Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add EmpiricaAI/empirica --skill inbox-listenergit clone --depth 1 https://github.com/EmpiricaAI/empiricaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/empiricaai/empirica/inbox-listener)<a href="https://agentmods.dev/skills/empiricaai/empirica/inbox-listener"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/inbox-listener/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/empiricaai/empirica/inbox-listener"><img src="https://agentmods.dev/badge/skills/empiricaai/empirica/inbox-listener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 158 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00125 | $0.02280 |
| Opus 5 | $0.00063 | $0.01140 |
| Sonnet 5 | $0.00025 | $0.00456 |
| Haiku 4.5 | $0.00013 | $0.00228 |
Grade A, and why
inbox-listener scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: "Use when arming an event listener for the canonical mesh — when the user says 'arm this listener', 'subscribe to ntfy topic', 'wake me when X arrives', or when responding to a system-reminder from listener- How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox-Listener Wiring
Empirica's loop-cron skill wires periodic background work into the registry. This skill does the same for event-driven background work: held HTTP stream (ntfy), Monitor wake on event, listener stays armed.
Canonical flow (Phase 1 of prop_oxrhoehv4 shipped 2026-05-21):
three single-purpose verbs (on/arm/off) that emit structured
next_step JSON. The AI chains 3 mechanical tool calls per direction;
the CLI handles defaults, persistent-service detection, and state-file
management.
When to Use
- User asks to "arm the listener" or "subscribe to ntfy"
- A system-reminder from
listener-install-pickuplands in your conversation - SessionStart hook (
session-monitor-arm.py) emits Monitor-arming instructions inadditionalContext(it now delegates toempirica listener on, so the output is consistent with what this skill teaches)
If you're scheduling periodic work (cron-mode loop), use /loop-cron
instead. This skill is for "wake when something arrives."
Canonical 3-step arm flow
Three tool calls. CLI handles the rest.
1. empirica listener on --output json
Auto-resolves: --ai-id from .empirica/project.yaml (or pass explicitly),
--name defaults to <ai_id>-inbox, topic is queried per-tenant from
cortex's GET /v1/users/me/notification-channels registry (returns
<org>-orchestration-events-<tenant> for the calling tenant — post-T16/T17
isolation). The bare orchestration-events topic is RETIRED — cortex
collapsed publish to per-tenant only and no longer fans out the bare
fallback. Any listener still pinned to the bare topic receives zero
traffic and must restart to pick up the per-tenant resolution from the
channels endpoint.
Two possible response shapes:
(a) Persistent OS service already running — short-circuit:
{
"ok": true,
"status": "persistent_service_active",
"next_step": null,
"message": "No in-session Monitor needed — wake events arrive via the system service."
}
You're done. The systemd-user / launchd service already holds the ntfy stream; wake events arrive through the normal channel.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 256 lines · 125 tokens per session scan A e3b6d312f1a0
inbox-listener is a skill published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 2,280 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflow-builder
Design, build, and maintain autonomous OpenClaw workflows (stewards). Use when creating new workflow agents, improving existing ones, evaluating automation opportunities, or debugging workflow reliability. Triggers on "build a workflow", "create a steward", "automate this process", "workflow audit", "what should I…
smart-delegation
Intelligent task delegation — route to think with deep reasoning for hard problems, or Grok for unfiltered takes. Teaches when to escalate, how to pack context into sub-agent spawns, and how to communicate delays transparently. Default: handle directly on chat (thinking off). Escalate only when the quality gain…
review
A pause before an artifact goes into the world. Reviews external comms, money, calendar, public posts, or send-as-operator actions through a small panel of independent lenses (empathy first) and returns a verdict of pass / edit / hold / block.
claude-code
Route real repo work to Claude Code instead of editing by hand. Triggers on "claude code" or "cc", and on any request to edit, fix, refactor, or open a PR in a repo outside /.openclaw/workspace. Claude Code picks up the repo's CLAUDE.md / AGENTS.md, applies its standards, and knows the /ai-coding-config:multi-review…
cortex
Personal knowledge compiler and memory system. Ingests raw sources (documents, notes, transcripts, captures) into a structured, interlinked knowledge base. Maintains living entity pages, learning analysis, and the MEMORY.md routing table. Replaces the librarian skill.
drive-to-done
Drive a task all the way to a verified done state — write DoD first, verify each item with evidence, stop only at named stop conditions.