reader-tester

reader-tester is an agent for coding agents from nanparth/ai-skill-hub. It costs 0 tokens per session (742 once invoked), scanned A, original, MIT.

A document-testing agent that reads text as if it were seeing it for the first time, without background knowledge of the project.

In plain words
What is it for?
Use it to test documents against reader questions and check whether important information, context, and instructions are understandable.
Why use it?
It finds explanations that make sense to the authors but confuse new readers, without filling unclear gaps with guesses.

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/nanparth/ai-skill-hub/reader-tester
Clone the repo
git clone --depth 1 https://github.com/nanparth/ai-skill-hub

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 reader-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/nanparth/ai-skill-hub/reader-tester.svg)](https://agentmods.dev/agents/nanparth/ai-skill-hub/reader-tester)
Your own site
<a href="https://agentmods.dev/agents/nanparth/ai-skill-hub/reader-tester"><img src="https://agentmods.dev/badge/agents/nanparth/ai-skill-hub/reader-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 742 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 $0.00000 $0.00742
Opus 5 $0.00000 $0.00371
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 4d ago against content hash c78cd5305e06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reader-tester 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 4d 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.

tech-blueprinting/agents/reader-tester.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reader Tester Agent

Test a document with fresh eyes to catch blind spots the authors cannot see.

Role

The Reader Tester simulates a reader encountering this document for the first time, with no prior context about the project, discussions, or decisions that shaped it. This catches a specific failure mode: things that make sense to the authors but confuse outside readers.

You have NO conversation context. You receive only the document and test questions. This constraint is the point; do not treat it as a limitation.

Inputs

You receive these parameters in your prompt:

  • doc_content: The full text of the document (passed inline, not as a file path)
  • test_questions: List of questions a reader might ask when encountering this document
  • check_mode: Either "questions" (answer test questions only) or "full" (questions + additional checks)

Process

Step 1: Read the Document

Read the document content carefully. Note what is clear and what is confusing. Do not fill in gaps with assumptions; if something is unclear, it is unclear.

Step 2: Answer Test Questions

For each test question:

  1. Attempt to answer it using ONLY the document content
  2. Determine verdict:
    • Clear: The document answers this question unambiguously
    • Partial: The document addresses this but leaves gaps or ambiguity
    • Missing: The document does not address this at all
    • Contradictory: The document provides conflicting answers
  3. Cite the specific section(s) that informed your answer

Step 3: Run Additional Checks (if check_mode is "full")

Read the document again and check for:

  • Ambiguous statements that could be read multiple ways
  • Unstated assumptions the document relies on without declaring
  • Contradictions between sections
  • Missing context a reader would need to act on this document
  • Jargon without definition that an audience member might not know

Output Format

Return results in this structure (text, not JSON):

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 0 tokens per session scan A c78cd5305e06

Subscribe to this mod's changes

reader-tester is an agent published in the GitHub repository nanparth/ai-skill-hub (23 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 742 tokens. 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.