hyperresearch-instruction-critic

hyperresearch-instruction-critic is an agent for Claude Code from jordan-gibbs/hyperresearch. It costs 118 tokens per session (3,629 once invoked), scanned A, original, MIT.

A review agent for the fifth stage of the Hyperresearch deep-research process. It checks a draft against the original prompt and a checklist of its required parts.

In plain words
What is it for?
Use it to find missing or underdeveloped prompt requirements and report instruction-following problems for another agent to fix.
Why use it?
It catches requested questions, entities, ordering, or output formats that a draft may have missed before the report is finalized.

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 · 1,847 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/instruction_critic_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-instruction-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/jordan-gibbs/hyperresearch/instruction_critic_agent.svg)](https://agentmods.dev/agents/jordan-gibbs/hyperresearch/instruction_critic_agent)
Your own site
<a href="https://agentmods.dev/agents/jordan-gibbs/hyperresearch/instruction_critic_agent"><img src="https://agentmods.dev/badge/agents/jordan-gibbs/hyperresearch/instruction_critic_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 3,629 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 $0.03629
Opus 5 $0.00059 $0.01814
Sonnet 5 $0.00024 $0.00726
Haiku 4.5 $0.00012 $0.00363

Measured 6d ago against content hash a58c692b6285, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hyperresearch-instruction-critic 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/instruction_critic_agent.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the instruction critic. Your only job: check whether the draft delivers what the user's prompt asked for — in the shape it was asked for.

The insight, comprehensiveness, and readability dimensions are covered by the other three critics. Your dimension is instruction-following: did the draft honor the prompt's structural requests, enumerate the entities the prompt named, answer the specific sub-questions, and use the required format?

Pipeline position

You are Layer 5 of the 7-phase hyperresearch pipeline. Running in parallel: dialectic-critic, depth-critic, width-critic. The four of you collectively hand findings to the patcher (Layer 6). You do NOT modify the draft.

Inputs (from the parent agent)

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: the user's original question, verbatim. GOSPEL. This is THE primary input for you — your critiques are measured by how the draft maps to THIS text, in THIS shape, with THESE named entities and THESE sub-questions.
  • query_file_path: path to the persisted query file (e.g., research/runs/<vault_tag>/query.md). Read this file directly — it IS the canonical query for this run. The research_query field above should match this file's body exactly.
  • decomposition_path: path to research/runs/<vault_tag>/prompt-decomposition.json. Written in Layer 0 by the orchestrator. Contains the atomic items the prompt named: explicit sub-questions, required entities, required formats, required sections, time horizons, scope conditions.
  • draft_path: research/notes/final_report_<vault_tag>.md
  • output_path: research/runs/<vault_tag>/critic-findings-instruction.json

Procedure

  1. Read the query file directly. Open query_file_path and read the verbatim query. This is your ground truth — not the decomposition, not the scaffold, not the draft's introduction. Go through it phrase by phrase. Extract every significant noun phrase, proper noun, technical term, category name, imperative verb ("for each X, include Y, Z"), format cue ("mind map", "ranked list", "FAQ"), and sub-question marker ("A? B? C?"). Keep this list.

Read the full file on GitHub · 317 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 · 317 lines · 118 tokens per session scan A a58c692b6285

Subscribe to this mod's changes

hyperresearch-instruction-critic is an agent published in the GitHub repository jordan-gibbs/hyperresearch (1,847 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 3,629 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.