claude-code-nextjs-skills / references
AGENTS.md72 starsChanged 17 days agoMITView on GitHub
Use ToolLoopAgent for a reusable in-memory tool loop. It takes instructions, unlike v6 text functions' system option. Configure stopWhen with stepCountIs for the task's budget. Agent construction describes the reusable policy; per-call options describe request-specific data. Verify the installed callOptionsSchema / prepareCall signatures rather than copying v7 runtime/tool context options. Do not put credentials or authorization decisions in model-controlled input. prepareStep can adjust active tools, messages and settings. In v6 its instruction/message overrides are step-local; v7 changes their carry-forward semantics.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/ai-sdk-7/references/agents.mdAGENTS.md
- skills/openai-agents-sdk/references/agents.mdAGENTS.md
- skills/react-best-practices/AGENTS.mdAGENTS.md
- skills/vercel-react-view-transitions/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-harness-reviewSkill
- ai-appSkill
- ai-elementsSkill
- ai-sdk-6Skill
- ai-sdk-7Skill
- ai-sdkSkill
- cache-componentsSkill
- chrome-devtoolsSkill
- frontend-designSkill
- goSkill
- handoffSkill
- hetzner-cloudSkill
- iconsSkill
- next-best-practicesSkill
- nextjs-chatbotSkill
- nextjs-seoSkill
- nextjs-shadcnSkill
- openai-agents-sdkSkill
- postgres-semantic-searchSkill
- react-best-practicesSkill
- shadcnSkill
- supabase-postgres-best-practicesSkill
- vercel-react-view-transitionsSkill
- web-design-guidelinesSkill
The file
We split this agents.md into the rules it gives an agent
3 rules. About 1 is common, 0 are distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Use ToolLoopAgent for a reusable in-memory tool loop.
- Common: line 10
Do not put credentials or authorization decisions in model-controlled input.
- Very specific: line 16
Use createAgentUIStreamResponse with uiMessages for an SDK UI route.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AI SDK 6 agents
Use ToolLoopAgent for a reusable in-memory tool loop. It takes
instructions, unlike v6 text functions' system option. Configure
stopWhen with stepCountIs for the task's budget.
Agent construction describes the reusable policy; per-call options describe
request-specific data. Verify the installed callOptionsSchema /
prepareCall signatures rather than copying v7 runtime/tool context options.
Do not put credentials or authorization decisions in model-controlled input.
prepareStep can adjust active tools, messages and settings. In v6 its
instruction/message overrides are step-local; v7 changes their carry-forward
semantics.
Use createAgentUIStreamResponse with uiMessages for an SDK UI route.
Validate/authenticate before execution and infer the agent's UI message type.
In-memory execution does not make a run durable across restarts.
Find details in the installed agent docs and ToolLoopAgent source or the
v6 agent guide.
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.