
Specstory Link Trail
If you've ever wondered what documentation or APIs Claude actually fetched during a coding session, this parses your SpecStory history files and gives you a clean audit trail. It groups URLs by session, shows fetch counts for repeated accesses, and separates successful fetches from failures with status codes. Handy when you need to find that API doc you saw earlier or understand what external resources were touched. The output includes a domain summary so you can see at a glance where most requests went. Built by SpecStory themselves, so it hooks directly into their history format without any setup.
- skills.sh installs
- 254
- GitHub stars
- 35
- last updated
- Aug 21, 2026
Install
$ npx -y skills add specstoryai/agent-skills --skill specstory-link-trail --agent claude-codeInstalls into .claude/skills of the current project.
Files
SpecStory Link Trail
Reviews your .specstory/history sessions and creates a summary of all URLs that were fetched via WebFetch tool calls. Useful for auditing external resources accessed during development.
How It Works
- Parses SpecStory history files for WebFetch tool calls
- Extracts URLs, status codes, and context
- Groups by session with timestamps
- Separates successful fetches from failures
- Deduplicates repeated URLs with fetch counts
Why Track Links?
During AI-assisted coding, your assistant fetches documentation, APIs, and resources on your behalf. Link Trail helps you:
- Audit what external resources were accessed
- Find that documentation page you saw earlier
- Review failed fetches that might need retry
- Understand your research patterns
Usage
Slash Command
| User says | Script behavior |
|---|---|
/specstory-link-trail | All sessions in history |
/specstory-link-trail today | Today's sessions only |
/specstory-link-trail last session | Most recent session |
/specstory-link-trail 2026-01-22 | Sessions from specific date |
/specstory-link-trail *.md | Custom glob pattern |
Sponsors
Details
- Repository
- github.com/specstoryai/agent-skills
- Category
- AI & Agent Building
- First seen
- Jun 3, 2026