A set of project instructions for building SkyFi MCP Server, which gives AI agents access to SkyFi satellite imagery. It covers a TypeScript server, a Python demo agent, documentation, tests, and deployment code in a monorepo—a repository containing multiple related projects.

Use it when developing, documenting, testing, or deploying this SkyFi satellite-imagery integration.

It gives developers a shared structure and technical decisions for implementing and testing the server.

How seeincodes/skyfi-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to seeincodes/skyfi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/seeincodes/skyfi-mcp/main/.agents/skills/find-skills/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/seeincodes/skyfi-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/seeincodes/skyfi-mcp/find-skills/github.svg)](https://agentmods.dev/skills/seeincodes/skyfi-mcp/find-skills)

Your own site

<a href="https://agentmods.dev/skills/seeincodes/skyfi-mcp/find-skills"><img src="https://agentmods.dev/badge/skills/seeincodes/skyfi-mcp/find-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/seeincodes/skyfi-mcp/find-skills"><img src="https://agentmods.dev/badge/skills/seeincodes/skyfi-mcp/find-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 574 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00574
Opus 5.5	$0.00000	$0.00230
Sonnet 5.5	$0.00000	$0.00115
Haiku 4.5	$0.00000	$0.00057

Measured 2mo ago against content hash 8232a8f3ab7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

find-skills 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 2mo 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.

.agents/skills/find-skills/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: find-skills

Context

SkyFi MCP Server — a production-grade MCP server wrapping SkyFi's satellite imagery platform for AI agent access.

Codebase

Target: TypeScript MCP server + Python demo agent
Structure: Monorepo with src/ (server), examples/demo-agent/ (Python), docs/ (documentation), tests/, infra/

Stack

TypeScript 5.x / Node.js 20 LTS / Cloudflare Workers
@modelcontextprotocol/sdk (MCP protocol)
Hono 4.x (HTTP framework, Workers-native)
Zod 3.x (validation + JSON Schema derivation)
Vitest (testing)
tsup (bundling)
Nominatim/OSM (geocoding)
Cloudflare Workers KV (ephemeral stores: idempotency, rate limits, quotes)
Prometheus + Grafana (self-hosted observability)
Python + Google ADK (demo agent)

Key Files

skyfi-mcp-prd.md — Original detailed PRD from SkyFi
docs/PRD.md — Condensed product requirements
docs/TASK_LIST.md — Phased implementation tasks with checklists
docs/TECH_STACK.md — Technology decisions, architecture diagram, env vars, schema
docs/USER_FLOW.md — User journey, API request/response examples
docs/MEMO.md — Architecture decisions with rationale and rejected alternatives
docs/ERROR_FIX_LOG.md — Error tracking log with category prefixes
docs/skill-lifecycle.yml — Skill lifecycle configuration

Processing Strategy

Request → Auth (header/config) → Abuse Protection → Input Validation → Simulation Engine → Pre-Auth Policy → Idempotency Store → Tool Handler → SkyFi API/Nominatim → Response Envelope → Transport (STDIO/HTTP+SSE)

Known Patterns

Two-step confirmation: quote_* → user confirms → execute_* (server-side enforced)
Standard response envelope on ALL tools: { status, tool, version, simulated, data, meta, warnings }
Simulation mode: simulate: true flag or SKYFI_SIMULATE=true env var
Idempotency keys required on all execute_* tools (24h TTL)
AOI area guardrails enforced before any API call
Credentials never stored server-side (stateless design)
Tool descriptions are product copy, not boilerplate (LLM-facing, preconditions documented)

Read the full file on GitHub · 48 lines

Files

What ships with it

2 files 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.

Changes

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.

2mo ago First seen · 48 lines · 0 tokens per session scan A 8232a8f3ab7e

Subscribe to this mod's changes

find-skills is a skill published in the GitHub repository seeincodes/skyfi-mcp (0 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. 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.

ai-agents cloudflare-workers geospatial mcp satellite-imagery skyfi

find-skills next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
find-skillsseeincodes/skyfi-mcp	Skill	0	7mo ago	MIT	A	0	Claude Code, Codex
arcgis-to-portaljsdatopian/portaljs	Skill	2.4k	9d ago	MIT	A	134	Claude Code
edge-commercefinsilabs/awesome-ecommerce-skills	Skill	63	15d ago	MIT	A	30	Claude Code, Codex
movement-trajectorymuend/geoai-skills	Skill	43	21d ago	MIT	A	118	Claude Code, Codex
review-stacklouisbrulenaudet/monorepo-template	Skill	19	5d ago	Apache-2.0	A	115	Claude Code, Codex
spatialiteznlgis/opengis-skills	Skill	76	10d ago	MIT	B	115	Claude Code, Codex
ae-ltd-context7-radaraegntic/cldcde	Skill	11	2d ago	MIT	A	42	Codex

skyfi-mcp: Skill for Claude Code