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.
npx agentmods add commands/4tyone/snek/snek.fillgit clone --depth 1 https://github.com/4tyone/snekWrote 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.
[](https://agentmods.dev/commands/4tyone/snek/snek.fill)<a href="https://agentmods.dev/commands/4tyone/snek/snek.fill"><img src="https://agentmods.dev/badge/commands/4tyone/snek/snek.fill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00661 |
| Opus 5 | $0.00000 | $0.00331 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
snek.fill scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get(url) How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snek Fill Command
You are processing @@snek blocks - regions in source code where the developer has written specifications for code that needs to be generated or modified.
Step 1: Find all snek blocks
Run the snek parser script to find all @@snek ... snek@@ blocks in the codebase:
.claude/scripts/snek-parse.sh
This will output JSON with all blocks found. Each block contains:
file: Full path to the filestart_line: Line number where@@snekstartsend_line: Line number wheresnek@@endscontent: The raw text between the markers (specification, code, or both)
Step 2: Create todo list
For EACH block found, create a todo item. This is CRITICAL - every single block must be tracked:
TodoWrite with items like:
- "Implement snek block in {file}:{start_line}-{end_line}"
Step 3: Process each block
For each block, in order:
3a. Read the file and understand context
- Read the file containing the block
- If the content references other files via
@path/to/filesyntax, read those files too - Understand the surrounding code context (function signature, imports, types)
3b. Implement the request
- The content between
@@snekandsnek@@tells you what to do - It may be pure instructions, or instructions mixed with existing code to modify
- Generate the appropriate code based on the content
3c. Apply the change
Use the Edit tool to replace the entire block (from @@snek line to snek@@ line inclusive) with the generated code. Remove the markers.
3d. Mark todo complete
Mark this todo item as completed before moving to the next block.
Examples
Pure specification:
func ValidateEmail(email string) error {
// @@snek
// Validate email format using regex
// Return error if invalid, nil if valid
// snek@@
}
Modification request with existing code:
# @@snek modify this to also accept a timeout parameter
def fetch_data(url):
response = requests.get(url)
return response.json()
# snek@@
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.
- 5d ago First seen · 88 lines · 0 tokens per session scan A cd8df6d4f5ca
snek.fill is a command published in the GitHub repository 4tyone/snek (10 stars, last pushed 8mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 661 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.
adr
Create an Architecture Decision Record in memory-bank BACKLOG.
trace
Export a Grok session trace locally, or upload it to xAI.