sc-clerk

sc-clerk is a skill for Claude Code, Codex from rahmanef63/si-coder-agent. It costs 68 tokens per session (649 once invoked), scanned A, original, MIT.

A stub command for setting up Clerk authentication in projects that use Clerk instead of Convex Auth. Clerk is a hosted user-login service, while Convex is a backend platform.

In plain words
What is it for?
Use it only as a placeholder for future Clerk setup involving allowed origins, a Convex JWT template, environment variables, and authentication configuration.
Why use it?
It records the intended setup but is not implemented yet, so it cannot currently perform the promised configuration. This prevents it from being mistaken for a working automation.

Skill for Claude CodeCodex

Part of the si-coder plugin — 21 skills, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/rahmanef63/si-coder-agent/sc-clerk
Any agent
npx skills add rahmanef63/si-coder-agent --skill sc-clerk
Clone the repo
git clone --depth 1 https://github.com/rahmanef63/si-coder-agent

Made for: Claude Code, Codex.

Or install si-coder, the plugin that ships this one along with the rest of its 21 skills, 1 MCP server.

Wrote 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.

agentmods badge for sc-clerk

README.md
[![agentmods](https://agentmods.dev/badge/skills/rahmanef63/si-coder-agent/sc-clerk.svg)](https://agentmods.dev/skills/rahmanef63/si-coder-agent/sc-clerk)
Your own site
<a href="https://agentmods.dev/skills/rahmanef63/si-coder-agent/sc-clerk"><img src="https://agentmods.dev/badge/skills/rahmanef63/si-coder-agent/sc-clerk.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.00649
Opus 5 $0.00034 $0.00324
Sonnet 5 $0.00014 $0.00130
Haiku 4.5 $0.00007 $0.00065

Measured today against content hash 6cbbb65a18a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sc-clerk 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/jwt-template.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/sc-clerk/SKILL.md · 54 lines

What it actually says

/sc-clerk — Clerk auth (STUB)

Status: boilerplate only. Use only when a project explicitly chooses Clerk over @convex-dev/auth.

When to use

By default /sc-all and /sc-convex use @convex-dev/auth. Use /sc-clerk only when:

  • The user explicitly requests Clerk.
  • An existing project already uses Clerk and is being migrated/maintained.
  • You want a managed auth UI without running self-hosted JWKS.

Scope when implemented

  • Read Clerk instance from CLERK_SECRET_KEY (Backend API).
  • Configure allowed origins (NEXT_PUBLIC_<app-url> + dev origin).
  • Create a JWT template named convex with the correct issuer claim so Convex can verify.
  • Write NEXT_PUBLIC_CLERK_FRONTEND_API_URL + publishable key to project .env.
  • Set up Convex auth.config.ts with providers: [{ domain: <clerk-issuer>, applicationID: 'convex' }].

Env vars

Var Purpose
CLERK_SECRET_KEY sk_test_ or sk_live_ Backend API key
NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY pk_test_ or pk_live_ Frontend key
NEXT_PUBLIC_CLERK_FRONTEND_API_URL https://<issuer-domain>

Suggested file layout

sc-clerk/
├── SKILL.md
└── scripts/
    ├── instance.js       # read instance config + origins
    ├── set-origins.js    # update allowed origins
    ├── jwt-template.js   # create the 'convex' JWT template
    └── sync-convex-auth-config.js  # write auth.config.ts in project

Note on Clerk MCP

Once clerk MCP is installed (https://mcp.clerk.com/mcp), prefer it for SDK snippet generation, integration patterns, and SDK-version-specific advice. /sc-clerk handles provisioning (origins, JWT template, env setup); Clerk MCP handles code patterns.

Files

What ships with it

1 file 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.

Changes

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.

  1. today Changed · +6 lines 6cbbb65a18a8
  2. 5d ago First seen · 48 lines · 68 tokens per session scan A ce156d16cca3

Subscribe to this mod's changes

sc-clerk is a skill published in the GitHub repository rahmanef63/si-coder-agent (14 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 649 once invoked, about $0.0003 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.

Related

Other skills, from other repositories