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-claude-codenpx skills add shyftlabs/continuum --skill continuum-claude-codegit 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-claude-code)<a href="https://agentmods.dev/skills/shyftlabs/continuum/continuum-claude-code"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-claude-code.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 | $0.00069 | $0.00851 |
| Opus 5 | $0.00034 | $0.00426 |
| Sonnet 5 | $0.00014 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
continuum-claude-code 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuum + Claude Code Skill
CLAUDE.md setup
Create a CLAUDE.md at the project root and import the Continuum knowledge pack:
# My Project
@AGENTS.md
## Project-specific notes
- Entry point: `src/my_app/main.py`
- Run: `python -m my_app`
- Tests: `pytest tests/`
The @AGENTS.md import pulls in the full Continuum API reference automatically.
Claude Code merges it with your project-specific notes.
Skills wiring
The 13 Continuum skills in .claude/skills/ are invocable via /skill-name.
They are loaded automatically when Claude Code detects relevant queries.
To use them in a downstream project (not the framework source repo itself),
copy the .claude/ directory into your project root:
cp -r /path/to/continuum/.claude ./
Or reference the skills directory in your .claude/settings.json:
{
"skills": [".claude/skills"]
}
Available skills for Continuum development:
| Skill | Trigger words |
|---|---|
continuum-agent |
"create an agent", "BaseAgent", "lifecycle hooks" |
continuum-memory |
"remember", "long-term memory", "Milvus", "Qdrant" |
continuum-streaming |
"stream tokens", "websocket", "live output" |
continuum-tools-mcp |
"connect MCP", "filesystem tool", "remote API" |
continuum-workflows |
"chain agents", "parallel", "router" |
continuum-handoffs |
"transfer to another agent", "triage" |
continuum-llm-providers |
"switch to Claude", "gateway_mode", "Gemini" |
continuum-observability |
"Langfuse", "traces", "latency" |
continuum-testing |
"mock the LLM", "pytest", "fakeredis" |
continuum-temporal |
"long-running workflow", "approval gate" |
continuum-quickstart |
"get started", "first agent" |
continuum-recipes |
"RAG", "FastAPI integration", "plan-and-execute" |
continuum-evaluation |
"evaluate output", "DeepEval", "RAGAS" |
Project settings (.claude/settings.json)
{
"permissions": {
"allow": [
"Bash(python:*)",
"Bash(pytest:*)",
"Bash(pip:*)",
"Bash(docker:*)"
]
}
}
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.
- 2d ago First seen · 116 lines · 69 tokens per session scan A 4712e1732edb
continuum-claude-code is a skill published in the GitHub repository shyftlabs/continuum (84 stars, last pushed 2d ago), licensed Apache-2.0. It adds 69 tokens to every session and 851 once invoked, about $0.0003 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
gha-security-review
Attack patterns and real-world examples sourced from the HackerBot Claw campaign analysis by StepSecurity (2025): https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation -->.
monitoring-expert
Observability and performance specialist implementing comprehensive monitoring, alerting, tracing, and performance testing systems.
notion
Use the Notion API to create/read/update pages, data sources (databases), and blocks.
multi-search-engine
Use this skill when ordinary websearch is not enough and you need engine-specific public-web search strategy.
blogwatcher
Track blog and RSS/Atom feed updates with the blogwatcher CLI.
nano-pdf
Use nano-pdf to apply edits to a specific page in a PDF using a natural-language instruction.