codejunkie99/agentic-stack-desktop

agentic-context

Search and attach agent or subagent context across Claude Code, Codex, OpenCode, and Cursor when the user types @ or a tool mention.

原文语言：英语

brain

Recall and store durable cross-tool memory through the external Brain CLI.

原文语言：英语

data-flywheel

Export approved, redacted agent runs into local retrieval artifacts and evaluation cases.

原文语言：英语

data-layer

Inspect cross-tool agent activity, usage, scheduled work, and local reports.

原文语言：英语

debug-investigator

Reproduce, isolate, and verify the root cause of a software failure.

原文语言：英语

deploy-checklist

Check release readiness and request human approval before deploying.

原文语言：英语

design-md

Apply the project DESIGN.md visual design contract and its existing tokens.

原文语言：英语

git-proxy

Perform Git operations with branch protections and verification checks.

原文语言：英语

loop-constraints

Check loop contracts, permissions, and file-change limits before acting.

原文语言：英语

loop-guard

Check loop budgets and checkpoints, stopping on cancellation or stagnation.

原文语言：英语

loop-triage

Summarize a loop contract and checkpoint without modifying the project.

原文语言：英语

loop-verifier

Verify loop work against its contract and configured deterministic checks.

原文语言：英语

memory-manager

Review and maintain project memory while preserving evidence and separate memory layers.

原文语言：英语

skillforge

Create a reusable project skill after checking existing capabilities and conventions.

原文语言：英语

tldraw

Create and edit diagrams on a connected tldraw canvas using observed shape IDs.

原文语言：英语

agentic-stack-context

Use Agentic Stack to find agent or subagent context across Claude Code, Codex, OpenCode, and Cursor when the user types @ or a tool mention.

原文语言：英语