core

core is a command for coding agents from wyattjoh/skills. It costs 0 tokens per session (1,591 once invoked), scanned C, original, MIT.

A set of Varlock commands for loading, checking, displaying, and explaining environment values from .env files according to a schema.

In plain words
What is it for?
Use it to inspect configuration locally or in continuous integration, choose an environment, print values in formats such as JSON or shell, and explain resolution results.
Why use it?
It helps find invalid or missing configuration while hiding sensitive values from command output.

Command

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 commands/wyattjoh/skills/core
Clone the repo
git clone --depth 1 https://github.com/wyattjoh/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 core

README.md
[![agentmods](https://agentmods.dev/badge/commands/wyattjoh/skills/core.svg)](https://agentmods.dev/commands/wyattjoh/skills/core)
Your own site
<a href="https://agentmods.dev/commands/wyattjoh/skills/core"><img src="https://agentmods.dev/badge/commands/wyattjoh/skills/core.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,591 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00000 $0.01591
Opus 5 $0.00000 $0.00796
Sonnet 5 $0.00000 $0.00318
Haiku 4.5 $0.00000 $0.00159

Measured 4d ago against content hash c6b5376757c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

core scanned grade C 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 4d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

> 📍 Embed in shell commands with `sh -c`, e.g. `sh -c 'do-something --token $(varlock printenv MY_TOKEN)'`.
skills/varlock/references/commands/core.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core commands: load, run, printenv, explain

The daily-driver resolution commands. All accept the common resolution flags (-p/--path, --env, --clear-cache, --skip-cache). Verified against varlock 1.10.0 --help.

load

Load env according to the schema, resolve + validate values, and print them. Sensitive values are redacted. The primary local-debug and CI-summary command.

varlock load [OPTIONS]
Flag Short Purpose
--format [format] -f Output format: pretty (default), json, env, shell, json-full.
--agent Agent-safe mode: redact sensitive values (defaults to JSON if --format unset).
--compact Compact output (json-full: no indentation; env/shell: skip undefined values).
--show-all When load is failing, show all items, not only failing ones.
--env <env> Set the environment (overridden by @currentEnv if present).
--path <path> -p Entry-point .env file/dir. Repeatable.
--summary-stderr Also write the pretty (redacted) summary to stderr.
--summary-file <file> Also write the pretty summary to a file (e.g. $GITHUB_STEP_SUMMARY).
--clear-cache Clear cache and re-resolve.
--skip-cache Skip cache for this invocation.

EXAMPLES: (verbatim from varlock load --help):

varlock load                    # Load and validate with pretty output
varlock load --format json      # Output in JSON format
eval "$(varlock load --format shell)"  # Load vars into current shell (useful with direnv)
varlock load --show-all         # Show all items when validation fails
varlock load --path .env.prod   # Load from a specific .env file
varlock load -p ./envs -p ./overrides  # Load from multiple directories
varlock load --compact          # Use compact format - skips undefined values, no indentation for json-full
varlock load --env production   # Load for a specific environment (⚠️ ignored if using @currentEnv!)
varlock load --format json-full --summary-stderr   # JSON on stdout + redacted human summary on stderr
varlock load --format json-full --summary-file /tmp/summary.txt   # JSON on stdout + redacted human summary written to file
varlock load --agent            # Agent-safe JSON output with sensitive values redacted

Read the full file on GitHub · 128 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. 4d ago First seen · 128 lines · 0 tokens per session scan C c6b5376757c8

Subscribe to this mod's changes

core is a command published in the GitHub repository wyattjoh/skills (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,591 tokens. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.