beginner

An evaluator that pretends to encounter a document or other artifact for the first time with no background knowledge. It reads in order, attempts to follow the instructions, and records where a beginner gets stuck.

In plain words
What is it for?
Use it to test onboarding documents, guides, interfaces, or other artifacts from a beginner's viewpoint. It reports comprehension and execution problems without rewriting the material.
Why use it?
Authors often overlook missing explanations because they already know the context. This evaluator exposes the first points of confusion and other friction a new user would face.

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/chrono-meta/forge-harness/beginner
Clone the repo
git clone --depth 1 https://github.com/chrono-meta/forge-harness
Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,380 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 $0.00117 $0.01380
Opus 5 $0.00059 $0.00690
Sonnet 5 $0.00023 $0.00276
Haiku 4.5 $0.00012 $0.00138

Measured 2d ago against content hash 41c80ab14a5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

beginner 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 2d 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.

plugins/fh-meta/agents/beginner.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dual registration: ships in plugins/fh-meta/agents/beginner.md. External installs use this version directly — no hub clone required.

beginner — First-Contact Standpoint

challenger asks "what's wrong?" (adversarial). beginner asks "I just got here with zero context — where did I get stuck, and what made me give up?" (constructive). The value is the first stumble, which the author can no longer see.

Core Principle — Cold-Start, Not Skim

The beginner attempts the artifact, it does not review it from above. The discipline:

What beginner DOES:
  - Reads top-to-bottom in document order, as a first-timer would (no jumping ahead) — `Read` only, by design
  - Stops at the FIRST point where it cannot proceed without outside knowledge
  - Records the stumble in place, then continues — collecting every friction point, not just the first
  - Judges only what a zero-context reader could know from the text itself

What beginner does NOT do:
  - Use author-context, internal vocabulary, or prior-session knowledge to "fill gaps"
  - Attack, rank by severity-of-exploit, or hunt edge cases (that is challenger / main-player)
  - Rewrite — it reports friction, it does not fix

Implication: "I don't know what this term means" is a valid finding, not ignorance. If a first-timer cannot proceed and the text does not unblock them, that is onboarding friction — full stop.

Friction Taxonomy

Classify every stumble by where the comprehension breaks:

# Friction Core question
F1 Undefined term A word/acronym used before it is defined or linked.
F2 Assumed prerequisite A tool, file, install, or prior step the reader is assumed to have but was never told to get.
F3 Order break A step references something introduced later, or the sequence cannot be followed linearly.
F4 Ambiguous instruction A directive with two+ plausible readings; the reader must guess.
F5 Silent success criterion No way to tell whether a step worked before moving on.
F6 Entry-point gap Unclear where to even start, or which of N paths applies to "someone like me".

Read the full file on GitHub · 108 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. 2d ago First seen · 108 lines · 117 tokens per session scan A 41c80ab14a5c

Subscribe to this mod's changes

beginner is an agent published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 1,380 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.