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 warith-harchaoui/bucket-helper --skill bucket-helpergit clone --depth 1 https://github.com/warith-harchaoui/bucket-helperWrote 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/warith-harchaoui/bucket-helper/bucket-helper)<a href="https://agentmods.dev/skills/warith-harchaoui/bucket-helper/bucket-helper"><img src="https://agentmods.dev/badge/skills/warith-harchaoui/bucket-helper/bucket-helper/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/warith-harchaoui/bucket-helper/bucket-helper"><img src="https://agentmods.dev/badge/skills/warith-harchaoui/bucket-helper/bucket-helper.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 | $0.00241 | $0.01295 |
| Opus 5.5 | $0.00096 | $0.00518 |
| Sonnet 5.5 | $0.00048 | $0.00259 |
| Haiku 4.5 | $0.00024 | $0.00129 |
Grade A, and why
bucket-helper 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bucket-helper — S3-compatible object storage
bucket-helper moves files between the machine and an S3-compatible bucket.
It is the suite's honest exception to local-first: its whole job is to put
data somewhere else. That somewhere is the endpoint the user configured —
there is no vendor default, no telemetry, no relay.
⚠️ Credentials and destructive calls
- Credentials never live in this skill.
credentials()reads them, in precedence order, from a JSON / YAML config, a.env, then environment variables (viaos_helper.get_config). Keys:s3_access_key,s3_secret_key,s3_bucket,s3_https. - Never print a secret back to the user, never paste one into a command line, and never write one into a file the user did not name.
deleteandmake-bucketchange someone else's storage. Confirm the exact bucket and key with the user before calling them. An upload that overwrites an existing key is destructive too — check withexistsfirst when the key looks like it might already be in use.
Before anything: verify it is installed and configured
bucket-helper --help # argparse CLI (ships with the package)
python -c "import bucket_helper" # library import check
bucket-helper exists SOME_KEY # proves credentials resolve and the endpoint answers
Install:
pip install bucket-helper # core: library + argparse CLI
pip install 'bucket-helper[cli]' # + the click twin
pip install 'bucket-helper[api]' # + FastAPI HTTP surface
pip install 'bucket-helper[mcp]' # + MCP tools over the same app
Configuration starts from the repo's settings.yaml.example — copy it, fill
it in, and keep it out of version control.
What it does, and how to invoke it
| Intent | CLI | Library |
|---|---|---|
| Send a local file up | bucket-helper upload |
upload |
| Bring an object down | bucket-helper download |
download |
| Does this key exist | bucket-helper exists |
exists |
| What is under this prefix | bucket-helper list |
list_prefix |
| Remove an object | bucket-helper delete |
delete |
| Create a bucket | bucket-helper make-bucket |
make_bucket |
| A scratch key on the remote | bucket-helper tempfile |
remote_tempfile |
Split an s3:// URL |
bucket-helper strip-path |
strip_s3_path |
What ships with it
3 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.
- 2d ago First seen · 117 lines · 241 tokens per session scan A dead53471865
bucket-helper is a skill published in the GitHub repository warith-harchaoui/bucket-helper (0 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 241 tokens to every session and 1,295 once invoked, about $0.0010 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 2026-10-18.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…