agentmods.dev

operations

operations is a skill for Claude Code from rapidreview-io/Merv. It costs 50 tokens per session (1,026 once invoked), scanned A, original, Apache-2.0.

An operations skill for Merv, a system that dispatches coding agents to machines and tracks their work.

In plain words
What is it for?
It is for checking project and worker status and, with approval, steering workers, dispatch, machine use, and compute limits.
Why use it?
It helps you find stalled work, blocked workers, unavailable machines, and dispatch or budget problems before deciding what to change.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the merv plugin — 4 skills, 1 MCP server shipped together

not rated 7repo changed 12d ago A scan 50 tokens original Apache-2.0

Good fit It is for checking project and worker status and, with approval, steering workers, dispatch, machine use, and compute limits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rapidreview-io/merv/operations
View source ↗ rapidreview-io/Merv rapidreview.io
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 rapidreview-io/Merv --skill operations
Clone the repo
git clone --depth 1 https://github.com/rapidreview-io/Merv

Made for: Claude Code.

Or install merv, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 operations

README.md
[![agentmods](https://agentmods.dev/badge/skills/rapidreview-io/merv/operations/github.svg)](https://agentmods.dev/skills/rapidreview-io/merv/operations)
Your own site
<a href="https://agentmods.dev/skills/rapidreview-io/merv/operations"><img src="https://agentmods.dev/badge/skills/rapidreview-io/merv/operations/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.

agentmods 80×15 button for operations

Your own site · 80×15
<a href="https://agentmods.dev/skills/rapidreview-io/merv/operations"><img src="https://agentmods.dev/badge/skills/rapidreview-io/merv/operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,026 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.
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 $0.00050 $0.01026
Opus 5.5 $0.00020 $0.00410
Sonnet 5.5 $0.00010 $0.00205
Haiku 4.5 $0.00005 $0.00103

Measured 12d ago against content hash d68662554e84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

operations 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 12d 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.

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.

clients/claude-code/skills/operations/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating a Merv project

Merv dispatches ready work to agent sessions on machines. This skill is how to see that machinery and steer it. Read first; every control below changes what runs.

Noun tools take {"action":"x","x":{...}}, with the selected projectId at the top level. For example, workflow.read takes {"action":"status","status":{}}.

Read before acting

  • project.read (status): the first read for any operational question. Dispatch, Fleet allocations, runners, sessions, waiting work, blockers. It changes nothing; do not propose a control just to inspect.
  • session.read (stuck): everything that stopped moving, and why. Each item has kind, code, why and next; why and next are advice, and the server still enforces every guard. Kinds include:
    • session_idle: no Merv call for a while. Not proof of a problem; it may be computing.
    • dispatch_held: withheld from automatic dispatch after failed launches.
    • work_blocked: something published a blocker, such as a worker's question to its owner (code agent_question, see the owners-agent skill).
    • work_waiting: waiting for its compute; it comes back by itself.
    • ready_quiet, dispatch_disabled, no_live_runner.
  • workflow.read (status) with an instanceId: one work item's gate and blockers.

Steering a worker

  1. session.read (find) with the work's instanceId returns its current and latest session and the threadId; session.read (threads) lists the thread of every stage.
  2. session.read (calls) with a threadId shows that thread's recent Merv calls; session.read (messages) shows the messages to it and the questions its agent asked.
  3. session.write (message) with threadId, body and requestId queues a durable message that the live visit, or the next one, reads.

A pending message refuses the worker's next Merv calls until it acknowledges, so say everything in one message and do not send one only to ask for status. A queued message is not proof it was read, and an acknowledgement is not proof a correction was made. Messaging does not stop compute or change an approved plan: for work that should end, halt it or end the record, then create replacement work that refers to the earlier evidence.

Read the full file on GitHub · 78 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. 12d ago Changed · -2 lines · -2 tokens per session d68662554e84
  2. 16d ago Changed · +4 lines 044da377950c
  3. 18d ago Changed · +5 lines 6039bf041829
  4. 19d ago First seen · 71 lines · 52 tokens per session scan A 15cb0d719481

Subscribe to this mod's changes

operations is a skill published in the GitHub repository rapidreview-io/Merv (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,026 once invoked, about $0.0002 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 2026-10-20.

Building agentsProject management
Related

operations compared with skills from other repositories

operations next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
operationsrapidreview-io/MervSkill74d agoApache-2.0A50Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code