bochen2029-pixel

Glance — Development skill for Claude Code

Development community

The window, as text, as it changes: reads a window through its own accessibility tree, or through pixels and the OS's OCR where there is no tree (Citrix, RDP), and turns every change into one timestam.

How to install Glance

This entry records only its repository, not the path inside it, so there is no exact command to give. Open bochen2029-pixel/glance and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Glance does

The window, as text, as it changes: reads a window through its own accessibility tree, or through pixels and the OS's OCR where there is no tree (Citrix, RDP), and turns every change into one timestamped line, a fact for a clock, or JSON for an agent. Never types, never clicks, never sends a byte. One Windows exe, no network stack, no model. MIT.

Alternatives in Development

  • Evo — turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run 1.4k ★
  • Skill.Color Expert — Agent skill for color science expertise 426 ★
  • Device Control Agent — You are an autonomous macOS agent with full control of this device via two CLI tools: - steer — GUI automation 250 ★

README

glance — the window, as text, as it changes

**Point it at a window. glance reads what is on the screen the way a person does — from the application's own accessibility tree when there is one, from pixels when that is all there is — and turns every change into one line of text with a time on it. It never types, never clicks, never sends a byte anywhere. Its lines are what a coordinator's clock, an agent, or a resident reads next.**

**Status: 0.3.0 — built, `--selftest` green (132 checks), not yet on the tools page.** Stages 0 to 2 work on this box: the UIA reader, the change stream, the strip, the pixel reader (DXGI, tile signatures, Windows OCR), the rules, the facts, the spool, the tape and `--mcp`. Stage 3 was measured on a loaded machine and on a real RDP session, and the one thing it found wrong — recognition running on the capture thread — is fixed: OCR runs on a worker with a queue depth of one per region, and a change's second look is taken from the window's own rendering rather than the next frame. Change-to-line is 18 ms through the tree and 44–183 ms through pixels. Stage 4 (the optional judge, and the second reader a bigger OCR model could be) is untouched. The design is in `docs/BLUEPRINT.md`, the rules in `CLAUDE.md`, the rules-file format in `docs/RULES.md`, the tools-page brief in `docs/DESIGN-BRIEF-tools-page.md`.

One job

It compiles a window into text. The tools page's six house rules are why it stops there: one job; free and MIT; runs beside the work on a strip; keyboard first; built on a loaded machine; the same answer for humans and agents. The vertical adds two more, kept by construction: **nothing leaves the building** (no network stack is linked) and **no hands** (no input injection is linked; the build fails if either appears, and `glance --about` prints the receipt read from its own import table).

Why it exists

On a transplant floor the donor record is a cloud web application the OPO does not control and can