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 skills add rjwalters/kicad-tools --skill repo-browsergit clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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/rjwalters/kicad-tools/repo-browser)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-browser"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-browser/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.
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-browser"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-browser.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01807 |
| Opus 5.5 | $0.00016 | $0.00723 |
| Sonnet 5.5 | $0.00008 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade B, and why
repo-browser scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/browser-use/SKILL.md 2>/dev/null Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| curl -sS -H @- https://api.browser-use.com/api/v2/billing/account How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex form of the
/repo:browsercommand. Other commands appear as$repo-<verb>skills. Helper scripts and.claude/paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.
$repo-browser — Browser-Automation Environment Health
Report whether this environment can drive a browser the way the adopting
org's policy expects, and offer to install what is missing. The stack is
Browser Use: the browser-use CLI (local Chrome,
cloud stealth browsers, or any CDP endpoint), its first-party agent skills,
and — when a key is present — the Browser Use Cloud account behind them.
This command provisions and reports; it never drives a browser. Task execution, URL policy, and what may enter a browser session belong to the adopting org's browser-automation policy (wherever that org keeps it), not to this command.
Shaped like [[remote]] and [[sudo]]: the report is read-only and safe to run anywhere; every install is an environment change and is confirmed before it runs.
Usage
$repo-browser # Report, then offer confirm-gated installs for what's missing
$repo-browser --check # Report only, never writes (also: any unknown argument)
Scope — and the neighboring commands it is not
This is environment provisioning, the remote/sudo/host-optimize family.
It is deliberately not [[update-tools]] business: that command scopes
itself to installer-managed tool packages with a local source clone to diff
against and routes pip/uv tools to [[deps]] — a globally installed uv CLI
has no local clone, so neither comparison model applies. If browser-use
was installed by an installer that records install-metadata.json, that
install's currency is [[update-tools]]' to report; this command only checks
presence, version, auth, and cloud health.
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.
- 8d ago First seen · 162 lines · 39 tokens per session scan B fadbfcc4715b
repo-browser is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,807 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.
repo-browser compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-browserrjwalters/kicad-tools | Skill | 73 | yesterday | MIT | B | 39 | Claude Code, Codex |
| vercel-sandboxvercel-labs/agent-browser | Skill | 48k | today | Apache-2.0 | A | 126 | Claude Code, Codex |
| protected-vercel-deploymentsvercel-labs/agent-browser | Skill | 48k | today | Apache-2.0 | A | 75 | Claude Code |
| agentcorevercel-labs/agent-browser | Skill | 48k | today | Apache-2.0 | A | 89 | Claude Code |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| lovablex-cmd/x-cmd | Skill | 4.7k | 9d ago | Apache-2.0 | A | 30 | Claude Code, Codex |
| agent-browserx-cmd/x-cmd | Skill | 4.7k | 9d ago | Apache-2.0 | A | 39 | Claude Code, Codex |