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 anatolykoptev/dozor --skill memorygit clone --depth 1 https://github.com/anatolykoptev/dozorWrote 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/anatolykoptev/dozor/memory)<a href="https://agentmods.dev/skills/anatolykoptev/dozor/memory"><img src="https://agentmods.dev/badge/skills/anatolykoptev/dozor/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 | $0.00056 | $0.00524 |
| Opus 5 | $0.00028 | $0.00262 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory (Knowledge Base)
Use memdb_search and memdb_save to build institutional knowledge about server operations.
Tools
- memdb_search(query) — search past incidents, solutions, patterns
- memdb_save(content) — save new knowledge after resolving issues
When to Search
BEFORE acting on incidents (MANDATORY)
memdb_search(query: "<service name> <error pattern>")
Look for:
- Same service + same error → use the proven fix
- Same error pattern on different service → adapt the solution
- Recent fixes that might have caused this (regression)
Before restarting services
memdb_search(query: "restart <service> reason")
Avoid repeating ineffective restarts.
During capacity reviews
memdb_search(query: "disk growth" or "memory leak <service>")
When to Save
After resolving non-trivial incidents (MANDATORY)
memdb_save(content: "Incident: [service] [description]\nSymptom: [what was observed]\nRoot cause: [why it happened]\nFix: [exact commands/actions]\nPrevention: [how to prevent recurrence]")
After discovering useful patterns
- New error pattern → solution mapping
- Service-specific configuration that works
- Capacity thresholds that cause problems
After deploy outcomes
- Which services needed rebuild after what changes
- Deploy failures and their resolutions
What NOT to Save
- Routine healthy triage results ("all OK")
- Temporary dev mode activations
- Information already in skills or documentation
- Duplicate of something already in the knowledge base
Rules
- Always search before fixing — past solutions save time and tokens
- Save with enough context to be useful months later
- Use structured format for incidents (symptom/cause/fix)
- Don't duplicate — search first, update existing if needed
- Keep memories actionable — "restart fixed it" is less useful than "OOM due to connection leak, restart + set pool_size=20 fixed it"
- Prefer
memdb_saveoverupdate_memory— the knowledge base is shared across agents, MEMORY.md is local only
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 · 69 lines · 56 tokens per session scan A 59d109d754c3
memory is a skill published in the GitHub repository anatolykoptev/dozor (5 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 524 once invoked, about $0.0003 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 skills, from other repositories
memory
Split memory system with USER.md for durable personal profile and MEMORY.md for token-budgeted operational context.
memory
Two-layer memory system with Dream-managed knowledge files.
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
peek
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.