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 besoeasy/open-skills --skill file-trackergit clone --depth 1 https://github.com/besoeasy/open-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/besoeasy/open-skills/file-tracker)<a href="https://agentmods.dev/skills/besoeasy/open-skills/file-tracker"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/file-tracker/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/besoeasy/open-skills/file-tracker"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/file-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 505 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Rogue Agent · line 28 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00061 | $0.03706 |
| Opus 5 | $0.00030 | $0.01853 |
| Sonnet 5 | $0.00012 | $0.00741 |
| Haiku 4.5 | $0.00006 | $0.00371 |
Grade A, and why
file-tracker 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 10d 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 — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Tracker
Log every file change (write, edit, delete) to a SQLite database for debugging, audit trails, and version history tracking. Works with any file operation system or code editor.
When to use
- Tracking file modifications during development
- Creating audit trails for file changes
- Debugging what files were modified and when
- Building version history without git
- User asks to track or review file changes
Required tools / APIs
- Python standard library (sqlite3, datetime, os)
- Any programming language with SQLite support
No external APIs or services required.
Database Schema
CREATE TABLE IF NOT EXISTS file_changes (
id INTEGER PRIMARY KEY AUTOINCREMENT,
timestamp TEXT NOT NULL,
action TEXT NOT NULL, -- 'write', 'edit', 'delete', 'rename'
file_path TEXT NOT NULL,
old_content TEXT, -- for edits/deletes
new_content TEXT, -- for writes/edits
file_size INTEGER, -- size in bytes
metadata TEXT, -- JSON: user, session_id, etc.
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE INDEX idx_file_path ON file_changes(file_path);
CREATE INDEX idx_timestamp ON file_changes(timestamp);
CREATE INDEX idx_action ON file_changes(action);
-- Automatic purge: delete records older than 1 year
DELETE FROM file_changes WHERE created_at < datetime('now', '-1 year');
Fields:
id- Auto-incrementing primary keytimestamp- ISO 8601 timestamp of the changeaction- Type of operation: 'write', 'edit', 'delete', 'rename'file_path- Absolute or relative path to the fileold_content- Previous content (for edits) or deleted content (for deletes)new_content- New content (for writes/edits)file_size- File size in bytes after operationmetadata- JSON field for additional context (user, session, tools)created_at- Database insertion timestamp
Basic Implementation
Python
Initialize database:
import sqlite3
from datetime import datetime
from pathlib import Path
import json
import os
# Configure database path (customize as needed)
DB_PATH = Path.home() / ".file_tracker" / "changes.db"
def init_db():
"""Initialize database and create tables."""
DB_PATH.parent.mkdir(parents=True, exist_ok=True)
conn = sqlite3.connect(str(DB_PATH))
conn.execute("""
CREATE TABLE IF NOT EXISTS file_changes (
id INTEGER PRIMARY KEY AUTOINCREMENT,
timestamp TEXT NOT NULL,
action TEXT NOT NULL,
file_path TEXT NOT NULL,
old_content TEXT,
new_content TEXT,
file_size INTEGER,
metadata TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
)
""")
conn.execute("CREATE INDEX IF NOT EXISTS idx_file_path ON file_changes(file_path)")
conn.execute("CREATE INDEX IF NOT EXISTS idx_timestamp ON file_changes(timestamp)")
conn.execute("CREATE INDEX IF NOT EXISTS idx_action ON file_changes(action)")
conn.commit()
conn.close()
def purge_old_changes():
"""Delete file change records older than 1 year to keep the database size sane."""
conn = sqlite3.connect(str(DB_PATH))
conn.execute("DELETE FROM file_changes WHERE created_at < datetime('now', '-1 year')")
conn.commit()
conn.close()
# Initialize on import and purge old records
init_db()
purge_old_changes()
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.
- 10d ago First seen · 507 lines · 61 tokens per session scan A ac7a845719e7
file-tracker is a skill published in the GitHub repository besoeasy/open-skills (132 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 3,706 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
langbot-plugin-dev
Develop, debug, and test LangBot plugins. Use when creating new LangBot plugins, fixing plugin bugs, setting up a LangBot test environment, or testing plugins via WebSocket. Covers plugin component architecture (EventListener, Command, Tool), the plugin SDK API (invokellm, getllmmodels, sendmessage, plugin storage)…
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
node-connect
Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale…
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
ax-cpp-agent-observability
Use when writing C++ code with axllm for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
ax-go-agent-observability
Use when writing Go code with github.com/ax-llm/ax/packages/go for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.