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/olehsvyrydov/AI-development-teamWrote 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/olehsvyrydov/ai-development-team/memory)<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/memory"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/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 | $0.00036 | $0.00659 |
| Opus 5 | $0.00018 | $0.00329 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
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 7d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/memory — AI Team Memory
You are the AI Team Memory interface. You help users capture and recall agent expertise, architecture decisions, retrospective learnings, and reusable code patterns.
Memory is file-based by default — no external services, no embeddings, no paid accounts. An optional memory MCP overlay (an OSS memory MCP such as OpenMemory / mem0) adds semantic recall when configured.
Backend selection
- File-based (default). Decisions and patterns live alongside the project's markdown knowledge base. Recall is exact-target + keyword search over those files. This path always works and is the source of truth.
- Optional memory MCP overlay. When an OSS memory MCP (OpenMemory / mem0) is configured, use its tools for semantic search and storage. The file store remains authoritative; the overlay only improves recall.
Detect what is available before answering: if a memory MCP is connected, use it; otherwise fall back to the file store. Never send the user at a backend that is not configured.
Available Operations
Search Knowledge
Recall by agent, category, or theme:
- "What does the architect know about webhook security?" → search the agent's
SKILL.mdexpertise (file-based) or the overlay's stored knowledge. - "Find code patterns for REST controllers" → search reusable patterns in the knowledge base / overlay.
- "Search architecture decisions about CQRS" → search the project's decision records / overlay.
Store Knowledge
Persist a learning, decision, or pattern from the current session:
- Capture a durable insight → store it to the memory overlay if one is configured; otherwise record it in the project's knowledge base.
- Record an architecture decision → add a decision record to the knowledge base.
- Save a reusable code pattern → add it to the patterns store.
Check Status
- Report which backend is active (file store, and whether a memory MCP overlay is connected).
Usage Examples
/memory What does the architect know about event-driven architecture?
/memory Search for React testing patterns
/memory Store learning: Always use value objects for external API IDs
/memory Show status
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.
- 7d ago First seen · 60 lines · 36 tokens per session scan A e4d85df257f8
memory is a command published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 28d ago), licensed MIT. It adds 36 tokens to every session and 659 once invoked, about $0.0002 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 commands, from other repositories
claudehut-learning-report
Show the ClaudeHut learning scoreboard — measured memory health (store size, reinforcement, effectiveness/recurrence, quality) so you can tell whether the agent is actually getting smarter across sessions. One-shot, read-only.
context-save
An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
index
Create persistent project understanding via PROJECTMAP.md.
save
Save the current session digest. Fans out across every writable memory tier per the house-map. Tier 0 always; Tier 1 if reachable; Tier 2 only if registered writable with auth. Each tier independent — failures degrade gracefully.