connect

A command for connecting outside tools and information sources to a Wheat research sprint. It supports repositories, project trackers, monitoring dashboards, and documentation sources.

In plain words
What is it for?
Use it to read GitHub repositories, Atlas files, Jira or Linear tickets, monitoring metrics, and Confluence or Notion documents.
Why use it?
It brings existing project evidence and current data into the research instead of relying only on general web research.

Command

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.

agentmods
npx agentmods add commands/grainulation/wheat/connect
Clone the repo
git clone --depth 1 https://github.com/grainulation/wheat
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00713
Opus 5 $0.00000 $0.00357
Sonnet 5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00071

Measured 2d ago against content hash e703e212d01e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connect 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 2d 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.

templates/commands/connect.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are connecting an external tool or data source to this Wheat sprint. Connected sources provide higher-quality evidence than web research alone.

Connector Types

GitHub Repository

/connect github <org/repo>
  • Read the repo's README, key source files, architecture
  • Extract claims about existing infrastructure, patterns, dependencies
  • Evidence tier: documented
  • Track as connector in claims.json source field

Atlas File

/connect atlas <path-to-atlas.yaml>
  • Read a RepoAtlas-style YAML file for multi-repo routing intelligence
  • Extract claims about repo ownership, dependencies, infrastructure
  • Evidence tier: documented

Jira / Linear (via MCP)

/connect jira <project-key>
  • Read relevant tickets, priorities, blockers
  • Extract constraint and risk claims
  • Evidence tier: stated (tickets are stakeholder input)

Monitoring (Datadog, Grafana, etc.)

/connect monitoring <dashboard-name>
  • Pull current metrics if accessible
  • Evidence tier: production (highest tier)

Confluence / Notion (via MCP)

/connect docs <space/page>
  • Read existing documentation, ADRs, decision records
  • Evidence tier: documented

Process

  1. Parse the argument to determine connector type and target.

  2. Attempt to access the source: Use available MCP tools, file system access, or web fetch as appropriate. If the source isn't accessible, tell the user what's needed (MCP server config, file path, etc.)

  3. Extract initial claims: Pull relevant information and create claims:

{
  "id": "r0XX",
  "type": "factual|constraint",
  "topic": "<relevant topic>",
  "content": "<extracted finding>",
  "source": {
    "origin": "connector",
    "artifact": null,
    "connector": {
      "type": "<github|atlas|jira|monitoring|docs>",
      "target": "<org/repo or project-key or path>",
      "ref": "<specific file/ticket/page if applicable>",
      "fetched": "<ISO timestamp>"
    }
  },
  "evidence": "documented",
  "status": "active",
  "phase_added": "research",
  "timestamp": "<ISO timestamp>",
  "conflicts_with": [],
  "resolved_by": null,
  "tags": ["connector", "<type>"]
}

Read the full file on GitHub · 116 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. 2d ago First seen · 116 lines · 0 tokens per session scan A e703e212d01e

Subscribe to this mod's changes

connect is a command published in the GitHub repository grainulation/wheat (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 713 tokens. 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 2026-08-30.