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/lizard-build/lizard-mcp/corenpx skills add lizard-build/lizard-mcp --skill coregit clone --depth 1 https://github.com/lizard-build/lizard-mcpWhat 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 | $0.00194 | $0.03427 |
| Opus 5 | $0.00097 | $0.01714 |
| Sonnet 5 | $0.00039 | $0.00685 |
| Haiku 4.5 | $0.00019 | $0.00343 |
Grade A, and why
lizard-core 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lizard platform
Lizard is a unified cloud for apps, services, agents, and managed databases. This MCP server exposes the whole platform through 33 tools — deploy a GitHub repo, provision managed Postgres/Redis/S3, and manage logs, metrics, secrets, domains, scaling, and shell exec — scoped to the caller's own workspaces and projects.
Mental model
workspace -> project -> service (app or addon)
- Workspace — account/org level. A user belongs to one or more (
workspace_list). - Project — a group of related services in one workspace (
project_list,project_create). - Service — a deployable unit. Every app deploys from a GitHub repo (
service_createwithrepoUrl) or starts empty and gets a source wired in later (service_set). There is no local tarball-upload path here — unlike thelizardCLI'slizard up, this MCP server can only deploy from a git repo URL, since it has no access to the user's local filesystem. - Managed addons —
postgres,redis,s3(addon_create). See Managed addons for each type's env vars. - Cross-resource refs —
${{<name>.<KEY>}}resolves at deploy time against the target's merged env. A ref to a missing target or key resolves to an empty string rather than failing the deploy (only circular refs throw). After wiring one, verify the consumer actually got a value —logs_tailorssh_exec -- env. Stored form is ID-based, so renaming an addon later doesn't break existing refs.
Most tools take a project (name/slug/ID) and service (name/ID) param, resolved by
exact name match, not fuzzy — call workspace_list / project_list / service_list
first if unsure which one the user means.
No local repo access
Unlike the lizard CLI or a coding agent working in the user's own checkout, this MCP
server never sees the user's files. It cannot read package.json, a Dockerfile, or
check for a git remote. That means:
- Ask the user for the repo URL, branch, and any build/start command instead of inferring them from local files.
- Rely on the platform's own build auto-detection (lizardpack) for common stacks (Go,
Node, Python, Rust, Ruby, PHP, Java, static) rather than guessing a
buildCommand/startCommandup front — only set those fields if the user states them, or a build actually fails without them. - If a build fails, read
deploy_events/logs_tailfor the real error before proposing a fix.
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.
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 · 259 lines · 194 tokens per session scan A 0a2d20c6903a
lizard-core is a skill published in the GitHub repository lizard-build/lizard-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 194 tokens to every session and 3,427 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
postgres
Configure DigitalOcean Managed Postgres with bindable variables or schema isolation. Use when setting up databases, creating users, managing permissions, configuring multi-tenant schemas, or troubleshooting database connectivity on App Platform.
huawei-cloud-ecs-sqlbot-deploy
Purchase Huawei Cloud X Instance server + one-click deploy SQLBot intelligent query application. Tech stack: Python 3.8+, Huawei Cloud SDK, COC (Cloud Operations Center) deployment. Key capabilities: AK/SK auth, X instance creation, auto security group config, SQLBot auto deployment. Use cases: Users who need to…
lizard-core
Core Lizard CLI usage guide. Read this before running any lizard commands. Covers the full app lifecycle (login, init, link, add, up, redeploy, logs, events, status, scale, restart, secrets, domains, run, ssh, metrics), the workspace → project → service model, managed addons (postgres, redis, s3 with auto-public…
static-blog-deploy
Skill "static-blog-deploy" from Morningstar202604/awesome-skillkit, covering static blog deploy, 支持平台, 安全设计, 使用示例 and hexo 部署.
deploio-provision
Provisions and connects managed backing services to Deploio apps — PostgreSQL, MySQL, Redis-compatible KVS, OpenSearch, and S3-compatible object storage. This skill should be triggered when the user needs to add a database, cache, or storage service: "add postgres to Deploio", "provision MySQL", "need a database on…
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.