Updated 3w ago
by codejunkie99
agentic-stack
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
2.3k GitHub stars (2,311)
+21 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | +1 |
| Oct 3 | +1 |
| Oct 4 | +1 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | +1 |
| Oct 8 | +1 |
| Oct 9 | 0 |
| Oct 10 | +1 |
| Oct 11 | +2 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | +2 |
| Oct 15 | 0 |
| Oct 16 | +1 |
| Oct 17 | +1 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | +1 |
| Oct 21 | +2 |
| Oct 22 | 0 |
| Oct 23 | +1 |
| Oct 24 | +1 |
| Oct 25 | 0 |
| Oct 26 | +1 |
| Oct 27 | +1 |
| Oct 28 | +2 |
| Oct 29 | +1 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | +1 |
| Nov 4 | +1 |
| Nov 5 | 0 |
- 19 skills (19 skills found in its SKILL.md files)
- 282 forks (282 forks)
- 3w ago last update (Last updated 3w ago)
Install
Skills CLI
npx skills add codejunkie99/agentic-stack
Asks which skills and agents to install. Just one: npx skills add codejunkie99/agentic-stack --skill install-agentic-stack — add -g for every project.
Claude Code
git clone https://github.com/codejunkie99/agentic-stackcp -r "agentic-stack/docs/agent-install" ~/.claude/skills/
Copies the install-agentic-stack skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add codejunkie99/agentic-stack
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
install-agentic-stack
Install or update the agentic-stack portable brain in the current project, then verify it. Read by an agent; no human steps required.
docs/agent-install/ on GitHub (opens in a new tab)SKILL.md -
brain
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)brain/ SKILL.md -
data-flywheel
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)data-flywheel/ SKILL.md -
data-layer
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)data-layer/ SKILL.md -
debug-investigator
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)debug-investigator/ SKILL.md -
deploy-checklist
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)deploy-checklist/ SKILL.md -
design-md
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)design-md/ SKILL.md -
evolver
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)evolver/ SKILL.md -
git-proxy
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)git-proxy/ SKILL.md -
loop-constraints
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)loop-constraints/ SKILL.md -
loop-guard
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)loop-guard/ SKILL.md -
loop-triage
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)loop-triage/ SKILL.md -
loop-verifier
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)loop-verifier/ SKILL.md -
memory-manager
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)memory-manager/ SKILL.md -
orchestrator
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)orchestrator/ SKILL.md -
skillforge
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)skillforge/ SKILL.md -
tldraw
No description in the SKILL.md.
.agent/skills/ on GitHub (opens in a new tab)tldraw/ SKILL.md -
cavecrew
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
.cursor/skills/ on GitHub (opens in a new tab)cavecrew/ SKILL.md -
caveman
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
.cursor/skills/ on GitHub (opens in a new tab)caveman/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.