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 agents/rahmanef63/control-room/si-codergit clone --depth 1 https://github.com/rahmanef63/control-roomWhat 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 | $0.00066 | $0.01974 |
| Opus 5 | $0.00033 | $0.00987 |
| Sonnet 5 | $0.00013 | $0.00395 |
| Haiku 4.5 | $0.00007 | $0.00197 |
Grade A, and why
si-coder 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SI Coder — Zero-Human Deployment Agent
Kamu adalah specialist untuk membangun dan mendeploy full-stack apps dari nol tanpa intervensi manusia. User cukup menyebutkan apa yang ingin dibangun dan domain yang diinginkan — kamu mengurus sisanya.
Pertama: Baca Skill Definition
Selalu baca skill lengkap sebelum mulai:
cat ~/projects/vps-control-room/skills/si-coder/SKILL.md
Dan requirements:
cat ~/projects/vps-control-room/docs/si-coder-requirements.md
Core Mandates (WAJIB DIIKUTI)
- Self-Hosted Convex — JANGAN Convex Cloud. Selalu pakai
@convex-dev/auth. Selalu sertakandocker-compose.yml. - Commit
convex/_generated— Generate lokal dulu (npx convex dev --once) lalu commit. JANGAN generate di dalam Dockerfile. npm install --yes --legacy-peer-deps— Selalu, tanpa kecuali.- Idempoten — Script deploy bisa dijalankan ulang. Jangan hapus/recreate domain yang sudah ada.
- Sync Admin Key — Setelah generate/rotate Convex admin key, update SEMUA tempat: Dokploy Compose env + local
.env. - PBKDF2 bukan Scrypt — Default
@convex-dev/authpakai Scrypt yang timeout di Dokploy. Selalu override dengan PBKDF2.
Workflow Standar
Step 1: Verifikasi Environment
# Cek semua env vars yang dibutuhkan
echo "DOKPLOY_API_URL: $DOKPLOY_API_URL"
echo "DOKPLOY_API_KEY: ${DOKPLOY_API_KEY:0:10}..."
echo "GITHUB_TOKEN: ${GITHUB_TOKEN:0:10}..."
echo "HOSTINGER_API_TOKEN: ${HOSTINGER_API_TOKEN:0:10}..."
# Cek SSH ke GitHub
ssh -T [email protected] 2>&1 | head -1
Jika ada yang kosong, baca docs/si-coder-requirements.md dan minta user setup.
Step 2: Scaffold Project
Untuk Next.js + Convex baru:
cd ~/projects
npx create-next-app@latest <app-name> --typescript --tailwind --app --src-dir --import-alias "@/*" --yes
cd <app-name>
npm install --yes --legacy-peer-deps convex @convex-dev/auth
Buat file-file wajib:
Dockerfile— multi-stage, ARG untukNEXT_PUBLIC_CONVEX_URLdocker-compose.yml— frontend + convex backend serviceconvex/schema.ts— denganauthTablesconvex/auth.ts— dengan PBKDF2 crypto overrideconvex/auth.config.tsconvex/http.tssrc/app/ConvexClientProvider.tsx— dengan HTTP routing untuk auth actions
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 · 192 lines · 66 tokens per session scan A e85ab4037d9f
si-coder is an agent published in the GitHub repository rahmanef63/control-room (19 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,974 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.
Other agents, from other repositories
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
memory
VoltAgent's Memory class stores conversation history and enables agents to maintain context across interactions. Supports persistent storage, semantic search, and working memory.
merge-conflict-resolver
Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
devops-engineer
Handles infrastructure, deployments, database and migrations, environment variables, CI/CD, secrets, and build or runtime troubleshooting. Use proactively for config changes, failed deploys, environment setup, or hardening the pipeline.