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.
npx skills add Abilityai/cornelius --skill test-memory-systemgit clone --depth 1 https://github.com/Abilityai/corneliusWrote 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/skills/abilityai/cornelius/test-memory-system)<a href="https://agentmods.dev/skills/abilityai/cornelius/test-memory-system"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/test-memory-system/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/skills/abilityai/cornelius/test-memory-system"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/test-memory-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.03476 |
| Opus 5 | $0.00014 | $0.01738 |
| Sonnet 5 | $0.00005 | $0.00695 |
| Haiku 4.5 | $0.00003 | $0.00348 |
Grade A, and why
test-memory-system 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 — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Memory System
Purpose
Comprehensively test the new memory improvements implemented in Local Brain Search:
- Phase 1: Intent Classification
- Phase 3: Spreading Activation
- Phase 4: Usage-Based Learning (Q-values)
State Dependencies
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Memory Config | resources/local-brain-search/memory_config.py |
✓ | Central configuration | |
| Q-Values | resources/local-brain-search/data/q_values.json |
✓ | Learned preferences | |
| Usage History | resources/local-brain-search/data/usage_history.jsonl |
✓ | Event tracking | |
| FAISS Index | resources/local-brain-search/data/brain.faiss |
✓ | Vector index | |
| Graph | resources/local-brain-search/data/brain_graph.pkl |
✓ | Note graph | |
| Test Report | resources/memory-test-reports/ |
✓ | Output location |
Prerequisites
- Virtual environment activated:
source resources/local-brain-search/venv/bin/activate - FAISS index built:
data/brain.faissexists - Graph built:
data/brain_graph.pklexists - Dependencies installed:
pip install -r requirements.txt
Inputs
- None (runs full test suite)
Process
Step 1: Environment Verification
Verify all components are installed and accessible.
cd resources/local-brain-search
source venv/bin/activate
# Check files exist
ls -la data/brain.faiss data/brain_metadata.pkl data/brain_graph.pkl
# Check Python dependencies
python -c "import faiss; import networkx; import sentence_transformers; print('All dependencies OK')"
# Check new modules exist
python -c "from intent import classify_intent; from spreading import spreading_activation; from learning import get_learning_stats; print('All new modules OK')"
Expected: All files exist, all imports succeed.
Step 2: Test Intent Classification
Test that queries are correctly classified into four intent types.
cd resources/local-brain-search
source venv/bin/activate
python intent.py
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 · 509 lines · 27 tokens per session scan A 431057d5b30a
test-memory-system is a skill published in the GitHub repository Abilityai/cornelius (106 stars, last pushed 16d ago), licensed MIT. It adds 27 tokens to every session and 3,476 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 2026-09-03.
Other skills, from other repositories
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
project-knowledge
Accumulated project memory: verified gotchas and prior findings for oh-my-posh work. Consult BEFORE touching shell integration scripts (zsh, pwsh, fish, bash, cmd/Clink), terminal or pty behavior, WSL-based shell testing, or internals (cache, segments, streaming, serve daemon). Read only the topic files relevant to…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
performing-fuzzing-with-aflplusplus
Perform coverage-guided fuzzing of compiled binaries using AFL++ (American Fuzzy Lop Plus Plus) to discover memory corruption, crashes, and security vulnerabilities. The tester instruments target binaries with afl-cc/afl-clang-fast, manages input corpora with afl-cmin and afl-tmin, runs parallel fuzzing campaigns with…
codspeed-optimize
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…