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/shyftlabs/continuum/continuum-tools-mcpnpx skills add shyftlabs/continuum --skill continuum-tools-mcpgit clone --depth 1 https://github.com/shyftlabs/continuumWrote 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/shyftlabs/continuum/continuum-tools-mcp)<a href="https://agentmods.dev/skills/shyftlabs/continuum/continuum-tools-mcp"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-tools-mcp.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 5.1 | $0.00094 | $0.03007 |
| Opus 5 | $0.00047 | $0.01503 |
| Sonnet 5 | $0.00019 | $0.00601 |
| Haiku 4.5 | $0.00009 | $0.00301 |
Grade A, and why
continuum-tools-mcp 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuum MCP / Tools Skill
Authoritative source: docs/tools.md.
Imports
from continuum.tools import (
MCPServerStdio, MCPServerSse, MCPServerStreamableHttp,
ToolExecutor, MCPUtil,
ToolContextConfig, ToolContextVariable,
create_static_tool_filter, ToolFilterContext,
MCPToolArtifact, RunArtifacts,
)
# `ToolExecutorConfig` is not in the `continuum.tools` namespace —
# import it from the executor module directly.
from continuum.tools.executor import ToolExecutorConfig
Three transports
| Transport | When |
|---|---|
MCPServerStdio |
Local subprocess MCP server |
MCPServerSse |
Legacy SSE-based remote |
MCPServerStreamableHttp |
Recommended for any modern remote |
local = MCPServerStdio(
{"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "./data"]},
name="local",
)
await local.connect() # ALWAYS connect first
remote = MCPServerStreamableHttp(
{"url": "https://example.com/mcp",
"headers": {"Authorization": "Bearer …"}},
name="remote",
)
await remote.connect()
Quickest agent wiring
from continuum.agent import BaseAgent, AgentRunner
agent = BaseAgent(
name="tool-agent",
instructions="Use the tools to answer.",
mcp_servers=[local, remote], # tool discovery is automatic
)
resp = await AgentRunner().run(agent, "...")
Manual ToolExecutor (for shared executors / restrictions)
executor = ToolExecutor(
tool_registry={
local: None, # None = expose all of this server's tools
remote: ["search", "ingest"], # restrict
},
config=ToolExecutorConfig(
max_concurrent_calls=5,
rate_limit_per_second=10.0,
timeout_seconds=30.0,
),
)
await executor.initialize() # REQUIRED when constructed with tool_registry
agent = BaseAgent(name="…", instructions="…", tool_executor=executor)
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 · 326 lines · 94 tokens per session scan A 2326157c3daf
continuum-tools-mcp is a skill published in the GitHub repository shyftlabs/continuum (84 stars, last pushed 3d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,007 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
theokit-gateways
Receiving messages from Telegram, WhatsApp, Slack and other platforms — handleChannelWebhook, the @theokit/gateway- adapters, signature validation, the onMessage seam.
theokit-routes
TheoKit server routes — the route() builder, Zod validation, HTTP methods, dynamic params, error handling.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
architecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or…
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
moai-ref-api-patterns
REST/GraphQL API design patterns, error handling conventions, and input validation reference for backend development. Agent-extending skill that amplifies backend domain work (spawned via Agent(general-purpose) with backend instructions) with production-grade API patterns. Use when designing APIs, implementing…