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/rahmanef63/si-coder-agent/sc-syncnpx skills add rahmanef63/si-coder-agent --skill sc-syncgit clone --depth 1 https://github.com/rahmanef63/si-coder-agentWhat 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 | $0.00104 | $0.01525 |
| Opus 5 | $0.00052 | $0.00763 |
| Sonnet 5 | $0.00021 | $0.00305 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
sc-sync 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sc-sync — Gitignored-file sync over Tailscale
Why this exists
A repo is checked out on two machines (say, a VPS and a laptop). .gitignore
deliberately keeps some files out of git — local notes, generated docs,
scratch config — so they never travel with git push / git pull. Plain SSH
scp/rsync between the two kept failing (NAT, dynamic IP, firewall...);
Tailscale is confirmed working on both ends. This skill wraps rsync over the
Tailscale interface so those gitignored files can move in either direction
without inventing a new transport.
It deliberately does not try to guess which machine it's running on via
hostname — that leaks a real, personally-identifying hostname into logs and
breaks the moment either machine is renamed or reimaged. Instead the
invoking side declares itself explicitly via SYNC_ROLE.
Requirements
- Both machines joined to the same tailnet (
tailscale statusshows both). - The repo is checked out at the same absolute path on both machines (the
default
SYNC_REMOTE_PATHassumes this — override it if the layout differs). rsyncinstalled on both machines.- The non-invoking side needs inbound SSH reachable over Tailscale — rsync
tunnels through SSH by default. That means:
- Linux/macOS:
sshdrunning, reachable from the tailnet. - Windows: OpenSSH Server is NOT on by default. You must explicitly
enable "OpenSSH Server" (Settings → Optional Features, or
Add-WindowsCapability -Online -Name OpenSSH.Server~~~~0.0.1.0in an elevated PowerShell) and make sure thesshdservice is running before alocal-vps/vps-localsync can reach a Windows box. This is a real per-machine caveat, not a generic assumption — check it on whichever side is the pull/push target if the connection times out.
- Linux/macOS:
Env vars
| Variable | Required | Default | Meaning |
|---|---|---|---|
SYNC_ROLE |
yes | — | Which machine this process is running on: exactly vps or local. Never inferred from hostname. |
SYNC_VPS_TS_ADDR |
yes | — | Tailscale MagicDNS alias or 100.x IP of the VPS, e.g. your-vps or 100.x.x.x. |
SYNC_LOCAL_TS_ADDR |
yes | — | Tailscale MagicDNS alias or 100.x IP of the local machine, e.g. your-laptop. |
SYNC_REMOTE_USER |
no | os.userInfo().username |
SSH user on the far side. |
SYNC_REMOTE_PATH |
no | this repo's own git rev-parse --show-toplevel |
Absolute repo path on the far side. Only override if the two checkouts don't live at the same path. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 118 lines · 104 tokens per session scan A 8591e88e7195
sc-sync is a skill published in the GitHub repository rahmanef63/si-coder-agent (14 stars, last pushed 5d ago), licensed MIT. It adds 104 tokens to every session and 1,525 once invoked, about $0.0005 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
convex-create-component
Designs and builds Convex components with isolated tables, clear boundaries, and app-facing wrappers. Use this skill when creating a new Convex component, extracting reusable backend logic into a component, building a third-party integration that owns its own tables, packaging Convex functionality for reuse, or when…
convex-quickstart
Initializes a new Convex project from scratch or adds Convex to an existing app. Use this skill when starting a new project with Convex, scaffolding with npm create convex@latest, adding Convex to an existing React, Next.js, Vue, Svelte, or other frontend, wiring up ConvexProvider, configuring environment variables…
convex-performance-audit
Audits and optimizes Convex application performance across hot-path reads, write contention, subscription cost, and function limits. Use this skill when a Convex feature is slow or expensive, npx convex insights shows high bytes or documents read, OCC conflict errors or mutation retries appear, subscriptions or UI…
convex-setup-auth
Sets up Convex authentication with user management, identity mapping, and access control. Use this skill when adding login or signup to a Convex app, configuring Convex Auth, Clerk, WorkOS AuthKit, Auth0, or custom JWT providers, wiring auth.config.ts, protecting queries and mutations with ctx.auth.getUserIdentity()…
convex-migration-helper
Plans and executes safe Convex schema and data migrations using the widen-migrate-narrow workflow and the @convex-dev/migrations component. Use this skill when a deployment fails schema validation, existing documents need backfilling, fields need adding or removing or changing type, tables need splitting or merging…
robel-auth
Integrate and maintain Robelest Convex Auth in apps by always checking upstream before implementation. Use when adding auth setup, updating auth wiring, migrating between upstream patterns, or troubleshooting @robelest/convex-auth behavior across projects.