Borrowing it
Nothing to install: this file belongs to kruchenburger/another-s3-manager. 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/kruchenburger/another-s3-manager/main/AGENTS.mdgit clone --depth 1 https://github.com/kruchenburger/another-s3-managerWrote 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/kruchenburger/another-s3-manager/agents-md)<a href="https://agentmods.dev/instructions/kruchenburger/another-s3-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/kruchenburger/another-s3-manager/agents-md/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/instructions/kruchenburger/another-s3-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/kruchenburger/another-s3-manager/agents-md.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 | $0.06093 | $0.06093 |
| Opus 5.5 | $0.02437 | $0.02437 |
| Sonnet 5.5 | $0.01219 | $0.01219 |
| Haiku 4.5 | $0.00609 | $0.00609 |
Grade A, and why
another-s3-manager 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 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.
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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project instructions
This file is the canonical project guide shared by Claude Code and Codex. When this repository is checked out inside the workspace, a session started directly here must, before planning or editing, read the workspace root guide and every applicable document in the neutral contract directory completely. Those shared project obligations remain applicable, but the full workspace harness (MCP, hooks, roles, and skills) is guaranteed only for sessions started from the workspace root. In a standalone clone where that parent workspace is absent, this guide remains self-contained and workspace extras are unavailable. Start from the workspace root when shared tooling is required.
Another S3 Manager
Lightweight web UI for managing files in S3 and S3-compatible storage.
This is a public repository. Never commit, push, or include in PR descriptions / commit messages / issue bodies any absolute paths from a developer's local filesystem (e.g.
D:\...,/Users/...,C:\...,/home/...). Specs and plans for this project live out-of-repo per the shared workspace specs-and-plans contract — when referencing them in a PR description, use only the relative tail (e.g.specs/2026-05-02-foo-design.md (out-of-repo)), never the full absolute path. Personal directory structure leaking into a public repo is a privacy issue and looks unprofessional.
Stack
- Backend: Python 3.13+, FastAPI, Boto3, JWT auth (cookie-based), per-username ban for brute-force defense
- Frontend: React + Mantine (Vite); FastAPI serves the built SPA at
/ - Deployment: Docker, Docker Compose, Kubernetes (chart hosted at github.com/kruchenburger/helm — in progress)
- Package manager: uv
Structure
another-s3-manager/
├── src/
│ └── another_s3_manager/
│ ├── __init__.py
│ ├── main.py # FastAPI app, API endpoints
│ ├── auth.py # JWT auth, CSRF, ban logic
│ ├── config.py # Config management (config.json)
│ ├── constants.py # App constants, paths
│ ├── database.py # SQLAlchemy engine + session_scope()
│ ├── models.py # ORM models (User, Role, Ban)
│ ├── s3_client.py # S3 client, role management
│ ├── users.py # User management (SQLite via SQLAlchemy)
│ ├── utils.py # Validation, sanitization
│ └── static/app/ # React SPA build output (generated, not tracked)
├── migrations/ # Alembic migrations (env.py + versions/)
├── alembic.ini
├── tests/ # pytest tests
├── frontend/ # React + Mantine source
├── data/ # Runtime data (not tracked)
├── pyproject.toml
├── Dockerfile
├── docker-compose.yml
└── uv.lock
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 · 332 lines · 6,093 tokens per session scan A e8f93456ba84
another-s3-manager AGENTS.md is an instructions file published in the GitHub repository kruchenburger/another-s3-manager (6 stars, last pushed 8d ago), licensed MIT. It adds 6,093 tokens to every session, about $0.0244 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 2026-10-29.
another-s3-manager AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| another-s3-manager AGENTS.mdkruchenburger/another-s3-manager | Instructions file | 6 | 8d ago | MIT | A | 6,093 | Codex, OpenCode |
| plan-forge dapr.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 4,975 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |