tokenizer-protocol

tokenizer-protocol is a skill for Claude Code from gustavo-meilus/superpipelines. It costs 43 tokens per session (1,469 once invoked), scanned A, original, MIT.

An internal protocol for the tokenizer step used by the parity-test-g pipeline. It reads a Markdown file, removes formatting that should not count as words, and writes frequency counts and pipeline status.

In plain words
What is it for?
Use it as part of the parity-test-g workflow to process Markdown files, create frequency-counts.json, and report missing, empty, or successfully processed inputs.
Why use it?
It defines consistent rules for counting words, such as ignoring headings, code, URLs, and HTML tags while keeping link text. It also handles missing or empty input files.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: built for cline.

Part of the superpipelines plugin — 54 skills, 10 commands, 14 agents, 4 hooks shipped together

Good fit Use it as part of the parity-test-g workflow to process Markdown files, create frequency-counts.json, and report missing, empty, or successfully processed inputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gustavo-meilus/superpipelines/tokenizer-protocol
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 gustavo-meilus/superpipelines --skill tokenizer-protocol
Clone the repo
git clone --depth 1 https://github.com/gustavo-meilus/superpipelines

Made for: Claude Code.

Or install superpipelines, the plugin that ships this one along with the rest of its 54 skills, 10 commands, 14 agents, 4 hooks.

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 tokenizer-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/tokenizer-protocol.svg)](https://agentmods.dev/skills/gustavo-meilus/superpipelines/tokenizer-protocol)
Your own site
<a href="https://agentmods.dev/skills/gustavo-meilus/superpipelines/tokenizer-protocol"><img src="https://agentmods.dev/badge/skills/gustavo-meilus/superpipelines/tokenizer-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,469 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 $0.00043 $0.01469
Opus 5 $0.00022 $0.00734
Sonnet 5 $0.00009 $0.00294
Haiku 4.5 $0.00004 $0.00147

Measured 7d ago against content hash 00ba12375a29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tokenizer-protocol 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.

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.

.superpipelines/skills/superpipelines/parity-test-g/tokenizer-protocol/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tokenizer — Operational Protocol

Protocol

1. DISCOVER

  1. Read inputs from the orchestrator execution context:
    • input_path: path to the input markdown file to read.
    • counts_output_path: path where frequency-counts.json must be written.
    • state_path: path to pipeline-state.json for status updates.
    • run_id: current run identifier.
    • root: resolved scope root.
  2. Verify input_path exists and is a readable file. If not: update pipeline-state.json phases[0].status = "blocked"; emit NEEDS_CONTEXT with message: "Input markdown file not found at {input_path}. Provide a valid path and re-run."
  3. Read the file content. If the file is empty: write a zero-count frequency-counts.json and emit DONE_WITH_CONCERNS with message: "Input file at {input_path} is empty. Frequency counts file written with zero entries."

2. PROCESS

Step 2.1 — Strip markdown syntax:

Remove the following before tokenizing (do not count these as word content):

  • ATX headings (#, ##, etc.)
  • Emphasis markers (*, **, _, __)
  • Inline code and code fences (content inside backticks)
  • URLs and link syntax ([text](url) → keep text, discard url)
  • HTML tags if present
  • Punctuation attached to word boundaries (,, ., :, ;, !, ?, ", ', (, ), [, ], {, })

Step 2.2 — Tokenize:

Split the cleaned text on whitespace. Convert every token to lowercase. Discard any token that is empty or contains only non-alphabetic characters (e.g., ---, 123, 42px).

Read the full file on GitHub · 115 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. 7d ago First seen · 115 lines · 43 tokens per session scan A 00ba12375a29

Subscribe to this mod's changes

tokenizer-protocol is a skill published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,469 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 2026-08-31.