/**/brain/, which reside outside the workspace sandbox boundary.

3. Native Markdown Rendering

[!TIP] All results render directly as GitHub Flavored Markdown. Session IDs are formatted with copyable code plus Antigravity UI navigation links (`<short_id>` [↗](conversation://<full_session_uuid>)) so the user can easily copy the session ID to ask follow-up questions or click directly into past conversations from chat.


Workflows & Command Reference

1. Discover and List Recent Sessions

Scan all brain directories under ~/.gemini and display conversation traces ordered chronologically (newest first):

# List most recent 10 sessions formatted as Markdown with clickable conversation links (default)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py --limit 10

# Group discovered sessions by project
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py --by-project

# Filter sessions by project name or workspace path
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py --project "spring-petclinic"

# Filter by a specific brain root (e.g., 'antigravity-cli' or 'antigravity')
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py --brain antigravity --limit 10

# Filter sessions by initial user prompt query
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py -q "Please build a unified static HTML"

2. Discover Projects Across Sessions (projects)

View a project overview table listing all discovered projects, workspace paths, session counts, and latest active times:

# List all discovered projects across ~/.gemini brain folders
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py projects

# Inspect all sessions within a specific project
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py projects "spring-petclinic"

3. Search Sessions by Prompt or Deep Transcript (search)

Find sessions matching a prompt keyword or search across conversation turns and tool calls:

# Search sessions by initial prompt across all brain directories
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py search "Please build a unified static HTML"

# Filter search by brain root
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py search "build static docs" --brain antigravity-cli

# Deep search across all conversation steps (user requests, model responses, tool args, commands)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py search "build-docs-site.js" --all-steps

# Search within a single specific session
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> search "node --test"

4. Inspect Session Overview (summary)

Pass a session UUID, partial prefix (e.g. c1e9ba23), or directory path to view metadata, timing, duration, model, workspace, and tool usage frequencies:

# Markdown formatted overview (default)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION_ID_OR_PREFIX>

5. Browse Conversation Timeline (steps)

Display conversation turns with step numbers, timestamps, sources (USER_EXPLICIT, MODEL), types, and preview/actions:

# Markdown table of conversation steps (default)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> steps --limit 20

# Filter to steps that called tools
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> steps --tools-only

# Filter to user prompt steps only
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> steps --user-only

6. Drill Down into a Specific Step (step)

Inspect the user prompt, model thinking, exact tool call parameters, triggering action, and step output logs:

# View step 5 details formatted in Markdown
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> step 5

# Limit step output log preview to 100 lines
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> step 5 --lines 100

7. Audit Tool & Command Executions

Quickly review all tool invocations or shell commands run during a session:

# List all tool invocations with targets and parameters in Markdown
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> tools

# Audit all shell commands run via run_command with working directories in Markdown
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> commands

8. Inspect Raw JSON Records (raw)

Retrieve untruncated JSON step data from transcript_full.jsonl:

uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> raw 1 --full

9. Compare Two Sessions Side-by-Side (compare)

Compare two sessions side-by-side to review timing, duration, step counts, user turns, tool invocations, files written, and outcomes:

# Compare two sessions by IDs or prefixes
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py compare <SESSION_1> <SESSION_2>

# Or via session inspection syntax
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION_1> compare <SESSION_2>

10. Inspect On-Disk Paths and Transcripts (paths)

Display exact disk locations and clickable file links (file://) for session directories, transcripts (transcript.jsonl, transcript_full.jsonl), logs, step outputs, and scratch files:

# Show disk paths for a single session
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> paths

# Show disk paths for multiple sessions simultaneously
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py paths <SESSION_1> <SESSION_2>

11. Delete Sessions and Projects (delete / rm)

Safely delete sessions by individual ID/hash, path, or project name. By default, sessions are moved to the macOS Trash (~/.Trash) to enable recovery if needed:

# Delete sessions by short hash or full session ID (moved to Trash by default)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete <SESSION_ID_OR_HASH>... --force

# Delete all sessions associated with a specific project
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete --project "spring-petclinic" --force

# Or delete by project name directly as a positional argument
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete "Buffered-Mult-Demo" --force

# Delete sessions not associated with any project
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete --project "(no workspace)" --force

# Preview matching sessions and targeted actions without deleting (dry run)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete --project "gpui-testing" --dry-run

# Permanently delete from disk (rm -rf) instead of moving to Trash
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete <SESSION> --permanent --force

# Delete a session using single-session syntax
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> delete --force

12. Export Per-Conversation Markdown Logs (export / prompts)

Generate one detailed Markdown document per conversation (recording session metadata, user prompts, interactive ask_question Q&A selections, thinking summaries, Antigravity's file/tool actions, and executed shell commands) along with an index README.md:

# Export all sessions for the current workspace project into ./prompts/ (default)
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py export
# Or using the 'prompts' alias:
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py prompts

# Export all sessions for a specific project into a custom directory
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py export --project "NuttX" -o ./prompts

# Export specific session(s) by ID or prefix into ./prompts/
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py export <SESSION_1> <SESSION_2> -o ./prompts

# Render a single session's Markdown log to stdout or to a specific file
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> export
uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py <SESSION> export -o ./prompts/session.md
Multi-Take Recording Audit & Cleanup

When an operator takes multiple attempts to record an asciinema .cast session in the same project workspace, ~/.gemini/**/brain/ accumulates every aborted or superseded session under that project (including sessions started from subdirectories like <project>/lib). Pair this audit with /asciinema (.agents/skills/asciinema/references/RUNBOOK-FORMAT.md) to run an incremental Record → Correlate → Post-Process → Verify gate after each recording and populate its Cast ↔ Trajectory Correlation ledger. Exporting by --project will include all takes (01-..., 02-..., etc.). To isolate the canonical session(s):

  1. Correlate Timestamps: Read the .cast header "timestamp" (Unix epoch start time) and raw duration (trim-cast.py <file> --info), then compare against the Created (Local) and Duration fields in the exported README.md (or agy-brain-explorer.py --project <proj>).
  2. Trash Superseded Takes: Move earlier aborted or superseded sessions to macOS Trash by short ID:
    uv run .agents/skills/agy-brain-explorer/scripts/agy-brain-explorer.py delete <OLD_ID_1> <OLD_ID_2> --force
  3. Clean & Re-Export: Wipe the target export folder (rm -rf <out_dir> && mkdir -p <out_dir>) before re-running export --project <proj> -o <out_dir> so stale 02-.../03-... files do not linger and the canonical trace is numbered cleanly starting at 01-.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert16d3 checks · Risk HIGH
  • Gen Agent Trust Hub16d

    This skill instructs the AI agent to explicitly bypass its security sandbox to access and manage sensitive session history data stored in the user's home directory. It also parses conversation transcripts which could contain malicious instructions from previous sessions, serving as a vector for indirect prompt injection.

  • Socket16d

    1 alert: gptAnomaly

  • Snyk16d

    Risk: LOW · No issues

Signed by skilld at 606a5d5. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago

README badge

README badge for domesticmouse/skills/agy-brain-explorer