strands-agents
Skill1 starsChanged 2 months agoMITView on GitHub
Build and debug Strands Agents SDK loops, especially TypeScript provider bridges, concurrent tools, transcript media, budgets and telemetry. Use for Strands implementation or a failing Strands run; not for generic AWS infrastructure or for installing skills inside an agent.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- JohnJBoren/claude-skills-ecosystemtheir own version, first seen Dec 26, 2025
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- JohnJBoren/claude-skills-ecosystem★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-tool-designSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Start with the failing boundary: provider response, SDK event stream, tool execution, transcript, or host transport.
- Distinctive: line 27
Read only the matching reference.
- Distinctive: line 39
Check the observable invariant: tools that must not run did not run.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Strands agents that survive real tool loops
Start with the failing boundary: provider response, SDK event stream, tool execution, transcript, or host transport. Preserve the user's language, provider and architecture. Identify the installed SDK and adapter versions from the resolved lockfile before applying a workaround. The field evidence here comes from TypeScript SDK 1.13.0; newer versions need a fresh applicability check.
Choose the relevant reference
| Task or symptom | Read |
| First turn fails; Vercel bridge; provider migration; reasoning leaves too little output | Provider boundaries |
| Tools race; calls exceed a budget; cancellation or usage accounting is wrong | Loop control |
| Repeated images inflate context; an endpoint rejects tool images; trace content leaks | Transcript and telemetry |
| Python implementation or translating a TypeScript finding | Language and version boundaries |
Read only the matching reference. For ordinary construction, use the official quickstart, then return here if a specific boundary needs investigation.
Diagnose with the smallest useful experiment
- Capture the error class, installed versions and sanitized event types. Avoid dumping request bodies or provider credentials to diagnose an event-shape problem.
- Reduce to one model turn and one tool round trip. A text-only completion does not prove tool compatibility. Keep a conforming-provider control case.
- Fix the boundary that failed. A retry cannot repair a deterministic stream shape; a type cast cannot adapt an incompatible provider protocol.
- Check the observable invariant: tools that must not run did not run; tool-result IDs still pair; a terminal result exists; reported usage is measured or unknown.
- Report the applicable versions, reproduction and remaining uncertainty. Do not turn one model's workaround into a default for every provider.
For offline SDK experiments use the scripted model. Batch protection demonstrates the actual hook seam; stream-start repair isolates the historical bridge defect. These files are examples to adapt, not instructions to install packages or change global agent configuration automatically.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

