Statelock: Deterministic guardrails for browser agents, enforced at CDP

No. 146 of 245 · GitHub · published 23 Oct 2026, 16:59 UTC · 34 min read

Programming & dev tools
AI & machine learning
Security
New project

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

Statelock is a Chrome DevTools Protocol proxy that sits between an AI browser agent and headless Chromium, checking each click, keystroke, upload or download against a user-written policy before it reaches the page, and checking post-conditions after commit actions. Every decision is recorded as evidence.

Read the original at github.com. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.64total under rubric v2.0

Significance0.53
Reader interest0.70
Audience breadth0.40
Practical relevance0.79
Substantiated0.79
Technical depth0.93
New information0.92
Counts against: Promotional0.14
Counts against: Overclaim0.24

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.62	0.30	0.66	0.53	0.36	+0.25	+0.132
Reader interest	0.74	0.50	0.86	0.70	0.36	+0.20	+0.140
Audience breadth	0.37	0.25	0.58	0.40	0.33	+0.10	+0.040
Practical relevance	0.87	0.70	0.80	0.79	0.17	+0.15	+0.119
Substantiated	0.96	0.60	0.82	0.79	0.36	+0.10	+0.079
Technical depth	1.00	0.85	0.94	0.93	0.15	+0.10	+0.093
New information	0.92	0.85	0.98	0.92	0.13	+0.10	+0.092
Promotional	0.04	0.25	0.12	0.14	0.21	−0.15	−0.021
Overclaim	0.18	0.35	0.18	0.24	0.17	−0.15	−0.036
Sum of contributions							+0.639
Claim-check penalty							0.000
Total, as published							0.639

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.