diff --git a/README.md b/README.md index 5251cd5..3ef5a19 100644 --- a/README.md +++ b/README.md @@ -26,6 +26,8 @@ Open `index.html` or `changelog.html` in any browser, or run `python3 -m http.se `changelog.html` is the standalone, pre-rendered changelog page. +`agent-templates.html` is a standalone page explaining the [lionbenjamin/agent-templates](https://github.com/lionbenjamin/agent-templates) toolkit. + `changelog.md` is a plain Markdown version of the changelog for AI agents. `llms.txt` and `llms-full.txt` provide LLM-readable context about the whole site. diff --git a/agent-templates.html b/agent-templates.html new file mode 100644 index 0000000..7a16507 --- /dev/null +++ b/agent-templates.html @@ -0,0 +1,294 @@ + + +
+ + +31 templates · 4 groups
+A companion toolkit for coding agents: spec-driven workflows that turn an idea into a deployed change.
+Install the workflows into Antigravity, Cursor, and Claude Code. Each named command carries the project from constitution through specification, planning, implementation, review, and deployment.
+A companion toolkit by lionbenjamin: spec-driven agent workflows you install into Antigravity, Cursor, and Claude Code. Same idea as pstack — named workflows a coding agent runs — but organized as a spec-first SDLC, from a written constitution through spec, plan, code, and deploy.
+/constitute → /specify → /plan → /implement → /deploy → /retro
+ +Install every workflow with ./install-workflows.sh, which copies them into ~/.claude/commands/, ~/.cursor/commands/, and the Antigravity dirs. Every step reads a shared technical constitution and a lessons-learned memory file, so the spec, the plan, the code, and the review stay consistent across sessions — spec-driven rigor with an auditable trail instead of one-shot vibe coding. Source and full docs: lionbenjamin/agent-templates.