Observed arrival · 2026-11-12
TXGR maps agent-skill workflows without running them
TXGR lets authors write an agent skill’s workflow in plain text, then maps and checks its declared steps.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People authoring or auditing agent skills
- Worth noticing
- The sample flags a review loop capped at three rounds with no declared exit path.
Field notes
The browser Playground accepts a written or pasted .txg workflow and returns diagnostics, parsed structure, and a token-budget estimate. TXGR Radar takes a skill collection as a ZIP and surfaces draft workflows; Junction identifies files referenced across skills, shared resources, and links needing review. The homepage labels the project v0.2 draft and says tool declarations are descriptive: the compiler does not execute commands or invoke agents.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue