ras-commander: Command for Claude Code

.claude/commands/agent-crossrepo.md

agent-crossrepo is a command for Claude Code from gpt-cmdr/ras-commander. It costs 0 tokens per session (576 once invoked), scanned A, original, MIT.

A coordination workflow for sharing requests between the ras-commander and hms-commander code repositories. A repository is a project’s code and files managed separately from other projects.

In plain words
What is it for?
Use it to document research requests or immediate implementation requests in Markdown files, using the appropriate repository and request templates.
Why use it?
It prevents the two projects from becoming accidentally coupled in Python code and makes cross-project handoffs explicit. Human approval is required before work proceeds.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is gpt-cmdr/ras-commander's own configuration. It tells Claude Code how to work on ras-commander itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ras-commander configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/commands/agent-crossrepo.md
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

Made for: Claude Code.

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 agent-crossrepo

README.md
[![agentmods](https://agentmods.dev/badge/commands/gpt-cmdr/ras-commander/agent-crossrepo/github.svg)](https://agentmods.dev/commands/gpt-cmdr/ras-commander/agent-crossrepo)
Your own site
<a href="https://agentmods.dev/commands/gpt-cmdr/ras-commander/agent-crossrepo"><img src="https://agentmods.dev/badge/commands/gpt-cmdr/ras-commander/agent-crossrepo/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 agent-crossrepo

Your own site · 80×15
<a href="https://agentmods.dev/commands/gpt-cmdr/ras-commander/agent-crossrepo"><img src="https://agentmods.dev/badge/commands/gpt-cmdr/ras-commander/agent-crossrepo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 576 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 $0.00000 $0.00576
Opus 5 $0.00000 $0.00288
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00058

Measured 11d ago against content hash 35ca25f65304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-crossrepo 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 11d 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.

.claude/commands/agent-crossrepo.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are initiating a cross-repository coordination request between ras-commander and hms-commander.

Cross-Repo Coordination Protocol

Key Principles:

  1. Cross-repo awareness exists ONLY at the AI/documentation layer - NOT in Python code
  2. All handoffs require explicit HUMAN approval before proceeding
  3. Communication happens through markdown files in feature_dev_notes/cross-repo/ or agent_tasks/cross-repo/
  4. Python APIs remain completely independent

Your Task

  1. Identify the request type:

    • Research/Future Feature → Use feature_dev_notes/cross-repo/
    • Immediate Implementation → Use agent_tasks/cross-repo/
  2. Create the request file:

    • Use naming convention: {YYYY-MM-DD}_{source}_to_{target}_{topic}.md
    • Source is current repo (ras-commander)
    • Target is sibling repo (hms-commander at C:\GH\hms-commander)
  3. Use the appropriate template:

    • Research: feature_dev_notes/cross-repo/_TEMPLATE_research_request.md
    • Implementation: agent_tasks/cross-repo/_TEMPLATE_implementation_request.md
  4. Fill out the request completely including:

    • Clear summary of what is needed
    • Background and context
    • Relevant files in this repo
    • Expected output from sibling repo
    • Any constraints or requirements
  5. Stop and inform the user:

    • Explain what request was created
    • Tell them the file path
    • Instruct them to review, then open hms-commander and provide the request context
    • Remind them that YOU CANNOT directly communicate with the other repo's agent

Sibling Repository Info

Repository Path Purpose
ras-commander C:\GH\ras-commander HEC-RAS automation (current)
hms-commander C:\GH\hms-commander HEC-HMS automation (sibling)

Example Workflow

1. You create: agent_tasks/cross-repo/2024-12-13_ras_to_hms_dss-export.md
2. You stop and tell user: "Request created. Please review, then open hms-commander."
3. User reviews request
4. User opens hms-commander, provides context
5. hms-commander agent implements, writes response
6. User brings response back here
7. You integrate with user oversight

Read the full file on GitHub · 59 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. 11d ago First seen · 59 lines · 0 tokens per session scan A 35ca25f65304

Subscribe to this mod's changes

agent-crossrepo is a command published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 576 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.