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/validatorsdao/slv/slv-performance-boostnpx skills add ValidatorsDAO/slv --skill slv-performance-boostgit clone --depth 1 https://github.com/ValidatorsDAO/slvWhat 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 | $0.00085 | $0.01260 |
| Opus 5 | $0.00043 | $0.00630 |
| Sonnet 5 | $0.00017 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade B, and why
slv-performance-boost scanned grade B with 1 finding 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 3d 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.
sudo systemctl disable --now slv-cpu-boost.service How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SLV CPU Performance Boost Skill
Keeps Solana validator / RPC nodes running at peak CPU frequency at all times. Runs alongside SMT disable and IRQ tuning as part of the slv v init / slv r init tuning phase.
What it applies
| # | Item | Effect | Reboot |
|---|---|---|---|
| 1 | apt-get update && apt-get upgrade -y |
Refresh OS packages and userland | No |
| 2 | Install HWE kernel (linux-image-generic-hwe-24.04) |
Enables amd_pstate 6.14+ on AMD |
Yes (AMD only when kernel < 6.14) |
| 3 | GRUB amd_pstate=active processor.max_cstate=0 cpufreq.default_governor=performance |
Initializes amd_pstate driver in active mode at boot | Yes (AMD only, first apply) |
| 4 | modprobe amd_pstate |
Try to load the driver at runtime | No |
| 5 | governor=performance |
Lock frequency at maximum | No |
| 6 | EPP=performance |
Push the energy/performance preference toward performance | No |
| 7 | boost=enabled / Intel no_turbo=0 |
Enable Turbo Boost | No |
| 8 | cpuidle state*/disable=1 |
Disable C-states to avoid latency spikes | No |
| 9 | scaling_max_freq=cpuinfo_max_freq |
Align scaling ceiling with the hardware ceiling | No |
| 10 | slv-cpu-boost.service (oneshot) |
Re-applies items 5-9 on every boot | No |
Related artifacts
ansible/cmn/boost_performance.yml- Idempotency marker:
/var/lib/slv/.boost_applied - Persistence script:
/usr/local/bin/slv-cpu-boost.sh - systemd unit:
/etc/systemd/system/slv-cpu-boost.service
Options
| Variable | Default | Description |
|---|---|---|
amd_pstate_mode |
active |
active (best performance) or passive |
Standalone run
ansible-playbook -i inventory.yml cmn/boost_performance.yml --limit <host>
ansible-playbook -i inventory.yml cmn/boost_performance.yml --limit <host> -e amd_pstate_mode=passive
Kernel update + reboot
When an AMD CPU is detected and uname -r is below 6.14, the playbook installs the HWE kernel, writes the amd_pstate=active GRUB cmdline, and the orchestrator (cmn/optimize_node.yml) detects need_reboot=true and reboots automatically.
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.
- 3d ago First seen · 94 lines · 85 tokens per session scan B 647271912262
slv-performance-boost is a skill published in the GitHub repository ValidatorsDAO/slv (89 stars, last pushed 11d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,260 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stellar-forge
Eval-driven coding harness for building production Stellar dApps. Routes tasks to 6 specialist agents, verifies output with structured evals, steers on failure, e2e-tests with Stellar Agentic Kit hooks, and knowledge-graphs every project. Use when building any Stellar app — tokens, DeFi, NFTs, payment APIs, or full…
stellar-mcp
MCP (Model Context Protocol) tools for Stellar development. Gives Claude direct access to the Stellar blockchain, filesystem, GitHub, and Playwright through configured MCP servers. Use when querying chain data, deploying contracts, managing repos, or running e2e tests from within the agent.
alchemy-agentic-gateway
Use when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features. Also use when the user mentions "SIWE", "SIWS", "x402", "MPP", "mppx", or "agentic gateway" — this skill covers wallet-based auth flows for Alchemy's x402 and MPP…
alchemy-api
Integrates Alchemy blockchain APIs using an API key. Requires $ALCHEMYAPIKEY to be set; if unavailable, use the alchemy-agentic-gateway skill instead. Use when user asks about EVM JSON-RPC calls, token balances, NFT ownership or metadata, transfer history, token prices, portfolio data, transaction simulation…
rpcedge
Use rpc edge Solana trading infrastructure via MCP tools - doctor, RPC health, priority fees, epoch/leaders, latency compare, Yellowstone first-seen sample, endpoint map, and signed-transaction relay. Prefer when the user needs low-latency Solana RPC/gRPC/sender setup, fee pricing, or agent-ready infra with keys in…
Solana Agent Builder
Build AI-powered agents for Solana blockchain — trading bots, DeFi strategies, token analysis, and on-chain automation with TypeScript.