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 kobie3717/ai-iq --skill memorygit clone --depth 1 https://github.com/kobie3717/ai-iqWrote 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/kobie3717/ai-iq/memory)<a href="https://agentmods.dev/skills/kobie3717/ai-iq/memory"><img src="https://agentmods.dev/badge/skills/kobie3717/ai-iq/memory.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 | $0.00029 | $0.02767 |
| Opus 5 | $0.00015 | $0.01384 |
| Sonnet 5 | $0.00006 | $0.00553 |
| Haiku 4.5 | $0.00003 | $0.00277 |
Grade A, and why
memory 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-IQ Memory System
Give your AI persistent memory that survives across sessions. Built on SQLite with hybrid search (keyword + semantic + graph).
When to Use
Use AI-IQ memory when you need to:
- Remember decisions: "Why did we choose React over Vue?"
- Track learnings: "Redis needs network_mode: host for Docker"
- Store preferences: "User prefers dark mode"
- Record errors: "API timeout bug fixed by increasing connection pool"
- Manage beliefs: "TypeScript adoption will improve code quality (confidence: 0.8)"
- Track predictions: "New feature will reduce support tickets by 20%"
Core Commands
All commands use the memory-tool CLI (installed with pip install ai-iq).
Adding Memories
# Basic add
memory-tool add learning "Redis needs network_mode: host in Docker" --project MyApp
# With tags and priority
memory-tool add decision "Chose PostgreSQL over MongoDB" --tags database,architecture --priority 8
# With expiration (for TODOs)
memory-tool add pending "Review PR #123" --expires 2026-04-10
# With relationships
memory-tool add learning "Fixed CORS by adding credentials: true" --related 42 --project MyApp
Categories: project, decision, preference, error, learning, pending, architecture, workflow, contact
Priority: 0-10 (default: 5). Higher = more important.
Searching Memories
# Hybrid search (keyword + semantic)
memory-tool search "docker networking"
# Semantic-only (vector similarity)
memory-tool search "docker networking" --semantic
# Keyword-only (FTS)
memory-tool search "docker networking" --keyword
# Verbose output
memory-tool search "docker networking" --full
# Get specific memory
memory-tool get 42
Filtering & Listing
# List all for project
memory-tool list --project MyApp
# Filter by category
memory-tool list --category decision
# Show stale memories
memory-tool list --stale
# Show expired TODOs
memory-tool list --expired
# Show pending items
memory-tool pending
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 · 375 lines · 29 tokens per session scan A 68a698f252d4
memory is a skill published in the GitHub repository kobie3717/ai-iq (18 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 2,767 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 2026-08-30.
Other skills, from other repositories
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
recall
Search the user's own past AI coding-agent conversations (across Claude Code, Codex, Cursor, Gemini, Qwen, Goose, OpenCode, Continue, Cline, and in-app chats) before redoing work. Use when the user references something they "did before", "talked about", "figured out earlier", asks "how did we…/what did we decide…
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.
repo-context-ledger
Maintain durable, evidence-based repository context whenever an agent initializes a repository, changes behavior, checkpoints or resumes work, switches AI tools or windows, collaborates through Git, prepares a pull request, or completes a coding task. Use the deterministic runtime to route bounded context, isolate…
pneuma-preferences
Persistent user preference memory across sessions. Consult this skill BEFORE making any design, style, or aesthetic decisions — choosing colors, themes, layouts, fonts, tone of voice, content density, or visual direction. Also consult when starting a new creative task in any mode, when the user corrects your style…