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/skyhook-io/radar/visual-testnpx skills add skyhook-io/radar --skill visual-testgit clone --depth 1 https://github.com/skyhook-io/radarWhat 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 | $0.00020 | $0.00059 |
| Opus 5 | $0.00010 | $0.00030 |
| Sonnet 5 | $0.00004 | $0.00012 |
| Haiku 4.5 | $0.00002 | $0.00006 |
Grade A, and why
visual-test 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.
What it actually says
Follow the workflow in .claude/commands/visual-test.md.
Do not modify the Claude command file. Treat it as the canonical workflow source for this repository.
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 · 9 lines · 20 tokens per session scan A 597ae28a05ee
visual-test is a skill published in the GitHub repository skyhook-io/radar (3,204 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 59 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 2026-08-30.
Other skills, from other repositories
higress-update-envoy-gateway
Update Higress Envoy binary and gateway image dependencies for e2e validation. Use when Codex needs to build Envoy packages from the current Higress branch, upload those packages to higress-group/proxy releases, update Makefile.core.mk ENVOYPACKAGEURLPATTERN and ENVOYLATESTIMAGETAG, run make build-gateway-local, retag…
qa-find-bugs
Drive the live product at https://dashboard.bex.co as a signed-in QA user (QAEMAIL / QAPASSWORD from .env), hunt real bugs across the hosting features, research each fix down to file:line, file the non-duplicate findings to the w6 board through /pm, and /ship the scheduled milestone. Use when the user asks to QA the…
refactor
Refactors code following Ousterhout's design principles. Analyzes complexity, creates prioritized refactoring plan, and executes with safety-first approach. Optimized for Vite/React, Tauri/Rust, Zustand stack.
software-design-review
Analyzes code based on John Ousterhout's "A Philosophy of Software Design". Identifies unnecessary complexity, shallow modules, information leaks, and design problems. Use when reviewing architecture, PRs, refactoring, or asking about code quality.
vet
Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.
test-skill
A minimal test skill for e2e testing of the skill pack resolver.