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 instructions/oscarjpicazo/spacedata/agents-mdgit clone --depth 1 https://github.com/oscarjpicazo/spacedataWrote 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/instructions/oscarjpicazo/spacedata/agents-md)<a href="https://agentmods.dev/instructions/oscarjpicazo/spacedata/agents-md"><img src="https://agentmods.dev/badge/instructions/oscarjpicazo/spacedata/agents-md.svg" alt="Measured on agentmods" 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 | $0.01566 | $0.01566 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
spacedata AGENTS.md 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spacedata
General
AGENTS.mdis the source of truth. AllCLAUDE.mdfiles are references to it — make changes here, not inCLAUDE.md.- Never add
Co-Authored-Byin commits or PR bodies.
Architecture
Bun monorepo (packages/*). One package for now:
| Package | What it does | Stack |
|---|---|---|
cli |
The spacedata command |
TypeScript, commander, Zod, neverthrow, satellite.js (SGP4) |
The MCP server lives inside the cli package (spacedata serve, src/mcp/mcp-server.ts): a lean 15-tool surface over stdio that reuses the source layer verbatim. Tool results carry the same {ok, source, cached, fetchedAt, data} / {ok: false, error} envelopes as the CLI; new sources should be exposed in both surfaces. In serve mode stdout belongs to the MCP transport — never write anything else to it.
Locally computed results (SGP4 position/passes/overhead) are layered: pure math in src/domain/propagation.ts (no I/O, like derive.ts), fetch+compute orchestration in src/compute/, reusing the CelesTrak source. Their envelope uses source: "celestrak+sgp4"; cached/fetchedAt describe the underlying element fetch.
Aggregated reports (spaceweather, aurora, events) fetch several products in parallel; only the core product's failure fails the command — every other section degrades to undefined plus an entry in data.warnings. Their envelope (src/core/aggregate.ts) reports cached: true only when every contributing fetch was cached, and the most recent fetchedAt.
Orbital events combine both patterns. sat events (compute/satellite-events.compute.ts, envelope spacetrack+gfz+analysis): detectors are pure math in domain/events.ts — element jumps against the object's own median/MAD noise floor (drag-detrended, gap-aware), SGP4 propagation residuals (propagationResidualKm in domain/propagation.ts) as corroboration, planetary Kp (GFZ, sources/gfz.source.ts) to separate storms from maneuvers. Events are inferences: they must always carry evidence and confidence, never a bare verdict, and thresholds/heuristics live as named constants with comments. events (compute/orbital-events.compute.ts, envelope spacetrack+launch-library+gfz) is the administrative digest — satcat_debut/satcat_change/TIP/LL2 previous, nothing inferred; grouping/classification helpers are pure in domain/catalog-events.ts. domain/iss-history.fixture.ts is real ISS gp_history (30 days around the 2026-07-02 reboost) and is the detector's ground-truth regression fixture — extend it, don't replace it, when recalibrating.
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.
- 4d ago First seen · 54 lines · 1,566 tokens per session scan A 95fc5fe64a74
spacedata AGENTS.md is an instructions file published in the GitHub repository oscarjpicazo/spacedata (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,566 tokens to every session, about $0.0078 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 instructions, from other repositories
spc copilot-instructions.md
Instructions for putervision/spc, covering state memory (state-memory-mcp), 1. priority order, 2. when to write to the graph, 3. workflow pattern and 4. codebase seeding on initialization.
spc CLAUDE.md
Instructions for putervision/spc, covering state memory (state-memory-mcp), 1. priority order, 2. when to write to the graph, 3. workflow pattern and 4. codebase seeding on initialization.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).