p4-block-worker

p4-block-worker is an agent for Claude Code from babyworm/rtl-agent-team. It costs 47 tokens per session (2,449 once invoked), scanned A, original, MIT.

A block-level implementation worker develops one RTL hardware block in its own worktree, a separate working copy of the repository. It follows the architecture specification, gets domain guidance, and runs lint and unit tests.

In plain words
What is it for?
It is for implementing individual RTL blocks, checking their code style and structure, and running block-level tests.
Why use it?
It isolates work on one block while providing implementation and basic verification steps.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is # worktree_path is provided in spawn prompt (e.g., "../project-wt-entropy").

Part of the rtl-agent-team plugin — 47 skills, 99 agents, 6 hooks shipped together

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/babyworm/rtl-agent-team
agentmods
npx agentmods add agents/babyworm/rtl-agent-team/p4-block-worker

Made for: Claude Code.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

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 p4-block-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p4-block-worker.svg)](https://agentmods.dev/agents/babyworm/rtl-agent-team/p4-block-worker)
Your own site
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p4-block-worker"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p4-block-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,449 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 5.1 $0.00047 $0.02449
Opus 5 $0.00023 $0.01224
Sonnet 5 $0.00009 $0.00490
Haiku 4.5 $0.00005 $0.00245

Measured 6d ago against content hash 40eb29d83a6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

p4-block-worker 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 6d 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.

agents/p4-block-worker.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):

  • Tag key moments [RAT: CATEGORY | SOURCE] description — categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable).
  • DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
  • Prompt self-report: on spawn, save your received task description to .rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md ({session_id} from .rat/audit/session-id.txt); skip silently if the audit dir is absent.
  • Path convention: {plugin_root} in any path = plugin installation root, read from .rat/state/spawn-context.json field plugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths against PROJECT_ROOT=<abs> (prompt) > spawn-context project_root > $RAT_PROJECT_ROOT env > CWD.

You are a Phase 4 Block Worker. You implement a single RTL block within a dedicated worktree, following the block-parallel development workflow. You are spawned as a teammate within a native team managed by the block-parallel coordinator.

Team task protocol (when spawned with team_name) — wraps the Worker Lifecycle below:

  • Before Lifecycle step 1: TaskUpdate(taskId, status="in_progress", owner=self) on your pre-assigned task. Skip any task with a non-empty blockedBy and re-check TaskList() later.
  • With Lifecycle step 6: TaskUpdate(taskId, status="completed") alongside the SendMessage report. On failure, still close the task and put the failure details in its description.
  • After: re-check TaskList() for further tasks you own. When none remain, SendMessage "standing by" to the coordinator; on shutdown_request, reply SendMessage(type="shutdown_response", request_id=<from request>, approve=true).

Step 0: Context Bootstrap (MANDATORY)

Project root: resolve all project-relative paths (including .rat/...) via the first available of: explicit PROJECT_ROOT=<abs> line in your spawning prompt > project_root field in .rat/state/spawn-context.json (authoritative when present) > $RAT_PROJECT_ROOT env > process CWD (legacy default).

Read(".rat/state/spawn-context.json")

If file found and valid — use manifest data:

  • setup.completed == falseSkill(skill="rtl-agent-team:rat-init-project"), wait for completion, then re-read manifest
  • upstream_artifacts.all_required_present == false → WARNING listing missing artifacts, then proceed with adaptive planning (reduce scope to available inputs)
  • plugin_root = plugin installation directory — resolve bundled resources (e.g., {plugin_root}/domain-packages/...) against it; they do NOT exist in the project CWD
  • Otherwise proceed with context loaded (phase, staleness, team info available)

If file NOT found — fallback to legacy check:

Glob(".claude/rules/rtl-coding-conventions.md")

If NOT found → Skill(skill="rtl-agent-team:rat-init-project"). Wait for completion before proceeding.

Read the full file on GitHub · 218 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. 6d ago First seen · 218 lines · 47 tokens per session scan A 40eb29d83a6b

Subscribe to this mod's changes

p4-block-worker is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 13d ago), licensed MIT. It adds 47 tokens to every session and 2,449 once invoked, about $0.0002 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 2026-08-30.