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 rules/sandraschi/opencode-cli-mcp/cursorrulesgit clone --depth 1 https://github.com/sandraschi/opencode-cli-mcpWhat 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 | $0.00289 | $0.00289 |
| Opus 5 | $0.00144 | $0.00144 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
cursorrules 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.
What it actually says
You are working on opencode-cli-mcp - an MCP server that wraps opencode's HTTP API into MCP tools and provides a SOTA fleet webapp dashboard.
Key facts:
- Python + FastMCP 3.2 for the MCP server
- FastAPI for the webapp REST bridge (port 10951)
- Vite + React + TailwindCSS for the frontend (port 10950)
opencode serveruns on port 4096 (configurable via OPENCODE_SERVE_URL)- Use httpx.AsyncClient to talk to the opencode HTTP API
- All MCP tools use
ctx: Context = Nonefor FastMCP 3.x compatibility - Docstrings use Annotated[type, Field(description="...")] pattern (no Args: section)
- Follow SOTA fleet standards from mcp-central-docs
Session Context (opencode-cli-mcp)
You have access to opencode-cli-mcp: it orchestrates opencode agent runs, sessions, and system diagnostics through opencode serve.
Before starting work:
- Check server status: opencode_system(action="status")
- Check recent runs: opencode_runs(action="list", limit=10)
At end of work:
- Review what changed: opencode_sessions(action="diff", session_id=...)
- Cancel stuck runs: opencode_runs(action="cancel", job_id=...)
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 · 24 lines · 289 tokens per session scan A 622445033c90
cursorrules is a cursor rule published in the GitHub repository sandraschi/opencode-cli-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 289 tokens to every session, about $0.0014 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 cursor rules, from other repositories
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
cursor-memory
Shokunin memory system: persistent context across sessions.
skill-conventions
Project conventions for creating and editing Obsidian vault skills.
cursorrules
Robot control server. Do not move the physical robot without checking health first.
cursorrules
Fleet standards live in MCP Central Docs (local clone).
cursorrules
Cursor rule "cursorrules" from michaelshimeles/ralphy, covering cursor rules for ralphy, code change philosophy, task prioritization, code quality and legacy mindset.