token-estimator

token-estimator is a skill for Claude Code, Codex from HashLips/agent-skills. It costs 45 tokens per session (442 once invoked), scanned A, original, MIT.

A read-only skill that estimates the rough token size of Markdown and plain-text files. Tokens are the small pieces of text that AI systems process.

In plain words
What is it for?
Use it on one file or a folder to count characters and estimated tokens, with recursive totals for Markdown, text, and MDX files.
Why use it?
It provides consistent ballpark sizes for comparing documents or checking context usage without calling a model provider.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it on one file or a folder to count characters and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hashlips/agent-skills/token-estimator
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.

Any agent
npx skills add HashLips/agent-skills --skill token-estimator
Clone the repo
git clone --depth 1 https://github.com/HashLips/agent-skills

Made for: Claude Code, Codex.

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 token-estimator

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashlips/agent-skills/token-estimator.svg)](https://agentmods.dev/skills/hashlips/agent-skills/token-estimator)
Your own site
<a href="https://agentmods.dev/skills/hashlips/agent-skills/token-estimator"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/token-estimator.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00045 $0.00442
Opus 5 $0.00023 $0.00221
Sonnet 5 $0.00009 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 7d ago against content hash 064c5b3e8f8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

token-estimator 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/estimate_tokens.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/token-estimator/SKILL.md · 47 lines

What it actually says

Token Estimator

Disclaimer

Rough estimate only — not billing-grade. Same file on disk → same numbers every run. Real token counts depend on the model’s tokenizer; this skill uses a fixed heuristic (⌈chars ÷ 4⌉, English-oriented). Use for ballparks and comparisons, not hard limits.

What It Does

  • One file — report chars and est_tokens.
  • Folder — recursively count every .md, .txt, .mdx file; report per file plus total.
  • Read-only — never modify targets.

Workflow

  1. Confirm path (file or directory).
  2. Run scripts/estimate_tokens.py when possible; otherwise apply references/estimation-method.md.
  3. Reply with totals first, then per-file lines only if there is more than one file.

Rules

  1. Deterministic — fixed extensions, alphabetical order, integer formula (chars + 3) // 4.
  2. Recursive — walk subdirectories; skip .git, node_modules, __pycache__, .venv, binaries.
  3. Label — always say est_tokens or ~tokens, never imply exact provider counts.

Output (Minimal)

total: 5376 chars, ~1344 est_tokens
references/foo.md: 1112 chars, ~278 est_tokens

One path in the reply is enough unless the user asked for several.

Reference

When To Use

  • Ballpark size of a doc, skill folder, or prompt file.
  • Same metric applied twice should match (sanity check, before/after edits).
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 47 lines · 45 tokens per session scan A 064c5b3e8f8e

Subscribe to this mod's changes

token-estimator is a skill published in the GitHub repository HashLips/agent-skills (24 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 442 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens