file-tracker

file-tracker is a skill for Claude Code, Codex from besoeasy/open-skills. It costs 61 tokens per session (3,706 once invoked), scanned A, original, MIT.

A file-change tracker that records writes, edits, deletes, and renames in a SQLite database. SQLite is a small database stored in a file.

In plain words
What is it for?
Use it to track development changes, investigate bugs, review file history, and audit modifications outside Git.
Why use it?
It provides an audit trail showing which files changed, what their contents were, and when the changes happened.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to track development changes, investigate bugs, review file history, and audit modifications outside Git.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/besoeasy/open-skills/file-tracker
Install

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.

Any agent
npx skills add besoeasy/open-skills --skill file-tracker
Clone the repo
git clone --depth 1 https://github.com/besoeasy/open-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for file-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/besoeasy/open-skills/file-tracker/github.svg)](https://agentmods.dev/skills/besoeasy/open-skills/file-tracker)
Your own site
<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.

agentmods 80×15 button for file-tracker

Your own site · 80×15
<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>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash ac7a845719e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/file-tracker/SKILL.md · 507 lines

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 key
  • timestamp - ISO 8601 timestamp of the change
  • action - Type of operation: 'write', 'edit', 'delete', 'rename'
  • file_path - Absolute or relative path to the file
  • old_content - Previous content (for edits) or deleted content (for deletes)
  • new_content - New content (for writes/edits)
  • file_size - File size in bytes after operation
  • metadata - 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()

Read the full file on GitHub · 507 lines

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.

  1. 10d ago First seen · 507 lines · 61 tokens per session scan A ac7a845719e7

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories