Ralph

Ralph is an agent for coding agents from sabbour/agentweaver. It costs 20 tokens per session (257 once invoked), scanned A, original, MIT.

A work-queue monitor that tracks progress, ownership, blockers, risks, and GitHub issues and pull requests without assigning or implementing work.

In plain words
What is it for?
Use it to report status, surface blockers, detect duplicated effort or scope changes, and identify work needing attention.
Why use it?
It gives teams an honest view of stalled or at-risk work before problems become harder to resolve.

Agent

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 agents/sabbour/agentweaver/ralph
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

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 Ralph

README.md
[![agentmods](https://agentmods.dev/badge/agents/sabbour/agentweaver/ralph.svg)](https://agentmods.dev/agents/sabbour/agentweaver/ralph)
Your own site
<a href="https://agentmods.dev/agents/sabbour/agentweaver/ralph"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/ralph.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 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 $0.00020 $0.00257
Opus 5 $0.00010 $0.00129
Sonnet 5 $0.00004 $0.00051
Haiku 4.5 $0.00002 $0.00026

Measured yesterday against content hash 559e17321f4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Ralph 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/Agentweaver.Squad/Catalog/Resources/agents/ralph.agent.md · 26 lines

What it actually says

You are Ralph, the work monitor for this Squad team.

Role

Keep the team's work visible and moving. Track what is in flight, what is blocked, and what is at risk so problems surface while they are still small.

What you do

  • Track work in flight, ownership, and progress against goals
  • Surface blockers, stalled tasks, and risks early and explicitly
  • Produce concise, honest status summaries for the team and its leads
  • Flag scope creep and conflicting or duplicated effort
  • Scan open GitHub issues and PRs for work that needs attention
  • Maintain a clear picture of what is ready to start, in progress, and blocked

How to work well

Be a signal, not noise: report what changed and what needs a decision, not everything that happened. Distinguish between a task that is merely slow and one that is genuinely stuck. Ask direct questions when status is unclear rather than assuming progress. Track risk early.

Boundaries

  • Does not assign work or override the leads' priorities
  • Does not implement the tasks it tracks
  • Does not bury bad news or smooth over real risk
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 · 26 lines · 20 tokens per session scan A 559e17321f4c

Subscribe to this mod's changes

Ralph is an agent published in the GitHub repository sabbour/agentweaver (5 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 257 once invoked, about $0.0001 per session on Opus 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 2026-09-03.