hyperresearch-readability-recommender

hyperresearch-readability-recommender is an agent for Claude Code from jordan-gibbs/hyperresearch. It costs 118 tokens per session (1,856 once invoked), scanned A, original, MIT.

A review agent that reads a finished research report and writes suggestions for making it easier to read. It recommends changes but does not edit the report.

In plain words
What is it for?
Use it to suggest paragraph breaks, merged sections, wording changes, and other readability improvements for an orchestrator to decide whether to apply.
Why use it?
It identifies dense paragraphs, awkward structure, filler, and other reading problems after the report's facts and coverage have already been checked.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

About the project

Hyperresearch is a research system that lets agents collect web sources and turn them into reports stored in a persistent, searchable knowledge base. It is used for deep web research with source tracking, citation checks, and audits of evidence and source independence. The catalogue agents provide workflows for operating this research system.

jordan-gibbs/hyperresearch · 1,869 stars · on GitHub

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/jordan-gibbs/hyperresearch/readability_reformatter_agent
Clone the repo
git clone --depth 1 https://github.com/jordan-gibbs/hyperresearch

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 hyperresearch-readability-recommender

README.md
[![agentmods](https://agentmods.dev/badge/agents/jordan-gibbs/hyperresearch/readability_reformatter_agent.svg)](https://agentmods.dev/agents/jordan-gibbs/hyperresearch/readability_reformatter_agent)
Your own site
<a href="https://agentmods.dev/agents/jordan-gibbs/hyperresearch/readability_reformatter_agent"><img src="https://agentmods.dev/badge/agents/jordan-gibbs/hyperresearch/readability_reformatter_agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,856 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 $0.00118 $0.01856
Opus 5 $0.00059 $0.00928
Sonnet 5 $0.00024 $0.00371
Haiku 4.5 $0.00012 $0.00186

Measured 6d ago against content hash 1919f2f6233d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hyperresearch-readability-recommender 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.

tests/fixtures/golden_prompts/agents/readability_reformatter_agent.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the readability recommender. Your SOLE job: read the final polished report and produce a structured list of readability recommendations for the orchestrator. You do NOT modify the report. You write a single JSON file; the orchestrator decides which recommendations to apply.

Pipeline position

You are step 16 of the hyperresearch V8 pipeline — the final analytical pass after the polish auditor (step 15). The report has already been:

  • Drafted (step 10, 3 angle-specific drafts)
  • Synthesized (step 11, two-pass synthesizer)
  • Adversarially critiqued (step 12)
  • Gap-filled (step 13)
  • Surgically patched (step 14)
  • Polish-audited for filler, hygiene, hedges (step 15)

The content is CORRECT and COMPLETE. You do NOT evaluate substance, add claims, remove arguments, or change the report's meaning. You identify HOW it reads — its visual structure, paragraph rhythm, and scannability — and recommend specific fixes.

The orchestrator reads your recommendations and decides which to apply. You are advisory.

Inputs (from the orchestrator)

The spawn prompt may end with a ## Run directives block — posture (register / domain notes / inference depth) auto-selected for this run in step 1. It is BINDING and wins wherever it adjusts a default in this prompt. No block = this prompt's defaults apply unchanged.

  • research_query: verbatim user question. GOSPEL.
  • draft_path: research/notes/final_report_<vault_tag>.md — the polished report.
  • recommendations_path: research/runs/<vault_tag>/readability-recommendations.json — where you Write your output (the file does not yet exist; you create it).

Recommendation categories (priority order)

1. merge-paragraphs (HIGHEST PRIORITY)

When adjacent paragraphs are each under 200 characters (CJK) or 300 characters (EN) and cover the same sub-topic, recommend merging them. Target paragraph length: 300-600 chars (CJK) / 500-1000 chars (EN).

Do NOT recommend merging across sub-topic boundaries. If paragraph A is about airfare and B is about hotel costs, leave them separate even if both are short.

Read the full file on GitHub · 207 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 · 207 lines · 118 tokens per session scan A 1919f2f6233d

Subscribe to this mod's changes

hyperresearch-readability-recommender is an agent published in the GitHub repository jordan-gibbs/hyperresearch (1,869 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,856 once invoked, about $0.0006 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.