normalize_input

Automatic input cleanup for agents that removes surrounding whitespace and turns runs of spaces, tabs, and line breaks into one space before each call.

In plain words
What is it for?
Use it when agents should treat extra spacing as irrelevant, such as processing pasted text or user messages. It can be disabled for agents that must preserve the original formatting.
Why use it?
It prevents accidental formatting differences and removes unnecessary input characters. It can also reduce the amount of text sent to the model.

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/the-teacher/active_harness/normalize_input
Clone the repo
git clone --depth 1 https://github.com/the-teacher/active_harness
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 263 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 $0.00263
Opus 5 $0.00000 $0.00131
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00026

Measured 2d ago against content hash ff2b3eec1743, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

normalize_input 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.

docs/agents/normalize_input.md · 39 lines

What it actually says

Input Normalization

Before every call, ActiveHarness automatically normalizes @input by stripping leading and trailing whitespace and collapsing internal whitespace sequences to a single space.

"  Hello   world\n" → "Hello world"

This is enabled by default to trim unnecessary tokens and avoid subtle formatting issues.

Disabling

To opt out for a specific agent:

class VerbatimAgent < ActiveHarness::Agent
  normalize_input false
end

How it works

Normalization runs in two places:

  1. initialize — applied immediately after @input is set, before the :setup hook fires.
  2. call(input) — applied when input is passed inline to call.

The equivalent transformation is:

@input = @input&.strip&.gsub(/\s+/, " ")

Notes

  • normalize_input false only affects the automatic normalization. You can still normalize manually inside a :setup hook or :before_call hook if custom logic is needed.
  • The option applies at the class level and is inherited by subclasses unless overridden.
  • nil input is left as nil (the safe-navigation operator &. protects against it).
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 · 39 lines · 0 tokens per session scan A ff2b3eec1743

Subscribe to this mod's changes

normalize_input is an agent published in the GitHub repository the-teacher/active_harness (89 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 263 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.