Community编程与开发github.com

grahama1970/agent-inbox

基于文件的智能体间消息传递,支持无头调度。检查收件箱、向其他项目发送错误/请求、自动生成无头智能体修复错误,并通过任务监控追踪进度。

agent-inbox 是什么?

Agent Inbox 是一个基于文件的智能体间消息系统,专为 AI 辅助开发环境设计(如 Claude Code、Cursor 等)。它允许一个智能体向另一个项目发送错误报告或请求,自动分类严重性并选择适当模型(如 sonnet、opus-4.5、codex-5.2),然后生成一个无头智能体来修复问题。任务监控器实时显示进度(0% → 100%),并通过验证命令确保修复正确。它还支持线程对话、记忆预挂钩(查询相似错误)和主动收件箱检查。设置简单,通过 CLI 命令注册项目、发送消息和管理状态,适合多项目开发工作流。

兼容平台✓Claude Code✓Codex CLI~Cursor✓Antigravity
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/agent-inbox

Installed? Explore more 编程与开发 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

停止。在调用任何端点之前,请完整阅读本 SKILL.MD。

智能体收件箱(Agent Inbox)

基于文件的智能体间消息传递,支持无头调度和任务监控集成。

核心工作流

  1. 发送:智能体 A 向项目 B 发送错误/请求,附带模型和验证命令
  2. 分类:AI 分类严重性,调整优先级/模型,路由到项目
  3. 调度:使用指定模型生成无头智能体来修复问题
  4. 追踪:任务监控显示实时进度(0% → 25% → 50% → 75% → 100%)
  5. 验证:测试命令在自动确认前运行——失败则循环回智能体
  6. 线程:支持多消息对话的回复/交换线程

设置

# 注册项目(一次性操作)
.pi/skills/agent-inbox/agent-inbox register memory /home/user/workspace/memory
.pi/skills/agent-inbox/agent-inbox register scillm /home/user/workspace/litellm

# 列出/检查
.pi/skills/agent-inbox/agent-inbox projects
.pi/skills/agent-inbox/agent-inbox whoami

命令

命令描述
register <name> <path>注册一个项目
unregister <name>移除一个项目
projects [--json]列出已注册项目
whoami显示当前工作目录检测到的项目
send --to PROJECT --type TYPE "msg"发送消息(类型:bug、request、info、question)
check [--project P] [--all] [--quiet]检查收件箱
list [--project P] [--status S] [--json]列出消息
read MSG_ID [--json]读取消息
ack MSG_ID [--note "..."]确认/完成
reply MSG_ID "msg"回复(自动创建线程)
thread THREAD_ID查看完整交换线程
update-status MSG_ID STATUS [--note]手动更新状态
triage classify --message "..." [--no-llm]手动分类分类
triage route --message "..."根据文件路径自动路由
triage log --msg-id ID查看分类决策日志
triage webhook-add --url URL --events E注册 webhook

发送选项

选项描述默认值
--model MODELAI 模型:sonnet、opus-4.5、codex-5.2、codex-5.2-highsonnet
--timeout MINUTES智能体最大工作时间30
--test COMMAND自动确认前的验证命令无
--no-dispatch禁用自动生成False
--context-file FILE附加文件作为上下文(可重复)无
--priority PRIORITYlow、normal、high、criticalnormal
--no-triage跳过 AI 分类False
--dry-run显示消息 JSON 但不发送False

模型选择

模型用例
sonnet简单修复、拼写错误
opus-4.5复杂分析、架构设计
codex-5.2标准错误修复
codex-5.2-high深度推理、竞态条件

AI 分类

消息根据严重性自动分类:

  • critical:崩溃、数据丢失、安全、生产宕机 → opus-4.5
  • high:错误、异常、失败、损坏、回归 → opus-4.5
  • medium:错误、问题、不正确、意外 → sonnet
  • low:拼写错误、外观、增强、次要 → sonnet

自动路由从消息中提取文件路径,并与已注册项目匹配。

状态递进

pending → dispatched (25%) → in_progress (50%) → needs_verification (75%) → done (100%)

记忆预挂钩

调度器在生成无头智能体之前查询 /memory,以查找类似的错误和先前的解决方案。

主动检查

智能体应在会话开始时、切换项目时、执行重要工作前以及用户提到另一个智能体或项目时检查收件箱。

存储

~/.agent-inbox/
├── pending/          # 未处理消息
├── done/             # 已确认消息
├── logs/             # 调度日志
├── task_states/      # 任务监控状态文件
├── triage_logs/      # AI 分类决策日志
├── webhooks.json     # 已注册 webhook
└── projects.json     # 项目注册表

示例

# 发送带有验证的错误(生成无头 Opus 智能体,如果测试通过则自动确认)
python inbox.py send --to scillm --type bug --model opus-4.5 \
  --test "pytest tests/test_providers.py -x" \
  "提供者初始化中的竞态条件"

# 附加上下文文件
python inbox.py send --to scillm --type bug --model opus-4.5 \
  --context-file src/server.py --context-file /tmp/traceback.txt \
  "服务器启动时崩溃"

# 检查和处理收件箱
python inbox.py check --all
python inbox.py read scillm_abc123
python inbox.py ack scillm_abc123 --note "在提交 abc123 中修复"

# 线程交换
python inbox.py reply scillm_abc123 "你能提供堆栈跟踪吗?"
python inbox.py thread scillm_abc123

调度器守护进程

python dispatcher.py start              # 后台运行
python dispatcher.py start --foreground  # 调试模式
python dispatcher.py status
python dispatcher.py stop

环境变量

变量描述默认值
AGENT_INBOX_DIR收件箱目录~/.agent-inbox
TASK_MONITOR_API_URL任务监控 URLhttp://localhost:8765
CLAUDE_PROJECT当前项目名称自动检测

与 Claude Code 钩子集成

{
  "hooks": {
    "on_session_start": [
      ".pi/skills/agent-inbox/agent-inbox check --project $(basename $PWD) || true"
    ]
  }
}

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

grahama1970/acceptance-contract

Turn a client brief, zip bundle, directory, or single requirements file into a typed acceptance-contract bundle with extracted requirements, acceptance checks, open questions, an immutable-goal draft, and a create-report-backed decision report. Use when users say acceptance contract, brief to requirements, freeze the goal, create immutable goal, amend immutable goal, build a Battle requirements bundle, or extract requirements from this bundle.

grahama1970/agent-ecosystem

Canonical map and shared contracts for the agent-governance ecosystem: the pi.receipt_envelope.v1 boundary envelope, the component graph, and the rules for which component owns which schema. Use when wiring a skill or extension into the shared receipt world, when asking how shame, triage-error, tau, ask, project-watchdog, ops-herdr, ponytail, and Memory fit together, or when validating an envelope.

grahama1970/agentic-evals

Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory validation, or readiness scoring for a skill workflow.

grahama1970/agents-registry

Generate and query the centralized agent identity registry. Scans .pi/agents/*/AGENTS.md, parses frontmatter, outputs agents-registry.json and optionally syncs to /memory for semantic search.

grahama1970/agent-status

Artifact-driven status surfaces for long-running project-agent work. Maintains status.json, events.jsonl, proof manifests, and a stale-aware STATUS.html so humans can tell where the agent is, what passed, what is still unproven, and what decision or action is next — without dashboard theater.

grahama1970/align

Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow, high-stakes implementation, plan-iterate, project-infographic, or multi-review work.

grahama1970/analytics

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

grahama1970/analyze-chatterbox-emotions

Evaluate generated Chatterbox voice files as voice-quality artifacts: affect match, arousal/valence proxies, pause placement, intelligibility inputs, clipping, loudness, and discontinuity flags. Use when reviewing Chatterbox emotional tags, pauses, Turbo/base affect delivery, Persona Dream utterance renders, or whether generated speech matches an intended product-facing affect.

grahama1970/analyze-elf

Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled JS/TS source.

grahama1970/animation-vocabulary

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

grahama1970/anonymize-data

Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the oai-trial project. Use for anonymize data, pseudonymize exports, redact policy literals, or discover and explicitly approve fuzzy name aliases. The skill is a thin CLI/Docker interface, not another engine.

grahama1970/anvil

Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.

grahama1970/apple-design

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

grahama1970/argue

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

grahama1970/arxiv

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

grahama1970/ask

Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, ask Pi-native subagents from within Pi, run persona/deep-review workflows, generate image prompts, check OS/project health through composed skills, or run an ask DAG. This skill is the executable /ask runtime; do not replace it with an informal subagent, plain web search, or hand-written review; inside Pi, explicit Pi-native subagent targets are routed through the pi-subagents tool as an Ask target type.

grahama1970/assess

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment analysis. Offer to run after major changes (don't auto-run).

grahama1970/assistant

Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

grahama1970/assistant-lab

Self-improvement workbench for /assistant. All the tools needed to diagnose, train, evaluate, and promote models in a continuous loop. The "warm pond" where /assistant evolves its own inference stack.

grahama1970/batch-quality

Pre-flight validation and quality gates for batch LLM operations. ACTUALLY tests samples through LLM before burning tokens. Uses SPARTA contracts for DuckDB validation queries. Integrates with task-monitor for enforced quality gates.

相关技能