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 agentmods add skills/rangerrick337/operator-os/memory-managernpx skills add rangerrick337/operator-os --skill memory-managergit clone --depth 1 https://github.com/rangerrick337/operator-osWrote 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/rangerrick337/operator-os/memory-manager)<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>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 | $0.00081 | $0.00596 |
| Opus 5 | $0.00041 | $0.00298 |
| Sonnet 5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
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.
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:
6. Memory/LONG_TERM.md(always)6. Memory/ACTIVE.md(always)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:
- Assess if it's worth remembering (not trivial details)
- Offer: "This seems important — want me to commit it to memory?"
- If yes, write to the appropriate tier
- If unsure which tier, default to Active
Do NOT ask about trivial or obvious things. Use judgment.
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.
- 3d ago First seen · 68 lines · 81 tokens per session scan A 8d5adf25a93d
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.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-debt
Harvest honey shortcut markers into a debt ledger.
workspace-conventions
Reminders about how Dawn's workspace tools behave and what the path-jail allows.
cite-sources
How to attribute every factual claim to a corpus document.