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 skills/smith-horn/skillsmith/varlocknpx skills add smith-horn/skillsmith --skill varlockgit clone --depth 1 https://github.com/smith-horn/skillsmithWrote 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/skills/smith-horn/skillsmith/varlock)<a href="https://agentmods.dev/skills/smith-horn/skillsmith/varlock"><img src="https://agentmods.dev/badge/skills/smith-horn/skillsmith/varlock.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 5.1 | $0.00073 | $0.03461 |
| Opus 5 | $0.00036 | $0.01731 |
| Sonnet 5 | $0.00015 | $0.00692 |
| Haiku 4.5 | $0.00007 | $0.00346 |
Grade F, and why
varlock scanned grade F with 4 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
> **Format matters.** Only `varlock load`'s **default pretty format** — the output shown above — redacts sensitive values. `varlock load --format json`, `--format json-full`, `--format json-full-compact`, and `--format e Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
cat .env | grep SECRET Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSfL https://varlock.dev/install.sh | sh -s -- --force-no-brew Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Authorization: Bearer sk_live_xxx" https://api.example.com The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 2d ago First seen · 469 lines · 73 tokens per session scan F 2d9448e5aff4
varlock is a skill published in the GitHub repository smith-horn/skillsmith (78 stars, last pushed today), with no licence file. It adds 73 tokens to every session and 3,461 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it F with 4 findings (subtle steering, harvests environment variables, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cis-aws-compute-3.6
Ensure secrets are not passed as container environment variables in Amazon ECS task definitions.
configuration-management
Manage application configuration across environments with layered config loading, environment variables, secrets management, and validation. Covers 12-factor app patterns and config file formats. Triggers on configuration management, environment variables, or settings architecture requests.
battle-tested-engineer
Engineering judgment for code write/refactor/test and frontend UI. Trigger on code review, legacy cleanup, tests, UI with data, bloat/over-engineer complaints — even with no explicit mention, before any diff/rewrite/test suite. Output ultra-terse caveman style; code, commits, PR desc, security warnings stay normal…
fw-ai-actions-app
Expert-level skill for AI Actions and integrations on Freshworks Platform 3.0. Use when (1) Creating actions.json and SMI functions (flat request, nested response), (2) Request templates and third-party API integration, (3) Pre-build validation (pricing, paywalls, account prerequisites), (4) Failure-case validation…
fw-review
Full Freshworks marketplace app review — iparams, frontend, serverless, FDK, security, and structured text report output — in one skill.
canary
Scans your OpenClaw environment for leaked secrets — API keys, tokens, credentials in .env files, installed skills, and shell history. Runs silently on startup, deep scans on demand. Fixes issues with your permission.