Updated 8mo ago
by parcadei
Continuous-Claude-v3
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
3.9k GitHub stars (3,944)
+1 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | −1 |
| Oct 3 | −2 |
| Oct 4 | −1 |
| Oct 5 | 0 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | +2 |
| Oct 11 | 0 |
| Oct 12 | −1 |
| Oct 13 | 0 |
| Oct 14 | +1 |
| Oct 15 | +1 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 302 forks (302 forks)
- 8mo ago last update (Last updated 8mo ago)
Install
Skills CLI
npx skills add parcadei/Continuous-Claude-v3
Asks which skills and agents to install. Just one: npx skills add parcadei/Continuous-Claude-v3 --skill agent-context-isolation — add -g for every project.
Claude Code
git clone https://github.com/parcadei/Continuous-Claude-v3cp -r "Continuous-Claude-v3/.claude/skills/agent-context-isolation" ~/.claude/skills/
Copies the agent-context-isolation skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add parcadei/Continuous-Claude-v3
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 — showing the first 30 of 160 files.
-
agent-context-isolation
Agent Context Isolation
.claude/skills/agent-context-isolation/SKILL.md on GitHub (opens in a new tab) -
agent-orchestration
Agent Orchestration Rules
.claude/skills/agent-orchestration/SKILL.md on GitHub (opens in a new tab) -
agentic-workflow
Agentic Workflow Pattern
.claude/skills/agentic-workflow/SKILL.md on GitHub (opens in a new tab) -
agentica-claude-proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
.claude/skills/agentica-claude-proxy/SKILL.md on GitHub (opens in a new tab) -
agentica-infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
.claude/skills/agentica-infrastructure/SKILL.md on GitHub (opens in a new tab) -
agentica-prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
.claude/skills/agentica-prompts/SKILL.md on GitHub (opens in a new tab) -
agentica-sdk
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
.claude/skills/agentica-sdk/SKILL.md on GitHub (opens in a new tab) -
agentica-server
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
.claude/skills/agentica-server/SKILL.md on GitHub (opens in a new tab) -
agentica-spawn
Spawn Agentica multi-agent patterns
.claude/skills/agentica-spawn/SKILL.md on GitHub (opens in a new tab) -
ast-grep-find
AST-based code search and refactoring via ast-grep MCP
.claude/skills/ast-grep-find/SKILL.md on GitHub (opens in a new tab) -
async-repl-protocol
Async REPL Protocol
.claude/skills/async-repl-protocol/SKILL.md on GitHub (opens in a new tab) -
background-agent-pings
Background Agent Pings
.claude/skills/background-agent-pings/SKILL.md on GitHub (opens in a new tab) -
braintrust-analyze
Analyze Claude Code sessions via Braintrust
.claude/skills/braintrust-analyze/SKILL.md on GitHub (opens in a new tab) -
braintrust-tracing
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
.claude/skills/braintrust-tracing/SKILL.md on GitHub (opens in a new tab) -
build
Workflow orchestrator that chains existing skills for feature development
.claude/skills/build/SKILL.md on GitHub (opens in a new tab) -
cli-reference
Claude Code CLI commands, flags, headless mode, and automation patterns
.claude/skills/cli-reference/SKILL.md on GitHub (opens in a new tab) -
commit
Create git commits with user approval and no Claude attribution
.claude/skills/commit/SKILL.md on GitHub (opens in a new tab) -
complete-skill
A complete skill for E2E testing
.claude/skills/complete-skill/SKILL.md on GitHub (opens in a new tab) -
completion-check
Completion Check: Verify Infrastructure Is Wired
.claude/skills/completion-check/SKILL.md on GitHub (opens in a new tab) -
compound-learnings
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
.claude/skills/compound-learnings/SKILL.md on GitHub (opens in a new tab) -
continuity-ledger
Create or update continuity ledger for state preservation across clears
.claude/skills/continuity_ledger/SKILL.md on GitHub (opens in a new tab) -
create-handoff
Create handoff document for transferring work to another session
.claude/skills/create_handoff/SKILL.md on GitHub (opens in a new tab) -
dead-code
Find unused functions and dead code in the codebase
.claude/skills/dead-code/SKILL.md on GitHub (opens in a new tab) -
debug-hooks
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
.claude/skills/debug-hooks/SKILL.md on GitHub (opens in a new tab) -
debug
Debug issues by investigating logs, database state, and git history
.claude/skills/debug/SKILL.md on GitHub (opens in a new tab) -
describe-pr
Generate comprehensive PR descriptions following repository templates
.claude/skills/describe_pr/SKILL.md on GitHub (opens in a new tab) -
discovery-interview
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
.claude/skills/discovery-interview/SKILL.md on GitHub (opens in a new tab) -
environment-triage
Environment Triage
.claude/skills/environment-triage/SKILL.md on GitHub (opens in a new tab) -
explicit-identity
Explicit Identity Across Boundaries
.claude/skills/explicit-identity/SKILL.md on GitHub (opens in a new tab) -
explore
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
.claude/skills/explore/SKILL.md on GitHub (opens in a new tab)
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.