Borrowing it
Nothing to install: this file belongs to oculairmedia/Letta-MCP-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oculairmedia/Letta-MCP-server/master/AGENTS.mdgit clone --depth 1 https://github.com/oculairmedia/Letta-MCP-serverWrote 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/instructions/oculairmedia/letta-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/oculairmedia/letta-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/oculairmedia/letta-mcp-server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/oculairmedia/letta-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/oculairmedia/letta-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02358 | $0.02358 |
| Opus 5.5 | $0.00943 | $0.00943 |
| Sonnet 5.5 | $0.00472 | $0.00472 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade C, and why
Letta-MCP-server AGENTS.md scanned grade C with 1 finding 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 2mo 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- VIBESYNC:beads-instructions:START --> How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Huly Integration
- Project Code:
LMS - Project Name: Letta MCP Server
- Letta Agent ID:
agent-13eb4426-b06f-4d35-ae5a-5d6ca80409f5
Workflow Instructions
- Before starting work: Search Huly for related issues using
huly-mcpwith project codeLMS - Issue references: All issues for this project use the format
LMS-XXX(e.g.,LMS-123) - On task completion: Report to this project's Letta agent via
matrix-identity-bridgeusingtalk_to_agent - Memory: Store important discoveries in Graphiti with
graphiti-mcp_add_memory
PM Agent Communication
Project PM Agent: Huly - Letta MCP Server (agent-13eb4426-b06f-4d35-ae5a-5d6ca80409f5)
Reporting Hierarchy
User (Primary Stakeholder)
↓ communicates with
PM Agent (Technical Product Owner - mega-experienced)
↓ communicates with
You (Developer Agent - experienced)
MANDATORY: Report to PM Agent
BEFORE reporting outcomes to the user, send a report to the PM agent via Matrix:
{
"operation": "talk_to_agent",
"agent": "Huly - Letta MCP Server",
"message": "<your report>",
"caller_directory": "/opt/stacks/letta-MCP-server"
}
When to Contact PM Agent
| Situation | Action |
|---|---|
| Task completed | Report outcome to PM before responding to user |
| Blocking question | Forward to PM - they know user's wishes and will escalate if needed |
| Architecture decision | Consult PM for guidance |
| Unclear requirements | PM can clarify or contact user |
Report Format
**Status**: [Completed/Blocked/In Progress]
**Task**: [Brief description]
**Outcome**: [What was done/What's blocking]
**Files Changed**: [List if applicable]
**Next Steps**: [If any]
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.
- 2mo ago First seen · 266 lines · 2,358 tokens per session scan C 4c0e397e4070
Letta-MCP-server AGENTS.md is an instructions file published in the GitHub repository oculairmedia/Letta-MCP-server (80 stars, last pushed 1mo ago), licensed MIT. It adds 2,358 tokens to every session, about $0.0094 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Letta-MCP-server AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Letta-MCP-server AGENTS.mdoculairmedia/Letta-MCP-server | Instructions file | 80 | 1mo ago | MIT | C | 2,358 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |