The default stepbystep edition (copy). Full build plan with tracker, per-step prompts, verify lines, rollback, landmines, and a not-building list. The agent never commits: it hands you one commit + push block per step.
Plugin stepbystep from marketplace agent-flow in memoliertorerr/agent-flow. Commands read from the repo's manifest — 19 days ago.
agent-flowRuns a step-by-step plan with a human in the loop. A coordinator session briefs an executor (a subagent or separate session) for each step, reviews the result itself (reads the diff, reruns the checks, fixes small issues) and hands the human one commit-and-push block per repository; by default the a
stepbystep-autopilotAutopilot edition of stepbystep. Generates a step-by-step build plan that agent sessions execute with minimal supervision: the agent commits each step itself once its verify command is green, runs a whole phase back to back, pushes the feature branch, and opens a pull request at each phase boundary
stepbystep-liteLightweight edition of stepbystep for small, well-understood work: a feature, fix, or refactor of roughly 3–8 steps. Writes one compact plan document that later agent sessions execute one step at a time: a scope line with an explicit not-doing list, a progress tracker, an opening prompt, and per-ste
stepbystep-portableGenerate a step-by-step build plan document that later agent sessions execute one step at a time — a single canonical progress tracker with per-step copy-paste prompts, concrete verify criteria, per-step model tiers, ground rules, rollback, landmines, and an explicit not-building-this section, plus
stepbystepGenerate a step-by-step build plan document that later agent sessions execute one step at a time — a single canonical progress tracker with per-step copy-paste prompts, concrete verify criteria, per-step model assignments, ground rules, rollback, landmines, and an explicit not-building-this section,
Run a step-by-step plan with a coordinator: brief an executor per step, review its diff and rerun the checks, hand the human one commit + push block per repository. Also live operator windows, parallel sessions and session handoffs.
5 skills
Autonomous stepbystep edition (copy). The agent commits each green step, runs a whole phase, and opens a pull request per phase, stopping at checkpoints.
5 skills
Lightweight stepbystep edition (copy) for 3-8 step features and fixes. One compact plan file with scope, tracker, opening prompt and per-step prompts.
5 skills
Tool-neutral stepbystep edition (copy). Same full format with generic model tiers and a commit convention you choose per plan.
5 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.