memory

memory is a skill for Claude Code, Codex from anatolykoptev/dozor. It costs 56 tokens per session (524 once invoked), scanned A, original, MIT.

A knowledge base skill for saving and retrieving operational notes about incidents, fixes, patterns, and capacity trends.

In plain words
What is it for?
Use it before investigating incidents or restarting services to search for related history, and after resolving a significant issue to save its symptoms, cause, fix, and prevention steps. It can also support reviews of disk growth or memory leaks.
Why use it?
It helps an operations team reuse lessons from earlier problems instead of investigating the same symptoms from scratch. It also records non-trivial fixes so they can be found later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before investigating incidents or restarting services to search for related history, and after resolving a significant issue to save its symptoms, cause, fix, and prevention steps. It can also support reviews of disk growth or memory leaks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anatolykoptev/dozor/memory
Install

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.

Any agent
npx skills add anatolykoptev/dozor --skill memory
Clone the repo
git clone --depth 1 https://github.com/anatolykoptev/dozor

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/anatolykoptev/dozor/memory.svg)](https://agentmods.dev/skills/anatolykoptev/dozor/memory)
Your own site
<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>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 524 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 59d109d754c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

skills/memory/SKILL.md · 69 lines

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

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

  1. Always search before fixing — past solutions save time and tokens
  2. Save with enough context to be useful months later
  3. Use structured format for incidents (symptom/cause/fix)
  4. Don't duplicate — search first, update existing if needed
  5. Keep memories actionable — "restart fixed it" is less useful than "OOM due to connection leak, restart + set pool_size=20 fixed it"
  6. Prefer memdb_save over update_memory — the knowledge base is shared across agents, MEMORY.md is local only

Read the full file on GitHub · 69 lines

Changes

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.

  1. 7d ago First seen · 69 lines · 56 tokens per session scan A 59d109d754c3

Subscribe to this mod's changes

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.