memory-manager

memory-manager is a skill for Claude Code, Codex from rangerrick337/operator-os. It costs 81 tokens per session (596 once invoked), scanned A, original, MIT.

A set of instructions for managing three levels of saved project memory: long-term facts, an active dashboard, and dated session logs.

In plain words
What is it for?
Use it to load memory at the start of a session, propose lasting facts for confirmation, update current project status, and record session summaries.
Why use it?
It keeps important context available across sessions without mixing permanent facts, current work, and daily notes together.

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/rangerrick337/operator-os/memory-manager
Any agent
npx skills add rangerrick337/operator-os --skill memory-manager
Clone the repo
git clone --depth 1 https://github.com/rangerrick337/operator-os

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-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/rangerrick337/operator-os/memory-manager.svg)](https://agentmods.dev/skills/rangerrick337/operator-os/memory-manager)
Your own site
<a href="https://agentmods.dev/skills/rangerrick337/operator-os/memory-manager"><img src="https://agentmods.dev/badge/skills/rangerrick337/operator-os/memory-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 596 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 $0.00081 $0.00596
Opus 5 $0.00041 $0.00298
Sonnet 5 $0.00016 $0.00119
Haiku 4.5 $0.00008 $0.00060

Measured 3d ago against content hash 8d5adf25a93d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-manager 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 3d 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.

Operator Team OS/3. Skills/memory-manager/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Manager Skill

Memory Location

All memory files live in Operator Team OS/6. Memory/.

3-Tier System

Tier File Purpose Who Writes
Long-Term LONG_TERM.md Canonical company facts. Rarely changes. Agent proposes, human confirms
Active ACTIVE.md Company dashboard — who's working on what, links to real files. Agent writes, human reviews
Logs logs/YYYY-MM-DD.md Daily session summaries. Append-only. Agent auto-generates

Reading Memory (Session Start)

Load in this order:

  1. 6. Memory/LONG_TERM.md (always)
  2. 6. Memory/ACTIVE.md (always)
  3. 6. Memory/logs/ — today's file and yesterday's file if they exist

Writing Memory

Long-Term (LONG_TERM.md)

  • Never write directly. Propose changes to the user.
  • Format: append [PROPOSED YYYY-MM-DD] <fact> and ask user to confirm.

Active (ACTIVE.md)

  • Write directly when priorities shift or a significant decision is made.
  • Date-stamp entries in the "Recent Decisions" section.
  • Update per-person "Focus" and "Where We're At" sections.
  • Link to deeper files using relative paths.
  • Active is a map, not a warehouse. Keep it brief and point to the real work.

Logs (logs/YYYY-MM-DD.md)

  • One file per day, shared across all users.
  • Append session summaries at end of session, or when context is about to be lost.
  • Format:
## Session — HH:MM (User Name)

**Topics**: topic1, topic2
**Decisions**:
- Decision description and rationale

**Action Items**:
- [ ] Action item description

**Notes**:
- Any other noteworthy context

Proactive Memory Behavior

When a conversation surfaces a significant decision, preference, or factual change:

  1. Assess if it's worth remembering (not trivial details)
  2. Offer: "This seems important — want me to commit it to memory?"
  3. If yes, write to the appropriate tier
  4. If unsure which tier, default to Active

Do NOT ask about trivial or obvious things. Use judgment.

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 81 tokens per session scan A 8d5adf25a93d

Subscribe to this mod's changes

memory-manager is a skill published in the GitHub repository rangerrick337/operator-os (10 stars, last pushed 6mo ago), licensed MIT. It adds 81 tokens to every session and 596 once invoked, about $0.0004 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.