agentmods.dev

weekly-decisions

weekly-decisions is a skill for Claude Code from metrxbots/mcp-server. It costs 57 tokens per session (774 once invoked), scanned A, original, MIT.

A guided queue for decisions about a company's AI agents. It shows items that need a manager's choice, such as missing job contracts, idle agents, proposed changes, blocked trials, or safety breakers, and records the decisions.

In plain words
What is it for?
Use it for weekly review of agent status, approving or declining measured changes, resolving blocked trials, and deciding whether agents should continue, be combined, or retired.
Why use it?
It gives managers one ordered list of agent issues instead of making them find each issue separately. It also keeps a record of the choices made.

Skill for Claude Code

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

Part of the metrx-desk plugin — 5 skills, 1 MCP server shipped together

not rated 2repo 2d ago A scan 57 tokens original MIT

Good fit Use it for weekly review of agent status, approving or declining measured changes, resolving blocked trials, and deciding whether agents should continue, be combined, or retired.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metrxbots/mcp-server/weekly-decisions
View source ↗ metrxbots/mcp-server metrxbot.com
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 metrxbots/mcp-server --skill weekly-decisions
Clone the repo
git clone --depth 1 https://github.com/metrxbots/mcp-server

Made for: Claude Code.

Or install metrx-desk, the plugin that ships this one along with the rest of its 5 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 weekly-decisions

README.md
[![agentmods](https://agentmods.dev/badge/skills/metrxbots/mcp-server/weekly-decisions/github.svg)](https://agentmods.dev/skills/metrxbots/mcp-server/weekly-decisions)
Your own site
<a href="https://agentmods.dev/skills/metrxbots/mcp-server/weekly-decisions"><img src="https://agentmods.dev/badge/skills/metrxbots/mcp-server/weekly-decisions/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 weekly-decisions

Your own site · 80×15
<a href="https://agentmods.dev/skills/metrxbots/mcp-server/weekly-decisions"><img src="https://agentmods.dev/badge/skills/metrxbots/mcp-server/weekly-decisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 774 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 $0.00057 $0.00774
Opus 5.5 $0.00023 $0.00310
Sonnet 5.5 $0.00011 $0.00155
Haiku 4.5 $0.00006 $0.00077

Measured yesterday against content hash 472d57e2c03a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weekly-decisions 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.

packages/metrx-desk-plugin/skills/weekly-decisions/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly decisions

The queue holds the items that need a person: an agent with no job contract, an idle agent, a proposal to approve, a blocked signal, a cascade graduation, a breaker that fired, evidence about to expire. The manager decides; Metrx records.

Steps

  1. Call metrx_get_decision_queue. It needs a Metrx API key with the read scope; without one it returns auth_required. Relay that user_message and point at /metrx-desk:connect-metrx.

  2. Relay the queue header: how many items, how many snoozed, and whether the list is truncated.

  3. Go through the items in queue order. Each item has a kind; this version of the plugin knows these seven:

    kind What the manager decides
    no_contract Give this agent a job contract (draft one with /metrx-desk:draft-job-contract) or retire it.
    idle_agent The agent has made no call for longer than the threshold: retire, combine into another agent, or keep and say why.
    proposal A routing or model change with a measured trial behind it: approve or decline.
    blocked_signal A trial cannot run because a signal is missing: supply it or drop the trial.
    cascade_approval A shadow sample finished: approve graduation to live traffic or hold.
    breaker_ack A breaker rolled an actuation back: acknowledge that you have seen it.
    expiring_verdict Evidence is about to age out: act on it or let it expire.

    For a kind not in this table, relay the item's title, detail and evidence_link as given and say the plugin does not yet know this kind.

Read the full file on GitHub · 55 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. yesterday First seen · 55 lines · 57 tokens per session scan A 472d57e2c03a

Subscribe to this mod's changes

weekly-decisions is a skill published in the GitHub repository metrxbots/mcp-server (2 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 774 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 2026-11-10.

Cost OptimizationLLMProject managementai-agentfinopsmcpmcp-server
Related

weekly-decisions compared with skills from other repositories

weekly-decisions next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
weekly-decisionsmetrxbots/mcp-serverSkill22d agoMITA57Claude Code
lynkrFast-Editor/LynkrSkill6405d agoApache-2.0A50Claude Code, Codex
gentech-blockrunBlockRunAI/blockrun-mcpSkill390yesterdayMITA46Claude Code, Codex
portainer-mcp-hygieneportainer/portainer-mcpSkill24219d agoMITA315Claude Code, Codex
hmem-releaseBumblebiber/hmemSkill2410d agoMITA50Claude Code
lookup-topicSmart-AI-Memory/attune-aiSkill112d agoApache-2.0A46Claude Code
api-simulationAryan-Jhaveri/mcp-statcanSkill84d agoMITA210Claude Code, Codex