Character Counter

text.count_characters

ProductionBounded custom (Class B)Deterministicstrictinstantv2.0.0

File inputNo network

Overview

You pass text (or a file_ref); we count characters under an explicit policy — Unicode code points or UTF-16 code units — with optional normalization and full metadata in the response. Do not use this for visible/grapheme counts or byte sizing.

LLMs miscalculate string length with Unicode — we give you exact counts under an explicit, documented policy.

Reliability

STRICT and deterministic — same input, policy, and normalization always yield the same count. Input validation (not retryable): neither text nor file_ref; both provided; text too long; invalid policy or normalization.

Context footprint

Eliminates ambiguity about what 'character' means — the policy is explicit. Accepts inline text up to 1,000,000 chars or file input via file_ref (up to 2 MB). Upload files via POST /v1/files/upload before passing file_ref. A successful call costs 1 execution credit.

When to use it

When exact character count matters and the counting unit must be documented.

When visible character count matters (use text.count_graphemes) or byte size (use text.count_bytes).

Scope

Note

Counts characters in text using an explicit policy (Unicode code points or UTF-16 code units) with optional normalization.

Non-goals

Does not count words/tokens/bytes
Does not perform text transformation

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

analysistext-processing

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call1 credit

File handling

Accepts file_refProduces file_refMax input976.6 KBMax file size1.9 MB

File limits

Constraints this skill applies to your input and generated files. The “Limited by” column shows the static source of each cap; none of these can be raised by upgrading your plan.

Limit	Value	Limited by
Maximum size per input file	1.9 MiB	Skill maximum

How we handle your data

Sensitive input, safe output

What this means

This skill may receive sensitive content, but it does not target sensitive data and returns only a structured non-sensitive result.

Squillify guarantees

Runs inside Squillify
This skill runs inside Squillify.
Payloads are not sent to an external service by this skill.
Squillify does not permanently store submitted payloads.
Telemetry records metadata only, not submitted content.
Submitted payloads are not used for training.
Submitted payloads are not reviewed by humans.
This skill does not target sensitive data.
The response does not contain submitted content.

Your responsibility

Squillify does not determine whether submitted content is sensitive. Your application is responsible for deciding what data it is allowed to submit. Your application is responsible for securing the response.

Read the Microskill Data Handling Policy

Input schema

Field	Type	Required	Description
text	string	No	Bounded inline text source. Required unless file_ref is provided.
file_ref	string	No	Tenant-scoped opaque text-file reference. Omit it to use the required inline text; never send both.
policy	string	No	Character unit; omit it for code_point.
normalization	string	No	Unicode normalization; omit it for none.

Output schema

Field	Type	Required	Description
skill	string	Yes	Producing skill key.
count	integer	Yes	Counted characters. This non-negative total is bounded by the documented input limit.
unit	string	Yes	Counted character unit.
policy	string	Yes	Applied character policy.
normalized	boolean	Yes	Whether normalization was applied.
normalization	string	Yes	Applied normalization form.
warnings	array	Yes	Bounded warning array containing from 0 through 4 items, where each item is one non-fatal advisory string.

API contract

POST /v1/execute

curl

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"text.count_characters","input":{"text":"Hello World","policy":"code_point"}}'

Integrations

TypeScript SDK

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("text.count_characters", {"text":"Hello"});

Errors

Code	HTTP	Retryable	Description
VALIDATION_ERROR	400	No	The request payload failed schema validation.
UNAUTHORIZED	401	No	Missing or invalid API key.
SKILL_NOT_ACCESSIBLE	403	No	The API key is not granted access to this skill.
SKILL_NOT_AVAILABLE_FOR_PLAN	403	No	This skill is not included in your current plan.
PLAN_ELIGIBILITY_UNAVAILABLE	503	Yes	Plan eligibility could not be decided. Retry after backoff.
SKILL_NOT_FOUND	404	No	The requested skill or version does not exist.
TENANT_RATE_LIMITED	429	Yes	Request rate limit exceeded. Retry after backoff.
QUOTA_EXCEEDED	429	Yes	Plan quota exhausted. Retryable once the quota period resets.
EXECUTION_TIMEOUT	504	Yes	Execution exceeded the allowed time budget.

Other limits

Limit	Value
Recommended inline bytes	32 KiB

Limitations

Does not count words/tokens/bytes
Does not perform text transformation
Counting visible characters (use count_graphemes)
Counting words (use count_words)

How to call

POST /v1/execute (requires authentication)

Request bodyjson

{
  "skillKey": "text.count_characters",
  "input": {
    "text": "Hello"
  }
}

Examples

Basic count

Inputjson

{
  "text": "Hello"
}

Expected outputjson

{
  "policy": "code_point",
  "count": 5,
  "normalized": false,
  "skill": "text.count_characters",
  "unit": "unicode_code_point",
  "normalization": "none",
  "warnings": []
}

Emoji with policy