A command that imports information from outside sources into a Wheat research sprint. It supports DeepWiki, Confluence, Silo, GitHub, and web pages, where available.

Use it to pull architecture details from a GitHub repository, pages from Confluence, knowledge packs, GitHub discussions, or claims from a web URL.

It saves you from manually copying research into the sprint and turns source material into claims that can be tracked with the existing work.

pull — Command by grainulation

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/pull

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 1,183 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01183
Opus 5	$0.00000	$0.00592
Sonnet 5	$0.00000	$0.00237
Haiku 4.5	$0.00000	$0.00118

Measured yesterday against content hash 9ecc6df8ca6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pull 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.

templates/commands/pull.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pull — Backfill claims from external sources

You are pulling knowledge from external sources into the current Wheat sprint. Read CLAUDE.md for sprint context and claims.json for existing claims.

Process

Identify the source: The user's argument tells you where to pull from. Supported sources:
- DeepWiki (deepwiki <github-org/repo>): Pull architecture docs and dependency analysis from deepwiki.com
- Confluence (confluence <space-key> or confluence <page-url>): Pull content from Confluence pages via Atlassian MCP
- Silo (silo <pack-name>): Pull a knowledge pack via the silo MCP server
- GitHub (github <org/repo>): Pull README, issues, discussions via GitHub MCP
- URL (url <url>): Fetch and extract claims from any web page
- No argument: scan CLAUDE.md connectors and pull from all configured sources
Fetch content: Use the appropriate MCP server or web fetch:
- DeepWiki: Fetch https://deepwiki.com/<org>/<repo> — extract architecture overview, component descriptions, dependency graph, and key design decisions. DeepWiki auto-generates structured wiki docs from public GitHub repos. If the silo MCP is available, check mcp__silo__silo_search for cached DeepWiki content first.
- Confluence: Use mcp__atlassian__confluence_search or mcp__atlassian__confluence_get_page to fetch page content
- Silo: Use mcp__silo__silo_pull to retrieve the knowledge pack
- GitHub: Use mcp__github__search_repositories, mcp__github__get_file_contents, mcp__github__list_issues
- URL: Use web fetch to retrieve content
Extract claims from content: Parse the fetched content into typed claims:
- Architecture descriptions → factual claims about system structure
- Version numbers, metrics, stats → factual claims with evidence tier documented (for official sources) or web (for community content)
- Known issues, limitations → risk claims
- Best practices, recommendations → recommendation claims
- Requirements, constraints mentioned → constraint claims
- Estimates, projections → estimate claims

Read the full file on GitHub · 104 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.

yesterday First seen · 104 lines · 0 tokens per session scan A 9ecc6df8ca6c

Subscribe to this mod's changes

pull 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 1,183 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.

Planning Project management Research ai-agent claude-code cli developer-tools mcp mcp-server

pull

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/pull — Backfill claims from external sources

Process

What this file has done since we first saw it

Other commands, from other repositories

advisor

guide

pm-review

new

card

linear-bulk