operator-inbox

operator-inbox is a skill for Claude Code, Codex from runxhq/runx. It costs 20 tokens per session (1,250 once invoked), scanned A, original, Apache-2.0.

A local work queue that turns bounded observations from external providers into trackable action items with human decisions and resumable scans.

In plain words
What is it for?
It records observations, maintains work-item identity and status, stores human dispositions, tracks scan progress, and lets operators read the resulting action queue.
Why use it?
It keeps operator state in a provider-neutral local queue instead of making a chat or service connector responsible for it. It also prevents duplicate work and supports reopening items when needed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It records observations, maintains work-item identity and status, stores human dispositions, tracks scan progress, and lets operators read the resulting action queue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/operator-inbox
Install

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.

Any agent
npx skills add runxhq/runx --skill operator-inbox
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for operator-inbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/operator-inbox.svg)](https://agentmods.dev/skills/runxhq/runx/operator-inbox)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/operator-inbox"><img src="https://agentmods.dev/badge/skills/runxhq/runx/operator-inbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.01250
Opus 5 $0.00010 $0.00625
Sonnet 5 $0.00004 $0.00250
Haiku 4.5 $0.00002 $0.00125

Measured 4d ago against content hash e3798c5543b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

operator-inbox scanned grade A with 0 findings 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (graph/plan/plan.mjs, graph/state.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/operator-inbox/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operator Inbox

Maintain a durable action queue without turning a connector into the owner of operator state.

The caller fetches bounded, grant-authorized provider pages and passes their normalized observations to this skill. The skill owns work-item identity, status, dispositions, replay suppression, reopen rules, and scan coverage. Every read and write is composed through data-store; the skill does not call Slack, SQLite, Postgres, or another provider directly.

Composes

  • data-store#append_event
  • data-store#list_stream_heads
  • data-store#read_events

What this skill does

Use local://runx/operator-inbox/default unless the operator selects another logical source. Unbound local refs resolve to SQLite under .runx/data/local-sources/. A hosted database is opt-in through the same data_source_ref binding. Runx Connect may still own OAuth, grants, and provider execution; that does not move this queue into the hosted control plane.

Observations and resumable checkpoints live in operator_inbox_scans, partitioned by query digest. Action snapshots live in operator_inbox_actions, with one stream per stable thread digest. Queue reads use bounded list_stream_heads pages; no command folds or transports the complete queue.

Direct invocation defaults to a bounded list_actions read against that local source. To record a disposition or provider observation, select the exact write runner; composed graphs can pass the prior action packet without re-reading or re-fetching provider data.

When to use this skill

  • Build or revisit a local action queue from bounded connector observations.
  • Preserve an explicit resolved, dismissed, waiting, or followed_up decision across repeated provider scans.
  • Reopen a completed item when a newer external occurrence arrives.
  • Inspect bounded action or scan state without handing queue ownership to the provider or hosted control plane.

Read the full file on GitHub · 131 lines

Changes

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.

  1. 4d ago First seen · 131 lines · 20 tokens per session scan A e3798c5543b2

Subscribe to this mod's changes

operator-inbox is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 1,250 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.