Make your AI code like it already knows your repo. Archcore gives coding agents the architecture, rules, and prior decisions of this repo — so new changes land where your project says they belong and follow the team's conventions, automatically.
FAQ
archcore-ai-plugin is a Claude Code plugin with 7 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes audit, capture, context. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
> /plugin marketplace add archcore-ai/plugin> /plugin install archcore@archcore-plugins
Repo: archcore-ai/plugin
Make your AI code like it already knows your repo.
Archcore gives coding agents the architecture, rules, and prior decisions of this repo — so new changes land where your project says they belong and follow the team's conventions, automatically.
Works in Claude Code, Cursor, Codex CLI, and GitHub Copilot CLI. One source of truth, in Git.
The agent pulls in the rules and decisions that apply — no command needed — and still gives you the seven skills below for anything explicit.

Describe what you want in plain English — Archcore routes it. The slash commands below are shortcuts to the same workflows.
| Command | Outcome | When to use |
|---|---|---|
/archcore:init | Make your repo legible to AI agents | First-time setup — seeds a stack rule, a run-the-app guide, and imports your CLAUDE.md / AGENTS.md / .cursorrules if present |
/archcore:context | Load what's already decided before you change code | Daily, before editing — pulls relevant rules, decisions, specs, patterns, and reference docs for a file, directory, or topic; or --git-changes for the rules governing your uncommitted changes |
/archcore:capture | Document what already lives in code | A module, API, pipeline, or integration has tribal knowledge but no doc yet |
/archcore:plan | Turn an idea into a scoped implementation plan | New feature, refactor, or initiative — pick depth with --track product|feature|sources|iso |
/archcore:decide | Record a decision and (optionally) make it a team rule | A decision was made — capture rationale, consequences, and turn it into an enforced standard |
/archcore:audit | Find stale, missing, or drifting docs | Health check — add --deep for a full audit, --drift for code/doc staleness |
/archcore:help | Navigate the skill catalog | When you forget which command fits |
Archcore plugins require the Archcore CLI on PATH — it serves the MCP server the plugin talks to.
# macOS / Linux / WSL
curl -fsSL https://archcore.ai/install.sh | bash
# Windows (PowerShell 5.1+)
irm https://archcore.ai/install.ps1 | iex
Verify: archcore --version · Update: archcore update · Docs: docs.archcore.ai/cli/install
Then add the plugin in your host:
Claude Code
/plugin marketplace add archcore-ai/plugin
/plugin install archcore@archcore-plugins
Cursor — requires Cursor 2.5+. Open Plugins, paste https://github.com/archcore-ai/plugin into Search or paste link, click Add Plugin. One-time MCP setup: copy docs/cursor.mcp.example.json into ~/.cursor/mcp.json (user-scoped) or .cursor/mcp.json (project-scoped).
Codex CLI — requires Codex CLI v0.117.0+.
codex plugin marketplace add archcore-ai/plugin
codex
# then run /plugins, open Archcore, select Install plugin
GitHub Copilot CLI — installs straight from this repo's plugin subdirectory.
copilot plugin install archcore-ai/plugin:plugins/archcore
Copilot CLI only: VS Code agent mode has no self-serve plugin install, and cloud-agent sandboxes do not load plugin hooks.
On Copilot the plugin brings skills, commands, agents and hooks — but not the MCP server. Copilot launches a plugin's MCP in the plugin's own directory rather than your project (github/copilot-cli#4234), so documents would land in the plugin cache. Register it per project instead:
archcore init --agent copilot --project "$PWD"
Claude Code — load the plugin for the current session:
claude --plugin-dir /path/to/plugin
Cursor — symlink the repo into Cursor's local plugins directory and reload the window:
ln -s /path/to/plugin ~/.cursor/plugins/local/archcore
# then in Cursor: Cmd/Ctrl+Shift+P → "Developer: Reload Window"
Codex CLI — point a local marketplace at the checkout:
codex plugin marketplace add /path/to/plugin
codex plugin add archcore@archcore-plugins
GitHub Copilot CLI — load the plugin directory directly:
copilot --plugin-dir /path/to/plugin/plugins/archcore
Cursor team rollouts — Dashboard → Settings → Plugins → Team Marketplaces → Import (paste the GitHub URL).
Open your project and try these three prompts. Each shows a different side of what your agent can now do.
Empty repo? Run
/archcore:initfirst — it seeds a stack rule, a run-the-app guide, and optionally imports your existingCLAUDE.md/AGENTS.md/.cursorrules.
1. "Before I change anything in src/auth/, what should I know?"
Your agent sees what's already decided for that path — before it touches the code.
2. "Add a new API handler and follow this repo's conventions." Your agent places the handler where your architecture says it belongs, instead of guessing.
3. "We picked PostgreSQL — record it as a team standard." The decision is captured, codified as a rule, and auto-applied to every future change in the same area. Decisions stop dying in chat scrollback.
The agent stops guessing and starts following the system.
CLAUDE.md / .cursorrules / AGENTS.md keeps growing and driftingNot for — chat memory, a prompt library, or a one-shot spec-to-code generator. Archcore is a repo truth layer for coding agents, not a methodology kit.
| Host | Status | Install |
|---|---|---|
| Claude Code | Production | Plugin marketplace |
| Cursor | Implemented | Plugin marketplace |
| Codex CLI | Implemented | Plugin marketplace |
| GitHub Copilot CLI | Implemented | copilot plugin install (subdir spec) |
Built on open standards (Agent Skills, MCP) — skills and MCP tools are shared across hosts; only manifests are host-specific.
| Tool | Category | How Archcore differs |
|---|---|---|
| BMAD / Spec Kit / Agent OS | Methodology | Archcore stores artifacts and a living context graph; methodology kits prescribe process. |
| Superpowers | Methodology | Shapes agent behavior; Archcore provides canonical project knowledge any agent can read. |
| claude-mem / Mem0 / agentmemory | Memory | They remember what you did; Archcore stores how the system is built and what was decided. |
| Cline Memory Bank | Docs | Same spirit, lower ceremony. Archcore adds typed relations and validated multi-step cascades. |
Pick a methodology tool for an opinionated dev flow. Pick a memory tool for session continuity. Pick Archcore when you want typed, queryable project truth that your coding agent respects on every request.
Claude Code: /plugin uninstall archcore@archcore-plugins
Cursor: remove from plugin settings.
Codex CLI: codex plugin uninstall archcore
GitHub Copilot CLI: copilot plugin uninstall archcore
Apache-2.0 · Issues and ideas: GitHub Issues
.agents/
plugins/
marketplace.json
.claude-plugin/
marketplace.json
.cursor-plugin/
marketplace.json
.gitignore
.gitmodules
demo.gif
docs/
cursor.mcp.example.json
TERMS.md
LICENSE
NOTICE
plugins/
archcore/
.claude-plugin/
plugin.json
.codex-plugin/
plugin.json
.codex.mcp.json
.cursor-plugin/
plugin.json
.mcp.json
.plugin/
plugin.json
agents/
archcore-assistant.md
archcore-assistant.toml
archcore-auditor.md
archcore-auditor.toml
assets/
icon.png
logo.png
bin/
check-archcore-write
check-cascade
check-code-alignment
check-precision
check-staleness
cli-gte
detect-host
git-scope
lib/
empty-state.sh
normalize-stdin.sh
session-start
validate-archcore
commands/
audit.md
capture.md
context.md
decide.md
help.md
init.md
plan.md
copilot-agents/
archcore-assistant.agent.md
archcore-auditor.agent.md
hooks/
codex.hooks.json
copilot.hooks.json
cursor.hooks.json
hooks.json
rules/
archcore-context.mdc
archcore-files.mdc
skills/
_shared/
adr-contract.md
globals.md
precision-rules.md
rule-contract.md
spec-contract.md
audit/
lib/
drift-detection.md
SKILL.md
capture/
SKILL.md
context/
SKILL.md
decide/
references/
continuations.md
SKILL.md
help/
SKILL.md
init/
lib/
agent-files.md
compose-overview.md
detect-config.md
detect-cross-cutting.md
detect-data-model.md
detect-domains.md
detect-entry-points.md
detect-hotspots.md
detect-integrations.md
detect-modules.md
detect-scale.md
detect-stack.md
detect-surface.md
extract-routing.md
extract-run-instructions.md
SKILL.md
plan/
references/
feature-flow.md
iso-flow.md
product-flow.md
sources-flow.md
SKILL.md
README.md© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic