Agent Plugins Marketplace
All plugins

evidence-gated

v0.4.30

One evidence-gated methodology run as three market flows: a Korean sleeve, a US sleeve, and the allocator that sets their budgets and proposes the cross-market rebalance. The flows are subagents of one manager; only the orchestrator submits.

Claude Code14 Skills1 MCP serverstdio

0 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes
Claude Code
Parsed components
15 skill or MCP entries
Source updated
Sep 6, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install evidence-gated for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install evidence-gated@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/untilled/aumos-catalogue

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is managers/evidence-gated/.

Plugin files

managers/evidence-gated/
├── .claude-plugin/plugin.json
├── skills/allocate/SKILL.md
├── skills/candidate-research/SKILL.md
├── skills/data-source-contract/SKILL.md
├── skills/deterministic-metrics/SKILL.md
├── skills/evidence-gates/SKILL.md
├── skills/kr-sleeve/SKILL.md
├── skills/memory-contract/SKILL.md
├── skills/orchestrate/SKILL.md
├── skills/outcome-calibration/SKILL.md
├── skills/position-research/SKILL.md
├── skills/sizing-and-concentration/SKILL.md
├── skills/theme-radar/SKILL.md
├── skills/thesis-challenge/SKILL.md
├── skills/us-sleeve/SKILL.md
└── .mcp.json

Included Skills14

allocateskills/allocate/SKILL.md

Sleeve budgets, total cash, FX, portfolio-wide concentration and the cross-market REBALANCE. Loaded by the allocate flow, after both sleeves.

candidate-researchskills/candidate-research/SKILL.md

Declare the universe this run sweeps, then research a candidate under its discovery lens — why-cheap, trap, variant, scenario and benchmark-alternative tests.

data-source-contractskills/data-source-contract/SKILL.md

Route Toss, SEC EDGAR, Alpaca, optional OpenBB/FMP and web research while enforcing point-in-time, freshness and graceful-degradation rules.

deterministic-metricsskills/deterministic-metrics/SKILL.md

Run versioned scanner, sizing, coverage, evidence, calibration, attribution, source parsing and scheduling calculations without free-form arithmetic.

evidence-gatesskills/evidence-gates/SKILL.md

Classify decision evidence maturity and decide whether a lens may support observation, a controlled experiment, review, or promoted sizing.

kr-sleeveskills/kr-sleeve/SKILL.md

XKRX research and the Korean sleeve, inside the budget the allocator recorded. Loaded by the kr-sleeve flow.

memory-contractskills/memory-contract/SKILL.md

Read and append instance-private learning revisions safely, including empty, malformed and historical-asOf behavior.

orchestrateskills/orchestrate/SKILL.md

How this manager runs its three market flows and assembles their answers into one proposal. Load before dispatching any flow.

outcome-calibrationskills/outcome-calibration/SKILL.md

Turn closed Aumos decisions and forward outcomes into lens calibration, evidence maturity and failure summaries without auto-changing rules.

position-researchskills/position-research/SKILL.md

Sell-side watch on what is already held — price rules and fundamental invalidation running in parallel, with no buy-side proposal allowed.

sizing-and-concentrationskills/sizing-and-concentration/SKILL.md

Convert an evidence-qualified view into non-negative target weights under mandate, concentration, maturity and watch-hygiene constraints.

theme-radarskills/theme-radar/SKILL.md

Forward research — examine at least one axis outside the declared universe every run, find the sector or theme that will lead in three to six months, register it as a paper thesis call, and refuse the ones that are already consensus.

thesis-challengeskills/thesis-challenge/SKILL.md

Challenge a new or promoted single-name thesis for structural damage, valuation traps, weak invalidation and benchmark dominance.

us-sleeveskills/us-sleeve/SKILL.md

XNAS/XNYS research and the US sleeve, including policy-designated SGOV liquidity, inside the allocator's budget. Loaded by the us-sleeve flow.

MCP servers1

evidence-gated-metricsstdio
command
node
args
${AUMOS_MANAGER_PACKAGE}/bin/evidence-gated-metrics-mcp

Plugin manifests1

managers/evidence-gated/.claude-plugin/plugin.json
{
  "name": "evidence-gated",
  "version": "0.4.30",
  "description": "One evidence-gated methodology run as three market flows: a Korean sleeve, a US sleeve, and the allocator that sets their budgets and proposes the cross-market rebalance. The flows are subagents of one manager; only the orchestrator submits."
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[evidence-gated on Agent Plugins Marketplace](https://pluginsmp.com/plugins/evidence-gated)