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-remotegit 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-remote)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-remote"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-remote/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-remote"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-remote.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 | $0.00026 | $0.30206 |
| Opus 5.5 | $0.00010 | $0.12082 |
| Sonnet 5.5 | $0.00005 | $0.06041 |
| Haiku 4.5 | $0.00003 | $0.03021 |
Grade F, and why
repo-remote scanned grade F with 5 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
passwordless-sudo drop-in is installed. Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
REPO_REMOTE_SSH_KEY=~/.ssh/id_ed25519 # key used for the SSH session (fine to share) Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
path, offer to install it (`curl -fsSL https://claude.ai/install.sh | bash`). Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
`169.254.169.254`) will fail or time out. The dev container gets what it needs Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Hygiene: the client ID is the only value placed in `curl`'s arguments. The How it starts
The opening of the file, as written. The whole thing — 1,987 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex form of the
/repo:remotecommand. Other commands appear as$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-remote — Remote Dev Session
Stand up (or reuse) a cloud VM with this repository cloned and synced, then
open a live SSH session in a new terminal window — landing in the repo, ready
to run claude and continue the work on the remote host.
Configuration is read from two layers (see below): shared cloud credentials
from ~/.config/repo/remote.env (reused across every repo), with the
target repo's .env layered on top for per-repo machine settings — and
free to override any shared value. The provisioning credentials are used
locally to drive the cloud CLI; they are never copied to the VM.
Usage
$repo-remote # Read .env, bring up / reuse the host, open SSH
$repo-remote --configure # Guided setup: shared creds (~/.config/repo/remote.env) + repo .env (machine)
$repo-remote gcp # Override REPO_REMOTE_PROVIDER for this run
$repo-remote aws
$repo-remote --status # List instances created by this command
$repo-remote --verify # Prove the SSH alias still reaches THIS repo's instance
$repo-remote --attach # Reconnect: verify the host, then open a session with a FRESH GitHub credential
$repo-remote --down # Stop instances created by this command
$repo-remote --down --delete # Terminate/delete them
First time in a repo? Run $repo-remote --configure to build the .env below,
then $repo-remote to launch.
The provisioning contract below is implemented once, as an executable
script — scripts/repo/repo-remote.sh, installed to
.claude/skills/repo/scripts/repo-remote.sh. The interactive flow here is a
thin wrapper: it runs the wizard/cost-confirmation UX, and once you say yes it
calls that script rather than re-issuing aws/gcloud calls from prose. The
same script is the headless entry point a non-interactive caller (e.g.
loom's fleet add-worker) invokes directly:
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 Changed · +14 lines 705936f6b6a3
- 8d ago First seen · 1,973 lines · 26 tokens per session scan F 3b9f37575c7d
repo-remote is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 30,206 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it F with 5 findings (asks for root, reaches for credential files, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.
repo-remote compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-remoterjwalters/kicad-tools | Skill | 73 | yesterday | MIT | F | 26 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 24k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 171 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 10d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | 2d ago | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | 3d ago | MIT | A | 78 | Claude Code |