source-tracker

source-tracker is a skill for Claude Code, Codex from moonlight-lupin/agent-skills. It costs 45 tokens per session (2,765 once invoked), scanned A, original, MIT.

A persistent citation manager for research sources. It stores cited web addresses in a portable database, removes duplicate URL variants, checks whether links still work, and exports bibliographies in several common formats.

In plain words
What is it for?
Use it to save and tag sources, deduplicate links, check stale citations, and export references as Markdown, BibTeX, CSV, or JSON.
Why use it?
It prevents sources from being lost across browser tabs, notes, and research sessions, and reduces manual bibliography cleanup.

Skill for Claude CodeCodex

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

Good fit Use it to save and tag sources, deduplicate links, check stale citations, and export references as Markdown, BibTeX, CSV, or JSON.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moonlight-lupin/agent-skills/source-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 moonlight-lupin/agent-skills --skill source-tracker
Clone the repo
git clone --depth 1 https://github.com/moonlight-lupin/agent-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 source-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/source-tracker.svg)](https://agentmods.dev/skills/moonlight-lupin/agent-skills/source-tracker)
Your own site
<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/source-tracker"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/source-tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,765 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.
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 $0.00045 $0.02765
Opus 5 $0.00023 $0.01383
Sonnet 5 $0.00009 $0.00553
Haiku 4.5 $0.00005 $0.00277

Measured 7d ago against content hash 8acd14c78232, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

source-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 7d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/source_db.py, scripts/url_health.py, tests/test_source_db.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

research/source-tracker/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Tracker

Overview

Source Tracker is a small persistent citation manager for research workflows. Research sources often scatter across browser tabs, notes, temporary files, and separate sessions. URLs get cited once and then disappear, duplicates accumulate as http/https or www variants, and bibliography export becomes a manual cleanup job at the end.

This skill fixes that by keeping a portable SQLite database of every cited URL: add sources as soon as they are cited, tag them by topic, deduplicate URL variants, re-check stale links, and export bibliographies in Markdown, BibTeX, CSV, or JSON.

The database path is configurable with --db-path or the SOURCE_TRACKER_DB environment variable. If neither is set, commands use ./sources.db relative to the current working directory.

Quick Start

From the skill directory:

python scripts/source_db.py add --url URL --topic TOPIC

A practical example:

python scripts/source_db.py add \
  --url "https://example.org/report" \
  --topic "battery supply chain" \
  --title "Example Battery Report" \
  --notes "Baseline market-size estimate" \
  --type report

Use a persistent project database when research spans folders or sessions:

export SOURCE_TRACKER_DB="$HOME/research/sources.db"
python scripts/source_db.py add --url "https://example.org" --topic "market scan"

Or pass the path explicitly:

python scripts/source_db.py --db-path "$HOME/research/sources.db" add --url "https://example.org" --topic "market scan"

Workflows

1. Add Sources

Add every URL at the moment it becomes a cited source. Always include a topic. Use a source type when the material is not a normal web page.

python scripts/source_db.py add \
  --url "https://example.com/article#section" \
  --topic "ai regulation" \
  --title "Example Article" \
  --notes "Defines the enforcement timeline" \
  --type news \
  --session-id "research-2026-07-06"

If --title is omitted, the script tries a best-effort GET request and parses <title>. If that fetch fails, the source is still added with a blank title.

Read the full file on GitHub · 359 lines

Files

What ships with it

6 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.

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. 7d ago First seen · 359 lines · 45 tokens per session scan A 8acd14c78232

Subscribe to this mod's changes

source-tracker is a skill published in the GitHub repository moonlight-lupin/agent-skills (53 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,765 once invoked, about $0.0002 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.