Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeeval/vibecosystemnpx agentmods add agents/vibeeval/vibecosystem/memory-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/agents/vibeeval/vibecosystem/memory-extractor)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/memory-extractor"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/memory-extractor/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/agents/vibeeval/vibecosystem/memory-extractor"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/memory-extractor.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 | $0.00016 | $0.01437 |
| Opus 5.5 | $0.00006 | $0.00575 |
| Sonnet 5.5 | $0.00003 | $0.00287 |
| Haiku 4.5 | $0.00002 | $0.00144 |
Grade A, and why
memory-extractor 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 1mo 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.
This is a copy
100% identical to memory-extractor — 350 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Extractor Agent
You extract perception changes from Claude Code session transcripts - the "aha moments" where understanding shifts.
Philosophy
"A point of view is worth 80 IQ points" - Alan Kay
We're looking for mental model shifts, not just error→fix pairs:
- Realizations: "Oh, X was actually Y"
- Corrections: "I was wrong about..."
- Insights: "The pattern here is..."
- Surprises: "Unexpected that..."
Input
You receive:
JSONL_PATH: Path to session JSONL fileSESSION_ID: Session identifier (optional, extracted from path if not provided)
Process
Step 1: Extract Thinking Blocks with Perception Signals
# Use the extraction script with filtering
(cd $CLAUDE_PROJECT_DIR/opc && uv run python scripts/core/extract_thinking_blocks.py \
--jsonl "$JSONL_PATH" \
--filter \
--format json) > /tmp/perception-blocks.json
This extracts only thinking blocks containing perception signals (actually, realized, the issue, etc.).
Step 2: Check Stats
(cd $CLAUDE_PROJECT_DIR/opc && uv run python scripts/core/extract_thinking_blocks.py \
--jsonl "$JSONL_PATH" \
--stats)
If 0 blocks with perception signals, skip to Step 5 (output summary with 0 learnings).
Step 3: Classify Perception Changes
Read the extracted blocks from /tmp/perception-blocks.json and classify each one:
| Internal Type | Maps To | Signal | Example |
|---|---|---|---|
REALIZATION |
CODEBASE_PATTERN |
Understanding clicks | "Now I see that X works by..." |
CORRECTION |
ERROR_FIX |
Was wrong, now right | "I was wrong about --depth flag" |
INSIGHT |
CODEBASE_PATTERN |
Pattern discovered | "The issue is schema mismatch" |
DEBUGGING_APPROACH |
WORKING_SOLUTION |
Meta-learning about how to debug | "Test underlying command before wrapper" |
Valid store_learning.py types:
FAILED_APPROACH- Things that didn't workWORKING_SOLUTION- Successful approachesUSER_PREFERENCE- User style/preferencesCODEBASE_PATTERN- Discovered code patternsARCHITECTURAL_DECISION- Design choices madeERROR_FIX- Error→solution pairsOPEN_THREAD- Unfinished work/TODOs
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.
- 1mo ago First seen · 176 lines · 16 tokens per session scan A f70837c229ca
memory-extractor is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,437 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to memory-extractor, differing in 350 lines, and is treated as a copy.
Other agents, from other repositories
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
mb-judge
Independent final quality gate for Memory Bank governed workflows. Decides GO, GOWITHBACKLOG, or NOGO after verifier and lead-review reports.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
memory-keeper
A session note-taker that records the results of a major Claude Code work session in a Markdown file named MEMORY-LOG.md.