#subagents

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Python implementation of coding agent core mechanisms, with architecture comparison across Claude Code / Kimi Code / Codex

Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.

Claude as subagents in Codex — scoped workers, resumable sessions, git-ignored logs.

A session-based working method for coding agents: plan in thin complete slices, build one at a time, verify by observing real behaviour, hand off cleanly. Skills + agents + 2 hooks for Claude Code.

Visualize Claude Code dynamic workflows from your terminal — a fan-out→barrier→reduce DAG, a gantt timeline, live concurrency, and a self-contained interactive HTML report. Zero runtime deps.

Awesome Claude Code And Agent Tools

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

🚢 A crew of IDE agnostic sub-agents, slash-command workflows and tools that drive a GitHub issue from open to a reviewed, CI-green pull request — autonomously. Flagship: /ship-issue.

Safe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated Fable 5 top rung. Not the cheapest router; the safest one inside Claude.

Long-running delegation architecture for Claude Code: a delegator main session + full-power orchestrator subagents — nested agents that actually delegate, skill-driven spawning, gates, crash-safe resume. Probe-proven physics + cleanroom test harness.

Delegate work to isolated sub-agents inside the pi coding agent — proven multi-agent patterns with safety, cost caps, and tracing built in.

JM's Claude Code workflow as a redistributable plugin: rules, hooks, agents, commands, and tweakcc patches packaged for less-advanced CC users.

Battle-tested multi-agent dev team for Claude Code — 9 specialized sub-agent templates + a 6-stage pipeline with agent memory, verdict protocols, commit checkpoints & standing review prompts. CLAUDE.md constitution, bug-pattern library, full Laravel + React example. Bilingual EN/AR. Extracted from a production app with 200+ releases.

Claude Code plugin for OpenAI Codex subagents, Codex Spark, parallel code review, and long-running Codex sessions via daemonless MCP

Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.

Best OpenCode Fork with Task DAGs & Semantic Retrieval 2026 - Stateful Agent Workbench

Keep Claude Code and Codex skills and subagents in sync from one source of truth.

Persistent explorer and worker subagents for the Pi coding agent

Local-first CLI: which Claude Code skills, subagents and hooks actually fire, what they cost, and which are dead weight.

Run Claude Code as a teammate that owns work end to end. A maintained CLAUDE.md (works as AGENTS.md) plus a plan/execute/review skill pipeline with external verification, adversarial review, and structurally safe parallel execution. Dated changelog, updated when model behaviour changes.

Deploy a Full AI Engineering Team 2026 - Claude 12-Agent System with Automated Quality Hooks

Portable agent patterns: reviewers and gates that deploy to Claude Code, Codex, Cursor, or any AGENTS.md harness from one source of truth.

A production-grade agent harness for the pi coding agent — subagents, isolated-worktree /ultraplan, guard-rail hooks, persistent memory, and the ftales enchanted TUI.

DeepAgents core understandings and developement of advanced ai agents. With memory, skill, tools, subagents, multiagents flow & cababilities etc.

Top Free Context Engineering Plugin 2026 - Claude Code, Cursor & Codex Setup

Stoa-substrate-aware overlay for parallel-dag-execution. Adds a dag-implementer-stoa variant that participates in the vault feedback loop via vault.claim + vault.agent-memory.

Multi-model orchestration plugin for Claude Code: an Opus supervisor delegates coding tasks to Haiku/Sonnet subagents, consults a Fable advisor, reviews every diff, and optionally routes work to OpenAI Codex. One orchestrator, the right model for every job.

[ClaudeCodeプラグイン]仮想会社

Confidence-gated model routing for coding agents — run work at the cheapest model that can pass verification. SKILL.md, MIT.