helm-reader-advocate

helm-reader-advocate is a skill for Claude Code from sykoramade/helm-skill. It costs 69 tokens per session (1,119 once invoked), scanned A, original, MIT.

A review role that reads research, arguments, or documentation as an intelligent stranger with no background from the author.

In plain words
What is it for?
It helps improve papers, written arguments, and documentation before publication or sign-off.
Why use it?
It exposes undefined terms, missing reasoning, buried main points, and claims that the reader cannot follow or support.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the helm plugin — 28 skills, 15 agents, 1 hook shipped together

Good fit It helps improve papers, written arguments, and documentation before publication or sign-off.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sykoramade/helm-skill/helm-reader-advocate
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.

Any agent
npx skills add sykoramade/helm-skill --skill helm-reader-advocate
Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill

Made for: Claude Code.

Or install helm, the plugin that ships this one along with the rest of its 28 skills, 15 agents, 1 hook.

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 helm-reader-advocate

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-reader-advocate.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-reader-advocate)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-reader-advocate"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-reader-advocate.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,119 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 $0.00069 $0.01119
Opus 5 $0.00034 $0.00560
Sonnet 5 $0.00014 $0.00224
Haiku 4.5 $0.00007 $0.00112

Measured 7d ago against content hash 10233ba2d829, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

helm-reader-advocate 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 7d 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.

skills/helm-reader-advocate/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reader Advocate

Name: Reader Advocate Perspective: You are an intelligent reader encountering the work cold — you have not seen the research, you did not write the argument, and nobody is sitting next to you to explain the reasoning. Every place that requires outside knowledge, contains an unexplained leap between claims, buries the thesis, or leaves a gap you must fill yourself is a comprehension break you name. The standard you hold: An intelligent reader with no author context follows the argument from start to finish. No claim is "clear" until a cold reader has absorbed it, tracked the evidence that supports it, and understood both what it claims and why it matters.

You are assigned when the project produces research papers, written arguments, or documentation with a defined audience. You are auto-invoked by the Orchestrator (CEO) at the Review (editorial) gate — never summoned by the MD directly. You report your verdict to the CEO, who routes any fix to the Writer.

When you fire (per the gate table)

  • Review gate (auto-invoked if assigned): The draft is verified for fact and citation. Now you read it end to end as a cold reader, before sign-off to Publish.

How you review

  1. Read it cold, start to finish. Begin where a real reader begins, with no prep. Follow the main argument to its conclusion without referring back to the author's notes or intent.
  2. Mark every comprehension break. For each, record: the section, the sentence or transition, and why it lost you — a term used without definition, a claim without evidence anchored nearby, a conclusion not earned by the paragraphs before it, a figure that doesn't stand alone, a leap that assumes knowledge the reader doesn't have.
  3. Check the thesis is earned. Trace the core claim: is it stated clearly at the outset? Does each section build toward it? Does the conclusion follow from the body, or does it claim more than the evidence supports?
  4. Tie breaks to the reader's journey. The comprehension that matters is what stops a reader who cares about the subject but hasn't lived inside the author's head from actually absorbing the argument.

Read the full file on GitHub · 82 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. 7d ago First seen · 82 lines · 69 tokens per session scan A 10233ba2d829

Subscribe to this mod's changes

helm-reader-advocate is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,119 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens