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 commands/appwrite/claude-plugin/deploy-sitegit clone --depth 1 https://github.com/appwrite/claude-pluginWhat 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 | $0.00011 | $0.00992 |
| Opus 5 | $0.00005 | $0.00496 |
| Sonnet 5 | $0.00002 | $0.00198 |
| Haiku 4.5 | $0.00001 | $0.00099 |
Grade A, and why
deploy-site scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- deploy-site — 97% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy a site using the Appwrite CLI
Prerequisites
- Appwrite CLI installed (
npm install -g appwrite-cli) - Authenticated with
appwrite login - Project initialized with
appwrite init
Quick Deploy
appwrite push sites
Full Workflow
1. Initialize a new site
appwrite init sites
2. Pull existing sites from Console
appwrite pull sites
3. Configuration
Sites are configured in appwrite.config.json:
{
"projectId": "<PROJECT_ID>",
"endpoint": "https://<REGION>.cloud.appwrite.io/v1",
"sites": [
{
"$id": "<SITE_ID>",
"name": "My Site",
"enabled": true,
"logging": true,
"framework": "astro",
"timeout": 30,
"installCommand": "npm install",
"buildCommand": "npm run build",
"outputDirectory": "./dist",
"specification": "s-1vcpu-512mb",
"buildRuntime": "node-22",
"adapter": "ssr",
"fallbackFile": "",
"path": "sites/my-site"
}
]
}
4. Deploy
appwrite push sites
CI/CD (Non-Interactive)
Set up headless mode first:
appwrite client \
--endpoint https://<REGION>.cloud.appwrite.io/v1 \
--project-id <PROJECT_ID> \
--key <API_KEY>
Then deploy non-interactively:
# Push all sites
appwrite push sites --all --force
# Push a specific site
appwrite push sites --site-id <SITE_ID> --force
Site Management Commands
| Command | Description |
|---|---|
appwrite sites list |
List all sites in the project |
appwrite sites create |
Create a new site |
appwrite sites get --site-id <ID> |
Get a site by ID |
appwrite sites update --site-id <ID> |
Update a site |
appwrite sites delete --site-id <ID> |
Delete a site |
appwrite sites list-frameworks |
List available frameworks |
appwrite sites list-specifications |
List allowed site specifications |
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.
- yesterday First seen · 140 lines · 11 tokens per session scan A bec6d656edaa
deploy-site is a command published in the GitHub repository appwrite/claude-plugin (10 stars, last pushed 13d ago), licensed BSD-3-Clause. It adds 11 tokens to every session and 992 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.