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 instructions/sandraschi/opencode-cli-mcp/claude-mdgit 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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
opencode-cli-mcp CLAUDE.md 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
opencode-cli-mcp
MCP server that wraps opencode's opencode serve HTTP API into MCP tools, with a SOTA fleet webapp dashboard.
Build & Test
- Install:
uv sync - Run MCP server:
uv run -m opencode_cli_mcp.server - Run webapp backend:
uv run python -m api.main - Run webapp frontend:
cd web_sota && npm run dev - Start all:
.\start.ps1 - Lint:
uv run ruff check . - Test:
uv run pytest - TypeScript check:
cd web_sota && npx tsc --noEmit
Architecture
- MCP server talks to
opencode serveHTTP API (default http://127.0.0.1:4096) - Webapp backend (FastAPI, port 10951) bridges MCP tools to REST
- Webapp frontend (Vite, port 10950) proxies /api to backend
- Tools in
src/opencode_cli_mcp/tools/: sessions, runs, agent, status - Shared tool registry in
src/opencode_cli_mcp/registry.py ensure_server()is wired into all session/status tools- OpenCode custom tools in
.opencode/tools/- TS definitions calling backend API - Docs served via
GET /api/docs, tool source viaGET /api/opencode-tools - Ports: 10950 frontend / 10951 backend / 4096 opencode
Key Patterns
opencode_run_agent(prompt, wait=false)launches background agentopencode_get_run_status(job_id)polls for completionopencode_session_diff(session_id)reviews changesopencode_cancel_run(job_id)kills stuck agent
API Routes
| Prefix | Purpose |
|---|---|
/api/capabilities |
Health + runtime introspection |
/api/opencode/* |
Proxy to opencode serve |
/api/runs/* |
Agent run tracking |
/api/tools |
Tool definitions |
/api/fleet |
Fleet app status |
/api/system |
OS/GPU/memory info |
/api/docs/* |
Documentation serving |
/api/opencode-tools/* |
OpenCode custom tool definitions |
/api/settings |
App settings CRUD |
Webapp Pages (11)
Dashboard, Sessions, Projects, Tools Hub, OC Tools, Apps Hub, Chat, Help, Settings, Status Audit, API Docs
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 · 52 lines · 535 tokens per session scan A ba06d0a79b51
opencode-cli-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/opencode-cli-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 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 instructions, from other repositories
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
solo AGENTS.md
Instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
untether GEMINI.md
Instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.
agent-tools AGENTS.md
Instructions for kairyou/agent-tools, covering agent instructions, build and test, layout, settled decisions and docs.
iPolloWork AGENTS.md
AGENTS.md instructions for Devin-AXIS/iPolloWork, covering agents.md, what ipollowork is, core philosophy, pull request expectations (fast merge) and validate every experience.