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 agents/yanamorelli/universal-memory/operating-protocolgit clone --depth 1 https://github.com/YanAmorelli/universal-memoryWhat 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 | $0.00000 | $0.00767 |
| Opus 5 | $0.00000 | $0.00383 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
operating-protocol 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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Protocol For Agents
Agents should use Universal Memory as a controlled context and mutation surface.
Session Start
- Read the host instruction file that applies to the workspace.
- Bootstrap Universal Memory once before planning or editing.
- Treat the returned project context as active and select only relevant skills.
Prefer the MCP tool when it is available:
bootstrap()
Otherwise, use the equivalent CLI command:
umem bootstrap --format json
The aggregate preserves the existing status, project-context, and skills-list contracts.
Treat data.context as active context and inspect data.skills.list. Then request metadata
only for relevant skills with umem skills detail <skill-id-or-name> --format json or MCP
get_skill_detail. Do not repeat bootstrap on later interactions in the same conversation
or session. Use status, context, list_skills, and layout status separately only when
the task needs an explicit follow-up diagnostic.
During Work
Use facts only for durable information:
- stable project constraints;
- durable user preferences;
- architectural decisions;
- fixed bugs or important operational learnings;
- obsolete fact cleanup when prior memory is no longer true;
- recurring workflow evidence that may become a skill.
Do not record transient logs, raw command output, secrets, or uncertain inferences. Do not record raw prompts, private customer data, or one-off task progress.
In shared-layout projects, treat umem/ as reviewable project content and
.umem/ as private operational state. Project facts, rules, and user-facing
skills that collaborators should inherit belong under umem/; local notes,
private facts, audit logs, snapshots, locks, and operational skills stay under
.umem/.
Ask before publishing context that could expose local operating details,
private investigations, customer data, credentials, or an operational skill.
Sharing an operational skill such as universal-memory requires explicit
approval through umem skills share ... --category operational --yes or MCP
share_skill(..., category="operational", confirm_operational=true).
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.
- yesterday First seen · 93 lines · 0 tokens per session scan A b4b7f111a881
operating-protocol is an agent published in the GitHub repository YanAmorelli/universal-memory (6 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 767 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.