Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/harrystamatoukos/ai-conversation-extractorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/harrystamatoukos/ai-conversation-extractor/mirror)<a href="https://agentmods.dev/commands/harrystamatoukos/ai-conversation-extractor/mirror"><img src="https://agentmods.dev/badge/commands/harrystamatoukos/ai-conversation-extractor/mirror/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/harrystamatoukos/ai-conversation-extractor/mirror"><img src="https://agentmods.dev/badge/commands/harrystamatoukos/ai-conversation-extractor/mirror.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.00569 |
| Opus 5 | $0.00003 | $0.00284 |
| Sonnet 5 | $0.00001 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
mirror scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mirror Command
View or manage your "Who Am I Really" psychological mirror profile — a living document built from your conversation patterns.
Default: View Current Profile
Read and display the current mirror profile:
VAULT_PATH="${OBSIDIAN_VAULT_PATH:-$HOME/Documents/Obsidian Vault}"
MIRROR_PATH="$VAULT_PATH/Claude Sessions/Mirror/Who Am I Really.md"
- Check if the profile exists at the path above
- If it exists, read it and present it to the user
- If it doesn't exist, tell the user:
No mirror profile found yet. Run
/ai-conversation-extractor:analyze-loopto build one as conversations are processed, or run/ai-conversation-extractor:mirror --rebuildto generate one from existing daily notes.
--rebuild: Rebuild from Scratch
If the argument is --rebuild:
- Scan all existing daily notes in
${OBSIDIAN_VAULT_PATH:-$HOME/Documents/Obsidian Vault}/Claude Sessions/Daily Notes/using Glob - Read through them chronologically to understand conversation patterns
- Also scan atomic notes (Insights, Decisions, Patterns, Models, Questions) for additional signals
- Build a fresh profile following the
who-am-iskill guidelines - Write to
Claude Sessions/Mirror/Who Am I Really.md
The rebuild reads existing extracted notes (not raw exports) — so it works even without the original conversation files.
Rebuild Process
- Glob for all daily notes:
Claude Sessions/Daily Notes/*.md - Read each chronologically (oldest first)
- For each note, look for personality signals:
- What topics recur?
- What decisions reveal values?
- What questions reveal concerns?
- What patterns reveal thinking style?
- Read atomic notes for deeper signals:
Claude Sessions/Insights/*.mdClaude Sessions/Decisions/*.mdClaude Sessions/Patterns/*.mdClaude Sessions/Models/*.mdClaude Sessions/Questions/*.md
- Synthesize into the profile structure from the
who-am-iskill - Write the profile with accurate metadata (dates analyzed, count)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 58 lines · 7 tokens per session scan A 76155718f667
mirror is a command published in the GitHub repository harrystamatoukos/ai-conversation-extractor (2 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 569 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.