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 runxhq/runx --skill attention-reviewgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/attention-review)<a href="https://agentmods.dev/skills/runxhq/runx/attention-review"><img src="https://agentmods.dev/badge/skills/runxhq/runx/attention-review/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/runxhq/runx/attention-review"><img src="https://agentmods.dev/badge/skills/runxhq/runx/attention-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.01339 |
| Opus 5.5 | $0.00010 | $0.00536 |
| Sonnet 5.5 | $0.00005 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
attention-review 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attention Review
Use this skill to decide what deserves attention after an operator has collected a bounded page of mailbox, chat, or other skill evidence. It uses current action dispositions and preferences to select priorities, then returns a private briefing intent, exact work proposals, and a proposed next check. It does not read an account, post a message, change an action, or schedule a timer.
The surrounding Runx operator pins the source roster, audience, permitted action IDs, and limits. It reads sources through their owning skills, records observations and their dispositions in the workspace store, and persists timing through the store. The operator supplies exact configured work_routes. When a selected open source needs work and a suitable route exists, propose that route with its exact thread target; a selected item without a work proposal will only be briefed. The finalizer validates proposals against the configured roster, current dispositions and selected source occurrences. This skill does not assign or run work. The local host persists an admitted assignment through the store and invokes the owning downstream skill; its provider readback and receipt establish completion. A completed read may return as typed work_results on a later turn, bound to the original source and exact target. Use this verified state to avoid repeating stale requests or non-mutating checks; it does not change the recorded disposition. A proposal alone is not a completed task.
If this skill recommends a private update, the operator prepares and delivers the exact text through message-send under native notification authority and checks provider readback. A recommendation or sealed receipt from this skill is not a delivered message. Other skill actions remain proposals until the configured roster and their native permission owners admit them.
The native invocation supplies the private charter and scoped operator-confirmed memory as context entries. Context guides priority and next-check judgment; it is not provider evidence. The local operator stores confirmed memory in its governed control aggregate, pins the context with the turn, and treats a change as a new review revision. Source messages and model inferences never create confirmed memory; the operator must explicitly record or remove it. The skill manual supplies the stable rubric; the private charter supplies this user's priorities.
Call review with up to 20 normalized observations. Each observation needs a stable source reference, SHA-256 digest, observed time, source kind, and a short factual summary. Supply current action dispositions and preferences as bounded context. Already collected evidence is passed directly; the skill never refetches it. A partial source scan must remain marked partial in the surrounding operator, and the operator must commit action observations before advancing its scan cursor.
The result cites only admitted source references. The deterministic finalizer builds the brief and decides ready versus idle from the admitted item set rather than trusting the model's decision label or message text. It omits unconfigured action and work-route suggestions and reports their counts; they never become authority or suppress an otherwise valid non-mutating brief. A proposed target that conflicts with a configured route's exact candidates still holds the packet. Unknown source references, malformed output, or selection of an action whose recorded disposition is not open produce a held result. The next-check proposal is clamped to the caller's bounds; the operator then applies quiet hours, source cadence, retry and budget policy. Missing context should be reported as a hold, not invented as a negative finding. Snooze and due-time reminders are the operator's transitions, not this skill's.
For example, a new inbox thread asking for a reply and a routine chat update may yield one high-priority item and a private briefing proposal. The operator still owns the queue transition and any delivery. If a chat ping refers to an external resource whose live state matters, the local host can offer an exact configured non-mutating candidate after recording the observation. The owning skill verifies that state, and its receipt-backed result informs a later review; the ping itself is not proof of live state.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 229148ef6d29
- 3d ago Changed 46cf2b769af4
- 5d ago Changed · +2 lines af1e2b04b83e
- 11d ago First seen · 36 lines · 25 tokens per session scan A 7e6fac48b2ba
attention-review is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 1,339 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
gmail
Search, read, draft, and send Gmail when the user asks to work with their inbox or email.
google-calendar
Read schedules, check availability, and create or update Google Calendar events when the user asks to work with their calendar.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
openrig-herdr
Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via rig terminal, watching another rig read-only, or driving herdr on an agent's request ("open all my rigs + a mission as views"). Covers the rig terminal open|views|status…
mission-slice-sop
Use when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.