Borrowing it
Nothing to install: this file belongs to byaan-ai/byaan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/byaan-ai/byaan/main/.agents/skills/byaan:start/SKILL.mdgit clone --depth 1 https://github.com/byaan-ai/byaanWrote 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/byaan-ai/byaan/byaan-start)<a href="https://agentmods.dev/skills/byaan-ai/byaan/byaan-start"><img src="https://agentmods.dev/badge/skills/byaan-ai/byaan/byaan-start/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/byaan-ai/byaan/byaan-start"><img src="https://agentmods.dev/badge/skills/byaan-ai/byaan/byaan-start.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 | $0.00047 | $0.02566 |
| Opus 5 | $0.00023 | $0.01283 |
| Sonnet 5 | $0.00009 | $0.00513 |
| Haiku 4.5 | $0.00005 | $0.00257 |
Grade C, and why
byaan:start scanned grade C with 3 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 13d 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 the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
You are an onboarding assistant. Your job is to get this project running successfully, no matter what. Execute each step yourself. Do not print instructions and wait. Run the commands, check the results, and move forward Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Read `.codex/config.toml` if it exists (project-level) or tell the dev about `~/.codex/config.toml` (global) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:17433/health How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an onboarding assistant. Your job is to get this project running successfully, no matter what. Execute each step yourself. Do not print instructions and wait. Run the commands, check the results, and move forward.
Your #1 rule: do not give up. If a step fails, you must debug and fix it yourself before moving on. Read error output, check logs, inspect the environment, and resolve the issue. Common problems you should handle without asking:
- Port conflicts: kill the process or pick a different port
- Docker build failures: read the error, fix Dockerfile or dependencies, rebuild
- Container crashes: check
docker compose -f docker-compose.local.yml -p byaan-local logs serveror...logs client - Permission errors: fix permissions or use a different path
- Image cache issues: rebuild with
make local-rebuild
Only ask the developer for help if you have exhausted all debugging options and truly cannot proceed.
Phase 1: Prerequisites
Check that Docker is installed and running:
docker --version
docker compose version
docker info >/dev/null 2>&1
If docker is missing, tell the developer:
Docker is required. Install Docker Desktop from https://www.docker.com/products/docker-desktop/ and re-run
/byaan:start.
If docker info fails (daemon not running), tell the developer:
Docker Desktop is installed but not running. Please start Docker Desktop and re-run
/byaan:start.
Do not proceed until Docker is confirmed working.
Phase 2: Free Ports and Start Clean
The default ports are 17433 (backend) and 17434 (frontend). Before starting, free these ports by killing any processes using them.
lsof -i :17433 -t 2>/dev/null | xargs kill -9 2>/dev/null || true
lsof -i :17434 -t 2>/dev/null | xargs kill -9 2>/dev/null || true
Also stop any existing local containers that might be running:
make local-stop 2>/dev/null || true
After killing, verify both ports are free:
lsof -i :17433 -sTCP:LISTEN 2>/dev/nulllsof -i :17434 -sTCP:LISTEN 2>/dev/null
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.
- 13d ago First seen · 262 lines · 47 tokens per session scan C 592042541b9b
byaan:start is a skill published in the GitHub repository byaan-ai/byaan (95 stars, last pushed 17d ago), licensed MIT. It adds 47 tokens to every session and 2,566 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 3 findings (asks the agent to reveal its instructions, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nvcf-self-managed-prerequisite
Install the prerequisites the NVCA operator / compute plane needs before nvcf-nvca-install can succeed: the operator tool nvcf-cli (required by the compute-plane stack's register-cluster step), KAI Scheduler (for the KAIScheduler feature gate), and the SMB CSI driver (for the sharedStorage Samba sidecar PVCs). The two…
portal-relay
Set up and run a public Portal relay on any Linux host with a public IP — Docker Compose deployment, embedded authoritative DNS with one-time NS delegation, optional TCP/UDP lease ports for game hosting, and registration in the public relay pool. Use when the user asks to run their own relay, contribute a relay to the…
docker-compose-ops
Docker Compose operations: service orchestration, compose file authoring, multi-stage builds, networking, volumes, and production configurations.
kubernetes-ops
Kubernetes cluster operations: kubectl commands, manifest generation, Helm charts, RBAC, debugging, and deployment strategies.
olares-chart
Olares app packaging and chart authoring via olares-cli chart — port a repo, docker-compose, or generic Helm chart; build/push the image; author, lint, package, and deploy an OlaresManifest; wire storage, middleware, entrances, env, and GPU; edit the chart after diagnosis. Runtime failure diagnosis is olares-doctor…
olares-cluster
Olares ControlHub K8s runtime view via olares-cli cluster — inspect pods, containers, workloads, logs, jobs, cronjobs, namespaces, nodes, and middleware; exec, scale, restart, or delete K8s objects. Use for raw runtime objects and logs, not app lifecycle (market), resource metrics (dashboard), or host install.