Borrowing it
Nothing to install: this file belongs to cohen-liel/hivemind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cohen-liel/hivemind/main/.claude/skills/s3-file-storage/SKILL.mdgit clone --depth 1 https://github.com/cohen-liel/hivemindWrote 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/cohen-liel/hivemind/s3-file-storage)<a href="https://agentmods.dev/skills/cohen-liel/hivemind/s3-file-storage"><img src="https://agentmods.dev/badge/skills/cohen-liel/hivemind/s3-file-storage/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/cohen-liel/hivemind/s3-file-storage"><img src="https://agentmods.dev/badge/skills/cohen-liel/hivemind/s3-file-storage.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 | $0.00037 | $0.01267 |
| Opus 5 | $0.00018 | $0.00633 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
s3-file-storage scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
await fetch(upload_url, { How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
S3 File Storage Patterns
Setup (boto3 + Python)
# storage.py
import boto3
from botocore.exceptions import ClientError
import uuid, mimetypes
s3 = boto3.client(
"s3",
aws_access_key_id=settings.AWS_ACCESS_KEY_ID,
aws_secret_access_key=settings.AWS_SECRET_ACCESS_KEY,
region_name=settings.AWS_REGION,
# For S3-compatible services (Cloudflare R2, MinIO):
# endpoint_url=settings.S3_ENDPOINT_URL,
)
BUCKET = settings.S3_BUCKET
CDN_URL = settings.CDN_URL # e.g. "https://cdn.example.com"
Upload Patterns
Direct upload from server
async def upload_file(file: UploadFile, folder: str = "uploads") -> str:
"""Upload file, return public URL."""
# Validate
MAX_SIZE = 10 * 1024 * 1024 # 10MB
ALLOWED_TYPES = {"image/jpeg", "image/png", "image/webp", "application/pdf"}
content = await file.read()
if len(content) > MAX_SIZE:
raise ValueError(f"File too large (max {MAX_SIZE // 1024 // 1024}MB)")
if file.content_type not in ALLOWED_TYPES:
raise ValueError(f"File type not allowed: {file.content_type}")
# Generate unique key
ext = mimetypes.guess_extension(file.content_type) or ".bin"
key = f"{folder}/{uuid.uuid4()}{ext}"
s3.put_object(
Bucket=BUCKET,
Key=key,
Body=content,
ContentType=file.content_type,
CacheControl="max-age=31536000", # 1 year cache for immutable files
)
return f"{CDN_URL}/{key}"
Presigned URL (client uploads directly — no server bottleneck)
def generate_upload_url(filename: str, content_type: str, folder: str = "uploads") -> dict:
"""Client uploads directly to S3 — bypasses your server entirely."""
ext = filename.rsplit(".", 1)[-1].lower() if "." in filename else "bin"
key = f"{folder}/{uuid.uuid4()}.{ext}"
url = s3.generate_presigned_url(
"put_object",
Params={
"Bucket": BUCKET,
"Key": key,
"ContentType": content_type,
"ContentLength": 5 * 1024 * 1024, # Max 5MB
},
ExpiresIn=300, # URL valid for 5 minutes
)
return {
"upload_url": url,
"key": key,
"public_url": f"{CDN_URL}/{key}",
}
# FastAPI endpoint
@router.post("/upload-url")
async def get_upload_url(
filename: str = Query(...),
content_type: str = Query(...),
user: User = Depends(get_current_user),
):
return generate_upload_url(filename, content_type, folder=f"users/{user.id}")
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.
- 11d ago First seen · 162 lines · 37 tokens per session scan A 479c6c8a96de
s3-file-storage is a skill published in the GitHub repository cohen-liel/hivemind (107 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,267 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
ring:creating-handoffs
Creating a handoff document that captures session state (completed work, decisions, open items, next steps) and delivering it via Plan Mode so the user gets the native 'clear context and continue implementing' resume option. Use when ending a session, when context grows large, or the user says 'handoff', 'save…
wheypoint
Mark the current conversation as a durable handoff so a new agent can resume the work. Use when the user wants to preserve state for a later or parallel session. Triggers include "hand this off", "write a handoff", "drop a wheypoint", "checkpoint this", "compact the conversation", and "/wheypoint". Also use for "wrap…
incident
Incident response and postmortem generation from git/deploy context. When something breaks in production, this skill builds a timeline, identifies the probable cause, and generates a structured postmortem document. Flags: --since, --service, --sev, --revert, --comms, --dry-run.
presentation
Generate PowerPoint (PPTX) presentations from a topic, outline, or content file. Creates professional slides using python-pptx with consistent theming and typography. Modes: [topic] (from scratch), from [file] (from markdown), --slides N, --theme dark|light|corporate, --outline-only, --out [path], --lang [code].
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…
pr-review-canvas
Create a OpenBitFun Canvas for reviewing a pull request, branch diff, or change set with Cursor-style diff cards, review maps, risk callouts, and focused reviewer flow. Use when the user asks for a PR review canvas, diff walkthrough, change-set overview, or visual review summary.