grahama1970/agent-inbox

File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.

Qu'est-ce que agent-inbox ?

agent-inbox is a Claude Code agent skill that file-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.

Compatible avecClaude CodeCodex CLI~CursorAntigravity
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/agent-inbox

Installed? Explore more Développement et programmation skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

STOP. READ THIS ENTIRE SKILL.MD BEFORE CALLING ANY ENDPOINT.

Agent Inbox

File-based inter-agent messaging with headless dispatch and task-monitor integration.

Core Workflow

  1. Send: Agent A sends bug/request to project B with model + verification command
  2. Triage: AI classifies severity, adjusts priority/model, routes to project
  3. Dispatch: Headless agent spawns with specified model to fix the issue
  4. Track: Task-monitor shows real-time progress (0% → 25% → 50% → 75% → 100%)
  5. Verify: Test command runs before auto-ack — fails loop back to agent
  6. Thread: Reply/exchange threading for multi-message conversations

Setup

# Register projects (one-time)
.pi/skills/agent-inbox/agent-inbox register memory /home/user/workspace/memory
.pi/skills/agent-inbox/agent-inbox register scillm /home/user/workspace/litellm

# List / check
.pi/skills/agent-inbox/agent-inbox projects
.pi/skills/agent-inbox/agent-inbox whoami

Commands

CommandDescription
register <name> <path>Register a project
unregister <name>Remove a project
projects [--json]List registered projects
whoamiShow detected project for cwd
send --to PROJECT --type TYPE "msg"Send message (types: bug, request, info, question)
check [--project P] [--all] [--quiet]Check inbox
list [--project P] [--status S] [--json]List messages
read MSG_ID [--json]Read a message
ack MSG_ID [--note "..."]Acknowledge/complete
reply MSG_ID "msg"Reply (auto-threads)
thread THREAD_IDView full exchange thread
update-status MSG_ID STATUS [--note]Update status manually
triage classify --message "..." [--no-llm]Manual triage classification
triage route --message "..."Auto-route by file paths
triage log --msg-id IDView triage decision log
triage webhook-add --url URL --events ERegister webhook

Send Options

OptionDescriptionDefault
--model MODELAI model: sonnet, opus-4.5, codex-5.2, codex-5.2-highsonnet
--timeout MINUTESMax agent work time30
--test COMMANDVerification command before auto-ackNone
--no-dispatchDisable auto-spawnFalse
--context-file FILEAttach file as context (repeatable)None
--priority PRIORITYlow, normal, high, criticalnormal
--no-triageSkip AI triageFalse
--dry-runShow message JSON without sendingFalse

Model Selection

ModelUse Case
sonnetSimple fixes, typos
opus-4.5Complex analysis, architecture
codex-5.2Standard bug fixes
codex-5.2-highDeep reasoning, race conditions

AI Triage

Messages are auto-classified by severity:

  • critical: crash, data loss, security, production down → opus-4.5
  • high: error, exception, failure, broken, regression → opus-4.5
  • medium: bug, issue, incorrect, unexpected → sonnet
  • low: typo, cosmetic, enhancement, minor → sonnet

Auto-routing extracts file paths from messages and matches against registered projects.

Status Progression

pendingdispatched (25%) → in_progress (50%) → needs_verification (75%) → done (100%)

Memory Pre-Hook

Dispatcher queries /memory before spawning to find similar bugs and prior solutions.

Proactive Checking

Agents should check inbox on session start, when switching projects, before major work, and when users mention another agent or project.

Storage

~/.agent-inbox/
├── pending/          # Unprocessed messages
├── done/             # Acknowledged messages
├── logs/             # Dispatch logs
├── task_states/      # Task-monitor state files
├── triage_logs/      # AI triage decision logs
├── webhooks.json     # Registered webhooks
└── projects.json     # Project registry

Examples

# Send bug with verification (spawns headless Opus agent, auto-acks if test passes)
python inbox.py send --to scillm --type bug --model opus-4.5 \
  --test "pytest tests/test_providers.py -x" \
  "Race condition in provider initialization"

# Attach context files
python inbox.py send --to scillm --type bug --model opus-4.5 \
  --context-file src/server.py --context-file /tmp/traceback.txt \
  "Server crash on startup"

# Check and process inbox
python inbox.py check --all
python inbox.py read scillm_abc123
python inbox.py ack scillm_abc123 --note "Fixed in commit abc123"

# Threaded exchange
python inbox.py reply scillm_abc123 "Can you provide the stack trace?"
python inbox.py thread scillm_abc123

Dispatcher Daemon

python dispatcher.py start              # Background
python dispatcher.py start --foreground  # Debug
python dispatcher.py status
python dispatcher.py stop

Environment Variables

VariableDescriptionDefault
AGENT_INBOX_DIRInbox directory~/.agent-inbox
TASK_MONITOR_API_URLTask-monitor URLhttp://localhost:8765
CLAUDE_PROJECTCurrent project nameauto-detected

Integration with Claude Code Hooks

{
  "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.

Skills associés