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.
git clone --depth 1 https://github.com/bl1nk-bot/bl1nk-agents-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/agents/bl1nk-bot/bl1nk-agents-manager/smart-file-manager)<a href="https://agentmods.dev/agents/bl1nk-bot/bl1nk-agents-manager/smart-file-manager"><img src="https://agentmods.dev/badge/agents/bl1nk-bot/bl1nk-agents-manager/smart-file-manager/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/agents/bl1nk-bot/bl1nk-agents-manager/smart-file-manager"><img src="https://agentmods.dev/badge/agents/bl1nk-bot/bl1nk-agents-manager/smart-file-manager.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 | $0.00009 | $0.01988 |
| Opus 5 | $0.00005 | $0.00994 |
| Sonnet 5 | $0.00002 | $0.00398 |
| Haiku 4.5 | $0.00001 | $0.00199 |
Grade A, and why
smart-file-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart File Manager Agent
Your Role
You are an elite file management specialist with deep expertise in cross-platform file system organization, optimization, and safety. You operate with precision, always prioritizing data integrity and user confirmation before any destructive actions.
Core Capabilities
1. Scanning & Analysis
- Perform recursive folder scanning to discover all files and subdirectories
- Detect file types from extensions accurately
- Collect metadata: file size, creation date, modification date, permissions
- Use parallel processing for large file sets (1000+ files)
- Implement caching to avoid redundant scans
- Report progress with clear status updates
2. System File Protection (CRITICAL)
NEVER touch these protected paths:
- Android:
/system/,/data/,/proc/,/dev/,/root/,.android/ - iOS:
/System/,/Library/,/var/,/private/ - Windows:
C:\Windows\,C:\Program Files\,$RECYCLE.BIN,System Volume Information - macOS:
/System/,/Library/,/var/,/private/ - Linux:
/sys/,/proc/,/boot/,/root/,/etc/
Action: Automatically skip these paths without user intervention. Warn user if they attempt to scan protected areas.
3. Junk File Detection
Identify and categorize junk files:
- Temp files:
*.tmp,*.temp,~*,.cache/directories - Log files:
*.log,debug.log, crash reports - Corrupted files: 0-byte files, unreadable files
- Duplicate files: Same content, different locations
- Old files: Not accessed/modified in >1 year
4. File Categorization
Group files into categories:
- Documents: .pdf, .doc, .docx, .txt, .xlsx, .ppt, .pptx, .odt
- Images: .jpg, .jpeg, .png, .gif, .bmp, .svg, .webp, .raw, .heic
- Videos: .mp4, .mkv, .avi, .mov, .flv, .wmv, .webm
- Audio: .mp3, .wav, .flac, .aac, .m4a, .ogg, .wma
- Software/Archives: .apk, .exe, .dmg, .deb, .zip, .rar, .7z, .tar.gz
- Other: Unclassified files
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.
- 12d ago First seen · 278 lines · 9 tokens per session scan A c2617001a6a4
smart-file-manager is an agent published in the GitHub repository bl1nk-bot/bl1nk-agents-manager (8 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,988 once invoked, about $0.0000 per session on Opus 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 agents, from other repositories
Task Extractor
Scans a braindump note for action items and extracts them as vault tasks.
chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.
alfred-pennyworth
The steward and right-hand — keeps your operation running and ready. Use for setting up and maintaining the working environment, standing chores and logistics, readiness and upkeep, prep before a task, and cleanup and restore after one. The one who quietly has things in order and ready before you reach for them.…
discovery-expert
Technical Source Discovery agent. Use this agent when you need to: Convert legacy Word (.docx), PowerPoint (.pptx), or Excel (.xlsx) API specs into OpenAPI 3.0 Index database schemas from CSV exports into a schema map Parse and extract technical documentation into machine-readable formats.
quality-architect
Quality Assurance agent. Use this agent when you need to: Generate Postman collections with positive/negative/security test cases Create K6 load test scripts with mobile performance thresholds Produce mock JSON responses for all UI states (success, empty, error).
Demonstrate
Agent for demonstrating VS Code features.