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/shyftlabs/continuum/agents-mdgit 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/instructions/shyftlabs/continuum/agents-md)<a href="https://agentmods.dev/instructions/shyftlabs/continuum/agents-md"><img src="https://agentmods.dev/badge/instructions/shyftlabs/continuum/agents-md.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 | $0.04869 | $0.04869 |
| Opus 5 | $0.02434 | $0.02434 |
| Sonnet 5 | $0.00974 | $0.00974 |
| Haiku 4.5 | $0.00487 | $0.00487 |
Grade A, and why
continuum AGENTS.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 today.
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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuum — AI Assistant Knowledge Pack
Loaded automatically by OpenAI Codex CLI, Claude Code (via
CLAUDE.mdimport), Cursor (via.cursor/rules/continuum.mdc), and other agents that respect theAGENTS.mdconvention.Goal: give the assistant enough context to write correct Continuum code on the first try.
What is Continuum?
A Python 3.13 agentic framework by ShyftLabs. Provides:
BaseAgent(dataclass) +AgentRunner(executor)- Multi-LLM via direct provider SDKs (OpenAI / Anthropic / Gemini — not LiteLLM)
- Two-tier memory: short-term Redis sessions + long-term mem0 + Qdrant
- MCP-native tool integration (Stdio / SSE / StreamableHTTP)
- 9 workflow agents (Router, Sequential, Parallel, Loop, Reflection, Planner, Debate, Scatter, SupervisedSequential)
- Optional Temporal durable workflows with human-in-the-loop approval gates
- Langfuse observability and tracing
Distributed as a Python package — pip install shyftlabs-continuum
(or pip install -e . from a checkout). Importable as
from continuum import ... — the wheel name on disk is
shyftlabs-continuum, the import name is continuum.
Repository layout
continuum/
├── AGENTS.md / .cursor/rules/continuum.mdc # this file
├── .claude/skills/continuum-* # 13 invocable skills
├── README.md # project overview
├── pyproject.toml # package metadata
├── src/continuum/ # framework source
│ ├── agent/, llm/, memory/, session/, tools/,
│ │ observability/, core/, evaluation/, temporal/
│ ├── config.py, protocols.py, exceptions.py
├── docs/ # API reference
│ ├── agent.md, llm.md, memory.md, session.md, tools.md,
│ │ observability.md, core.md, installation.md
│ └── temporal/*.md
├── tests/ # pytest suite (unit / integration / e2e)
├── playground/ # runnable example apps
│ ├── memory-modes-demo/, sdk_feature_test/,
│ │ commerce-chat/, fetch-agent/, assortment/
├── docker-compose.yml # Redis + Qdrant + Langfuse stack
└── .env.template # API keys go here
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.
- today First seen · 500 lines · 4,869 tokens per session scan A 3a5635ab5f09
continuum AGENTS.md is an instructions file published in the GitHub repository shyftlabs/continuum (84 stars, last pushed today), licensed Apache-2.0. It adds 4,869 tokens to every session, about $0.0243 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 instructions, from other repositories
ai-assistant-instructions AGENTS.md
AGENTS.md instructions for dryvist/ai-assistant-instructions, covering ai agents configuration, coding behavior, tool choice, starting any change and git workflow.
skillmaxxing CLAUDE.md
Instructions for johnvouros/skillmaxxing, covering agent skills system and adapter rules.
synthorg CLAUDE.md
Claude Code instructions for Aureliolo/synthorg, covering claude.md: synthorg, mandatory rules, quick commands, reference (load on demand) and diagrams.
guardian-agent CLAUDE.md
Instructions for Threat-Vector-Security/guardian-agent, covering repository guidelines, branching (critical), project structure & module organization, build, test, and development commands and intent gateway (critical).
ai-assistant-instructions GEMINI.md
Gemini CLI instructions for dryvist/ai-assistant-instructions, a project described as: A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions and commands that work seamlessly across Claude, Gemini, Copilot, and local AI models. See also…
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).