tokenize-then-parse

tokenize-then-parse is a skill for Claude Code from jimmc414/claude-code-plugin-marketplace. It costs 28 tokens per session (639 once invoked), scanned A, original, MIT.

A two-stage approach for processing structured text: first split it into tokens, then turn those tokens into a nested structure.

In plain words
What is it for?
Use it for interpreters, compiler front ends, parenthesized expressions, and text with clear token boundaries.
Why use it?
Separating tokenizing from parsing makes interpreters and similar text processors easier to organize and debug. It is unnecessary for simple fixed formats.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the norvig-patterns plugin — 54 skills shipped together

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 skills/jimmc414/claude-code-plugin-marketplace/tokenize-then-parse
Any agent
npx skills add jimmc414/claude-code-plugin-marketplace --skill tokenize-then-parse
Clone the repo
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplace

Made for: Claude Code.

Or install norvig-patterns, the plugin that ships this one along with the rest of its 54 skills.

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 tokenize-then-parse

README.md
[![agentmods](https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/tokenize-then-parse.svg)](https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/tokenize-then-parse)
Your own site
<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/tokenize-then-parse"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/tokenize-then-parse.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 639 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 5.1 $0.00028 $0.00639
Opus 5 $0.00014 $0.00319
Sonnet 5 $0.00006 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured 2d ago against content hash 2f8a12c5b2c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tokenize-then-parse 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/norvig-patterns/skills/tokenize-then-parse/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tokenize-then-parse

When to Use

  • Building interpreters or compilers
  • Processing parenthesized expressions
  • Structured text with clear token boundaries
  • Multi-stage processing pipeline

When NOT to Use

  • Simple fixed format (just split)
  • Very complex grammar (use parser generator)
  • No clear token boundaries

The Pattern

Tokenize text into a stream of tokens, then parse tokens into a structure.

def tokenize(s):
    """Convert string to list of tokens."""
    return s.replace('(', ' ( ').replace(')', ' ) ').split()

def parse(tokens):
    """Parse tokens into nested structure."""
    token = tokens.pop(0)
    if token == '(':
        result = []
        while tokens[0] != ')':
            result.append(parse(tokens))
        tokens.pop(0)  # Remove ')'
        return result
    else:
        return atom(token)

def atom(token):
    """Convert token to appropriate type."""
    try:
        return int(token)
    except ValueError:
        try:
            return float(token)
        except ValueError:
            return token

Example (from pytudes lis.py)

def tokenize(s):
    """Convert a string into a list of tokens."""
    return s.replace('(', ' ( ').replace(')', ' ) ').split()

def read_from_tokens(tokens):
    """Read an expression from a sequence of tokens."""
    if len(tokens) == 0:
        raise SyntaxError('unexpected EOF')

    token = tokens.pop(0)

    if token == '(':
        L = []
        while tokens[0] != ')':
            L.append(read_from_tokens(tokens))
        tokens.pop(0)  # Remove ')'
        return L
    elif token == ')':
        raise SyntaxError('unexpected )')
    else:
        return atom(token)

def atom(token):
    """Numbers become numbers; every other token is a symbol."""
    try:
        return int(token)
    except ValueError:
        try:
            return float(token)
        except ValueError:
            return Symbol(token)

def parse(program):
    """Read a Scheme expression from a string."""
    return read_from_tokens(tokenize(program))

# Usage
parse("(+ 2 (* 3 4))")
# Returns: ['+', 2, ['*', 3, 4]]

parse("(define square (lambda (x) (* x x)))")
# Returns: ['define', 'square', ['lambda', ['x'], ['*', 'x', 'x']]]

Read the full file on GitHub · 104 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 · 104 lines · 28 tokens per session scan A 2f8a12c5b2c8

Subscribe to this mod's changes

tokenize-then-parse is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 639 once invoked, about $0.0001 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 2026-09-04.

Related

Other skills, from other repositories

ai-ml-development

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

travisjneuman/.claude · 43 tokens

codexer

Python research assistant with Context7 MCP. Use for Python library research, evaluating packages, enforcing strict Python coding standards, or fetching up-to-date library docs via Context7.

PracticalSwan/agent-skills · 38 tokens

fastapi

Skill "fastapi" from ashish7802/awesome-api-skills, covering fastapi skill, ecosystem graph, quick start, production patterns and dependency injection.

ashish7802/awesome-api-skills · 0 tokens

python-packaging

Configure Python package metadata, setup.py, and pyproject.toml for distribution using UV or setuptools. Use when setting up Python packages, configuring build systems, or preparing projects for PyPI publication.

armanzeroeight/fastagent-plugins · 43 tokens

analyzing-windows-prefetch-with-python

Parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns.

pinkpixel-dev/skills-collection-1 · 43 tokens

clean-code

Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.

Sagargupta16/claude-skills · 66 tokens