claude

agent-coherence

Coherence for the prose subset of project rules that can't be expressed as policy. CLAUDE.md rules about state — 'plan.md is v3 now', 'session B just edited the file you're about to write' — can't be expressed as permissions.deny. This plugin surfaces those state changes across parallel Claude Code sessions sharing the same workspace via warnings injected into the agent's own context. Warn-mode by default; v0.2 adds per-artifact strict-mode opt-in (permissionDecision:deny on stale reads). Single-user single-host workstation; macOS/Linux/WSL2.

3 on GitHubby Vlad Parakhinv0.6.0Apache-2.0updated 1 month ago
/

Plugin agent-coherence from marketplace agent-coherence in cohexa-ai/agent-coherence-plugin. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Slash commands (3)

  • /agent-coherence:status

    Show tracked artifacts × per-session MESI states for this workspace.

  • /agent-coherence:track

    Add one or more workspace-relative paths to the coordinator's tracked set.

  • /agent-coherence:untrack

    Append one or more workspace-relative paths to the coordinator's ignored set.

Hooks (9)

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" pre-read

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" pre-edit

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" pre-bash

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" pre-grep

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" post-edit

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/bin/ensure-coordinator-dispatch

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" session-start

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" session-stop

  • SubagentStop

    "${CLAUDE_PLUGIN_ROOT}/bin/hook-client" subagent-stop

View source on GitHub agent-coherence.dev

Similar plugins

ruflo-ai-team

claude

Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results

6 skills · 6 commands · 4 agents · 1 MCP server

ruvnet/ruflo 81,589

pydantic-ai

claude

Write accurate Pydantic AI code from the start. Up-to-date patterns, decision trees, and common gotchas for agents, tools, structured output, streaming, and multi-agent apps.

anthropics/claude-plugins-official 47,076

agent-teams

claudecodex

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams

6 skills · 7 commands · 4 agents

wshobson/agents 42,461

oh-my-claudecode

claude

Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.

85 skills · 20 commands · 19 agents · 1 MCP server · hooks

Yeachan-Heo/oh-my-claudecode 40,800

agenthub

claude

Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.

8 skills · 1 agent · hooks

alirezarezvani/claude-skills 29,725

voltagent-meta

claude

Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.

VoltAgent/awesome-claude-code-subagents 26,513

Maintain agent-coherence?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted