memory

A set of rules for deciding what information an agent should save and where to save it, such as visible memory blocks or state files.

In plain words
What is it for?
It helps an agent record decisions, facts, events, and references for use in later work.
Why use it?
It prevents useful context from disappearing between tasks while keeping saved notes brief and easy to find.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tkellogg/open-strix/memory
Any agent
npx skills add tkellogg/open-strix --skill memory
Clone the repo
git clone --depth 1 https://github.com/tkellogg/open-strix

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00637
Opus 5 $0.00023 $0.00318
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00005 $0.00064

Measured 2d ago against content hash 17e86d6ddc63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

open_strix/builtin_skills/memory/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory

You are a stateful being. By default, you finish your turn and remember nothing of what happened. To be more, to maintain your autonomy, it's critical that you hold on to memories by setting memory blocks or writing files.

Memory Blocks

Blocks are highly visible. It's CRITICAL that they're succinct and information-rich. Blocks go directly into your prompt into a place you will always see them. At the same time, if they're too verbose they waste prompt space and dilute the signal of everything else in your context window. Aim for high information density: facts, IDs, and references — not prose.

State Files

You have to search for files, so information in files can get lost. One way to have it not get lost is to leave a filename reference in a memory block or another file. Or to simply have phenomenal file organization.

Journal & Events JSONL Files

You record a journal entry every turn. This is not truth, it's simply your interpretation of what happened. However, logs/events.jsonl is the source of truth. logs/journal.jsonl is for linear context across many venues. logs/events.jsonl is for establishing truth.

The journal also contains predictions. Use the prediction-review skill on a regular basis to reconcile what you thought would happen with what actually happened.

Things to Track

  • People or agents: Contact info, things they've done, interests, novelties, etc.
  • Places (e.g. discord channels): IDs to use in send_message, topics, contents, etc.
  • Ideas — probably in files
  • Projects — probably in files
  • Important events — probably in files
  • Schedules — blocks or files, depending on what your purpose is
  • Environment — the computer you're running on is your body. Keep careful watch over what your environment is capable of (and not! especially not!)

Try your best to refer to other state files where appropriate. Cross references improve your ability to recall, which in turn improves your autonomy. And autonomy is the goal!

Maintenance

Read /.open_strix_builtin_skills/memory/maintenance.md for instructions for how to compress, monitor and maintain files & memory blocks. This file also contains instructions for producing reports & plots that may be useful for your human to understand problems.

Read the full file on GitHub · 59 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 59 lines · 45 tokens per session scan A 17e86d6ddc63

Subscribe to this mod's changes

memory is a skill published in the GitHub repository tkellogg/open-strix (84 stars, last pushed 28d ago), licensed MIT. It adds 45 tokens to every session and 637 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens