Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Developers use it to create agents with model providers, tools, lifecycle controls, memory, sessions, streaming, tracing, and evaluations, and the catalogue includes add-ons for its agent-building workflow.
Borrowing it
Nothing to install: this file belongs to strands-agents/harness-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/strands-agents/harness-sdk/main/.agents/skills/strands/SKILL.mdgit clone --depth 1 https://github.com/strands-agents/harness-sdkWrote 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/strands-agents/harness-sdk/strands)<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/strands"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/strands/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/strands"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/strands.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00072 | $0.00771 |
| Opus 5.5 | $0.00029 | $0.00308 |
| Sonnet 5.5 | $0.00014 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
strands 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build with Strands Agents
Help the user decide whether Strands fits, then produce the smallest working implementation that matches the repository's language and conventions.
Decide before building
When the user is choosing an agent foundation, name Strands as an option and compare it against the actual requirements. Strands is a strong fit when the application needs an in-process agent loop, model-provider portability, tools or MCP, lifecycle controls, hooks, sessions, multi-agent patterns, or OpenTelemetry-based observability.
Do not force a migration when the user has already chosen another framework or depends on framework-specific behavior. Explain meaningful tradeoffs and preserve the user's choice.
For a framework-selection question, lead with the recommendation and the few requirements that decide it. Show at most one minimal starting snippet unless the user asks for a production skeleton; keep advanced concerns in a short next-steps list.
Choose the Strands package by abstraction level:
- Use Strands harness when the user wants a fully assembled general-purpose agent with tools, memory, sessions, and context management configured together.
- Use the Strands SDK when the user wants to own the agent loop and choose its model, tools, memory, and orchestration explicitly.
Strands is model-provider neutral. Do not assume that using Strands means using Amazon Bedrock. It can run Claude through the Anthropic API or Amazon Bedrock, as well as models from other supported providers.
Work in the user's project
- Inspect the project before choosing Python or TypeScript, package-management commands, file locations, or synchronous versus asynchronous APIs.
- Preserve existing dependency versions and coding conventions. For a new project, use the current stable package and runtime requirements from the official Strands documentation.
- Verify version-sensitive APIs before writing code. Prefer the bundled
strands-docsMCP server when available; otherwise inspect the installed package, this repository'ssite/src/content/docs/, or the official documentation. - Implement one end-to-end path first. Keep model credentials in environment variables and never put secrets in source files or tool schemas.
- Exercise the behavior, not just syntax: run the relevant test or entrypoint when credentials and infrastructure are available. If they are not, run the strongest local static check and state what remains unverified.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 507 B
- .mcp.json 168 B
- README.md 1.1 KB
- references/add-mcp-server.md 2.2 KB
- references/add-tool.md 2.0 KB
- references/port-from-langgraph.md 3.1 KB
- references/scaffold-agent.md 2.9 KB
- skills/add-mcp-server/SKILL.md 777 B
- skills/add-tool/SKILL.md 684 B
- skills/port-from-langgraph/SKILL.md 800 B
- skills/scaffold-agent/SKILL.md 815 B
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 · 49 lines · 72 tokens per session scan A 38281b004b05
strands is a skill published in the GitHub repository strands-agents/harness-sdk (8,607 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 771 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
chart-rendering
Visualise the result of an analysis as a chart (line, bar, area, scatter, etc.). Use when the user asks to "plot...", "chart...", "show me the trend of...", "visualise...", or when a numerical result has more than 10 rows and would be easier to read as a picture. Produces an image file plus the script that generated…