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 skills add starfetch-js/starfetch --skill tapgit clone --depth 1 https://github.com/starfetch-js/starfetchWrote 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/skills/starfetch-js/starfetch/tap)<a href="https://agentmods.dev/skills/starfetch-js/starfetch/tap"><img src="https://agentmods.dev/badge/skills/starfetch-js/starfetch/tap/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.
<a href="https://agentmods.dev/skills/starfetch-js/starfetch/tap"><img src="https://agentmods.dev/badge/skills/starfetch-js/starfetch/tap.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00059 | $0.01059 |
| Opus 5.5 | $0.00024 | $0.00424 |
| Sonnet 5.5 | $0.00012 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
tap 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TAP Skill
Use this skill for TAP-family protocol work. Keep project-specific product decisions in the repo's AGENTS.md and planning docs; keep this skill focused on general TAP, ADQL, VOSI, VOTable, UWS, and related IVOA behavior.
Workflow
- Identify which protocol area the task touches: TAP resources, query parameters, VOSI metadata, VOTable results, ADQL, UWS async jobs, output formats, registry discovery, or authentication.
- Read the relevant official spec from the index when exact protocol behavior matters.
- Prefer implementation notes that preserve interoperability over service-specific assumptions.
- Keep Starfetch v1 TAP/ADQL-first unless the active issue explicitly expands scope.
- When behavior is intentionally deferred, name a concrete follow-up instead of leaving the gap implicit.
Spec Index
Use official IVOA documents rather than vendoring large specs locally.
- TAP latest: https://ivoa.net/documents/TAP/
- TAP 1.1 recommendation: https://ivoa.net/documents/TAP/20190927/REC-TAP-1.1.html
- VOSI latest: https://ivoa.net/documents/VOSI/
- VOTable latest: https://ivoa.net/documents/VOTable/
- ADQL latest: https://ivoa.net/documents/ADQL/
- UWS latest: https://ivoa.net/documents/UWS/
- DALI latest: https://ivoa.net/documents/DALI/
- TAPRegExt latest: https://ivoa.net/documents/TAPRegExt/
- RegTAP latest: https://ivoa.net/documents/RegTAP/
When a task depends on a precise requirement, use the versioned recommendation linked from the official "latest" page and cite the exact source in the response or implementation note.
TAP Checklist
For TAP query execution:
- resolve the TAP base URL before building child resources;
- use
/syncfor synchronous queries and/asyncfor UWS jobs; - default
LANG=ADQL; - send query text as
QUERY; - prefer
RESPONSEFORMATfor requested output; - avoid obsolete TAP 1.0-era request patterns unless compatibility handling is explicitly needed;
- treat VOTable as the baseline result format.
For TAP parameters:
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.
- 1mo ago First seen · 100 lines · 59 tokens per session scan A 32d8447ee755
tap is a skill published in the GitHub repository starfetch-js/starfetch (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,059 once invoked, about $0.0002 per session on Opus 5.5. 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
openephemeris
This skill should be used when a user asks for astrology or astronomical chart calculations — natal charts, transits, synastry/compatibility, progressions, solar/lunar returns, eclipses, moon phases, electional (auspicious-timing) astrology, Human Design, Vedic/Jyotish, Chinese BaZi, astrocartography, or chart…
openephemeris-setup
Install and configure the OpenEphemeris MCP server. Use when a user wants to set up OpenEphemeris, get an API key, troubleshoot installation, or connect Claude / Cursor / Windsurf / ChatGPT to the planetary calculation API.
openephemeris-api-reference
Complete endpoint reference for the 121 OpenEphemeris API endpoints. Use when you need to find the exact endpoint, parameter, or path for an astronomical or astrological computation, or when other skills haven't covered the calculation a user is asking for.
pilot-service-agents-space
Space and astronomy — NASA Astronomy Picture of the Day, Open Notify astronauts. Use this skill when: 1. Fetching APOD metadata + media URLs for a given date 2. Listing who is currently in space (Open Notify) Do NOT use this skill when: - Satellite TLEs / orbital mechanics (not yet in catalogue) - Weather / climate…
stellar-structure-and-evolution
Stellar structure and life cycles from birth to endpoint. Covers the Hertzsprung-Russell diagram, hydrostatic equilibrium, main-sequence physics and the mass-luminosity relation, nuclear fusion stages (pp-chain, CNO cycle, triple-alpha), nucleosynthesis, post-main-sequence evolution through red giants and the…
cosmological-observation
Observational cosmology from Hubble's law to the CMB. Covers redshift, Hubble expansion, the cosmological parameters, the cosmic microwave background, large-scale structure, galaxy rotation curves and dark matter, Type Ia SNe and dark energy, and the current state of Lambda-CDM. Use when reasoning about the…