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 OpenLinkSoftware/ai-agent-skills --skill s3-query-skillgit clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-skillsWrote 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/openlinksoftware/ai-agent-skills/s3-query-skill)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/s3-query-skill"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/s3-query-skill.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 5.1 | $0.00224 | $0.04393 |
| Opus 5 | $0.00112 | $0.02197 |
| Sonnet 5 | $0.00045 | $0.00879 |
| Haiku 4.5 | $0.00022 | $0.00439 |
Grade C, and why
s3-query-skill scanned grade C with 2 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 8d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
# ~/.aws/credentials Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Common Crawl's own [get-started docs](https://commoncrawl.org/get-started) describe `s3://commoncrawl/` as anonymously readable via `--no-sign-request`. Live testing during this skill's build did **not** confirm that — b How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
S3 API Query Client Skill
DuckDB httpfs · AWS CLI / boto3 · rclone · S3-compatible endpoints
Purpose
Act as the client side of the S3 API — read and query data that already lives at an S3 or S3-compatible endpoint, in place, without a bulk download. The skill covers two access modes:
- In-place SQL query — DuckDB's
httpfsextension runsSELECTdirectly against remote Parquet/CSV/JSON objects over the S3 protocol (range requests only pull the bytes a query needs). This is the pattern behind Daniel van Strien's post on querying the 2.1-billion-row Common Crawl Foundation index straight from a laptop, "for $0" — the index is published as an S3-compatible Hugging Face Storage Bucket and queried with DuckDB, no download step. - Object-level operations — list, head, get, put, and sync via AWS CLI / boto3 / rclone, for browsing a bucket or pulling specific objects (e.g. individual WARC/WAT/WET files).
Supported Endpoint Types
| Endpoint type | Example | Auth | Notes |
|---|---|---|---|
| AWS S3 — public/anonymous bucket | s3://commoncrawl/ |
none in theory (--no-sign-request) |
⚠️ Verified 2026-07-02: currently returns 403 on both ListObjectsV2 and GetObject via anonymous/unsigned requests — see the Common Crawl access note below for the working alternative |
| AWS S3 — private bucket | s3://your-bucket/ |
AWS access key/secret or SSO profile | Standard AWS auth chain |
| Hugging Face Storage Buckets | https://s3.hf.co/<namespace> |
HF User Access Token → S3-style key (HFAK…) + secret |
Path-style addressing required; single region us-east-1; ListObjectsV1 unsupported |
| Cloudflare R2 / MinIO / Wasabi / Backblaze B2 / other S3-compatible | custom endpoint_url |
provider-issued key/secret | Same client shape as HF; only endpoint_url + addressing style change |
⚠️ Common Crawl access note (verified live 2026-07-02)
What ships with it
7 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.
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.
- 8d ago First seen · 285 lines · 224 tokens per session scan C d65a47a8add6
s3-query-skill is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed 4d ago), licensed MIT. It adds 224 tokens to every session and 4,393 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.