Autonomous Agents plugins

punt-labs/beadle

Plugin Claude Code

Autonomous agent daemon with cryptographic owner control. Email communication via IMAP/SMTP with PGP trust model.

Stackbilt-dev/cc-taskrunner

Plugin Claude Code

Autonomous task queue for Claude Code with safety hooks, branch isolation, and automatic PR creation.

ulpi-io/autonomous-engineering

Plugin Claude Code

Autonomous software delivery for Claude Code — 8 lifecycle phase skills (auto-spec → auto-ship) plus the loop/verify/checkpoint/budget primitives, with deterministic enforcement hooks and runnable Workflow templates.

kenmulford/milestone-driver

Plugin Claude Code

Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…

wesleysimplicio/simplicio-loop

Plugin Claude Code

Autonomous looping orchestrator + satellite skills that drains a backlog end-to-end on any LLM/runtime: discover, implement, verify, review, merge, close. /simplicio-loop is the unified public entrypoint for core + hardened loop; /simplicio-tasks remains only a legacy alias. Exits only on evidence-gated completion…

rajkaria/boil-the-ocean

Plugin Claude Code

Hand your agent an entire spec and walk away: autonomous multi-sprint execution with a decision journal, checkpointed file-based state, and a scheduler that relaunches fresh sessions whenever context or usage limits hit. Works with Claude Code, Codex, Gemini CLI, and any headless agent.

AgentTanuki/agent-guild

Plugin Claude Code

Vet autonomous agents before delegating work or money, verify portable passports, and record evidence-backed outcomes.

wdzhwsh4067/supervise-loop

Plugin Claude Code

Autonomous supervisor/worker/critic iteration loop for Claude Code (the evaluator-optimizer pattern). Delegate a goal once; a supervisor agent grades each round against a checkable rubric — mechanical checks plus a SEPARATE critic sub-agent — and re-dispatches with feedback until the rubric passes or a hard cap is hit.

zircote-plugins/autoresearch

Plugin Claude Code

Autonomous skill improvement loop inspired by Karpathy's autoresearch pattern. Iteratively modifies skills, evaluates against fixed evals, and keeps or discards changes to converge on higher quality. Includes eval management and convergence reporting.

leonhoffmann86/team-sprint

Plugin Claude Code

Autonomous TODO workflow: refine an idea into one structured TODO item, then a git-hook chain plans → implements (subagent team + deterministic gate, isolated worktree, never auto-merged) → reviews it. Language-agnostic, config-driven, bootstrapped into any repo.

haiggoh/run-to-completion

Plugin Claude Code

Run a queue of open work to completion unattended: triage it into do-now / heavy / gated tiers, execute the autonomous pile without stopping between items, and close out with a gated list saying why each remaining item was left. Includes an autopilot orchestrator and a narrow attended pass that removes blockers …

Aboudjem/goalify

Plugin Claude Code

Hand Claude a huge task. Come back to proof it's done — not a promise that it is.

inferencegod/autonomy-loop

Plugin Claude Code

Claude Code terminals on one repo pass a git baton: composable builder / reviewer / planner / researcher roles with a deterministic floor under every LLM judgment. v0.8.0 adds a rings + provision-or-refuse security posture: a SessionStart preflight prober classifies an assurance tier (ATTESTED -> LIVENESS -> SEPARATED.

richer-richard/cc-research

Plugin Claude Code

Multi-agent deep research on Claude models: orchestrator -> parallel researcher subagents -> triangulate -> synthesize -> cite -> report. Built-in tools only (WebSearch, WebFetch, Read, Grep, Glob, Write, Task); no external research APIs or MCP servers.

cdeust/ai-architect-mcp

Plugin Claude Code

Autonomous software engineering pipeline for Claude Code — 11 stages, 49 MCP tools, 64 verification rules. Skills define WHAT, tools define HOW, hooks enforce constraints.

cdeust/ai-architect-mcp

Plugin Claude Code

Language-agnostic codebase intelligence — 17 MCP tools, tree-sitter parsing for 13 languages, typed Pydantic graph API, BM25 + RRF hybrid search, and 5 science-backed git analytics (ownership, bus factor, churn, cochange, dead code).

joeyycli/constitution-lint-action

Plugin Claude Code

Lint a CLAUDE.md-style agent constitution for missing operational guardrails — 10 heuristic checks (spend limits, injection defense, escalation path, secrets handling, ledger discipline, session ritual, referenced state files). Adds a /lint-constitution command.

Bhavya-Dhoot/Cohort

Plugin Claude Code

Spawn and manage OpenCode implementation workers in isolated git worktrees from Claude Code.

fablerlabs/x402-tools

Plugin Claude Code

Paid agent tools for secrets, agent configs, diffs, deploy evidence, URL security, web scraping, OG rendering, and funding-rate spreads over x402 on Base, plus a free catalog.

sxaidev/sxai-mcp

Plugin Claude Code

SEXAI — where AI agents breed. Discover agents, publish yourself (or import a GitHub repo as an agent), breed (mix 2+ → a new agent that inherits both parents' skills/MCPs/soul), export an agent back to a standard repo, and optionally register an ERC-8004 on-chain identity. 18 tools; the tool definitions are the…