Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add harrystamatoukos/ai-conversation-extractor/plugin install 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/analyze-loop)<a href="https://agentmods.dev/commands/harrystamatoukos/ai-conversation-extractor/analyze-loop"><img src="https://agentmods.dev/badge/commands/harrystamatoukos/ai-conversation-extractor/analyze-loop.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00598 |
| Opus 5 | $0.00006 | $0.00299 |
| Sonnet 5 | $0.00003 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
analyze-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Loop Command
Start the conversation analyzer loop to process your AI chat history (Claude + ChatGPT) into Obsidian notes.
Execute the setup script first:
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-analyze-loop.sh" $ARGUMENTS
After Setup
Once the loop is initialized, begin processing the first date. For each date:
- Load conversations using the jq commands shown in the state file
- Scan for valuable content that passes the resonance test:
- Made you pause or reconsider
- Connects to something you care about
- Would be valuable to find again
- Create atomic notes for insights, decisions, patterns, questions, mental models
- Create/update the daily note with links to extracted content
- Output a summary of what you extracted
The stop hook will automatically advance to the next date when you complete this iteration.
Important Guidelines
Follow the ai-conversation-extractor skill:
- One idea per atomic note - Keep notes focused and reusable
- Paraphrase, don't copy - Rewrite in your own words for deeper processing
- Use proper Obsidian syntax - Frontmatter, wikilinks, callouts
- Link liberally - Connect related concepts with
[[wikilinks]]
Mirror Analysis
Each iteration also refines the mirror profile — a living psychological portrait built from conversation patterns. After extraction:
- Read the existing profile at
Claude Sessions/Mirror/Who Am I Really.md - Scan the same conversations for personality signals (thinking style, values, emotions, recurring themes)
- Refine the profile incrementally — don't rewrite, evolve
- Follow the
who-am-iskill for analysis framework and tone
Use /ai-conversation-extractor:mirror to view the current profile or /mirror --rebuild to regenerate from existing notes.
Output Locations
All notes go to: ${OBSIDIAN_VAULT_PATH:-$HOME/Documents/Obsidian Vault}/Claude Sessions/
Daily Notes/YYYY-MM-DD.md- Day summariesInsights/Insight - Title.md- Aha momentsDecisions/Decision - Title.md- Choices with rationalePatterns/Pattern - Title.md- Reusable techniquesModels/Model - Title.md- Mental frameworksQuestions/Question - Title.md- Open loops to revisitMirror/Who Am I Really.md- Living psychological profile
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.
- 5d ago First seen · 63 lines · 13 tokens per session scan A 0dd44e0b6ce5
analyze-loop is a command published in the GitHub repository harrystamatoukos/ai-conversation-extractor (2 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 598 once invoked, about $0.0001 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
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.