add-language

add-language is a skill for Claude Code from madeinoz67/madeinoz-knowledge-system. It costs 87 tokens per session (3,632 once invoked), scanned A, original, MIT.

A step-by-step guide for adding support for a new programming language to Codanna, using a six-part parser architecture based on Tree-sitter, a tool that turns source code into a structured syntax tree.

In plain words
What is it for?
Use it when implementing a new language parser, setting up its Tree-sitter grammar, defining scope resolution, adding example files, and testing the implementation.
Why use it?
It gives parser work a consistent structure and explains how language scopes, symbol resolution, behavior, and audits fit together.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./contributing/tree-sitter/scripts/setup.sh [language].

Good fit Use it when implementing a new language parser, setting up its Tree-sitter grammar, defining scope resolution, adding example files, and testing the implementation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/madeinoz67/madeinoz-knowledge-system
agentmods
npx agentmods add skills/madeinoz67/madeinoz-knowledge-system/add-language

Made for: Claude Code.

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 add-language

README.md
[![agentmods](https://agentmods.dev/badge/skills/madeinoz67/madeinoz-knowledge-system/add-language/github.svg)](https://agentmods.dev/skills/madeinoz67/madeinoz-knowledge-system/add-language)
Your own site
<a href="https://agentmods.dev/skills/madeinoz67/madeinoz-knowledge-system/add-language"><img src="https://agentmods.dev/badge/skills/madeinoz67/madeinoz-knowledge-system/add-language/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for add-language

Your own site · 80×15
<a href="https://agentmods.dev/skills/madeinoz67/madeinoz-knowledge-system/add-language"><img src="https://agentmods.dev/badge/skills/madeinoz67/madeinoz-knowledge-system/add-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,632 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 $0.00087 $0.03632
Opus 5 $0.00044 $0.01816
Sonnet 5 $0.00017 $0.00726
Haiku 4.5 $0.00009 $0.00363

Measured 11d ago against content hash e8a4b2a1e18e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

add-language 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 11d 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.

.claude/skills/add-language/SKILL.md · 491 lines

How it starts

The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Language Implementation Skill

This skill guides you through implementing a new language parser in Codanna following the established six-layer architecture.

When to Use This Skill

  • User asks to "add support for [language]"
  • User wants to "implement [language] parser"
  • User says "create new language implementation"
  • User mentions "extend language support"
  • User asks about "adding a new programming language"

Prerequisites

Before starting, ensure you have:

  1. Tree-sitter grammar for the target language
  2. Understanding of language's scoping rules (local, module, global, etc.)
  3. Example code files in examples/[language]/ for testing
  4. Documentation references (see below)

Core Documentation References

This skill references three comprehensive documentation files:

Quick Start Workflow

Step 1: Setup Tree-sitter Grammar

# Install the grammar for exploration
./contributing/tree-sitter/scripts/setup.sh [language]

# Test parsing example files
tree-sitter parse examples/[language]/comprehensive.[ext]

Step 2: Create Language Directory Structure

# Create the six-file structure
mkdir -p src/parsing/[language]
cd src/parsing/[language]

# Create required files
touch mod.rs definition.rs parser.rs behavior.rs resolution.rs audit.rs

Step 3: Implement Core Traits

Follow this order (dependencies flow downward):

1. definition.rs  → LanguageDefinition trait
2. parser.rs      → LanguageParser trait (depends on definition)
3. behavior.rs    → LanguageBehavior trait (depends on parser)
4. resolution.rs  → Custom ResolutionContext (depends on behavior)
5. audit.rs       → NodeTrackingState (optional but recommended)
6. mod.rs         → Public API and registration

Read the full file on GitHub · 491 lines

Files

What ships with it

3 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. 11d ago First seen · 491 lines · 87 tokens per session scan A e8a4b2a1e18e

Subscribe to this mod's changes

add-language is a skill published in the GitHub repository madeinoz67/madeinoz-knowledge-system (3 stars, last pushed 5mo ago), licensed MIT. It adds 87 tokens to every session and 3,632 once invoked, about $0.0004 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.