ambient-hud
Skill1 starsChanged 33 days agoMITView on GitHub
Instructions for the upstream ambient-status-v1 Windows overlay and its scoped metrics. Use to plan passive token and routing visibility outside the terminal. Requires a separately installed compatible runtime and valid local ledgers; missing measurements stay unavailable.
In this repository114 other files it gives its agents.
- agent-cacheSkill
- agent-compressionSkill
- agent-intelSkill
- agent-overlapSkill
- agent-stateSkill
- app-testSkill
- audit-dagSkill
- auto-distillSkill
- auto-memorySkill
- auto-routerSkill
- benchSkill
- bootstrapSkill
- botte-learnSkill
- botte-nnSkill
- botte-proxySkill
- botte-wrapSkill
- cacheSkill
- call-chainsSkill
- capabilitiesSkill
- cardinalSkill
- checkupSkill
- clarificationSkill
- clusterSkill
- code-complexitySkill
- code-duplicationSkill
- code-fingerprintSkill
- code-rulesSkill
- code-stateSkill
- code-wrappersSkill
- comfyuiSkill
- completion-proofSkill
- conductorSkill
- context-budgetSkill
- context-compressorSkill
- context-profilerSkill
- context-slicerSkill
- context-windowsSkill
- control-loopSkill
- cost-estimatorSkill
- dag-optimizerSkill
- dashboardSkill
- decision-ladderSkill
- demoSkill
- diff-languageSkill
- directives-auditSkill
- docgenSkill
- docs-stewardSkill
- dynamic-workflowsSkill
- efficiencySkill
- eventsSkill
- fallow-likeSkill
- fallowSkill
- fast-contextSkill
- fixSkill
- fleetSkill
- hailo-visionSkill
- harness-deltaSkill
- harvestSkill
- hermes-bridgeSkill
- hermes-second-brainSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Never exposes project paths in the window.
- Distinctive: line 48
No launch-at-login or automatic startup.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ambient HUD
Package scope and prerequisites
This catalog ships instructions, not the executable runtime. Python modules, scripts, local services and optional tools named below must be installed separately from the upstream project. Check their availability before running commands; if they are missing, explain the prerequisite instead of claiming execution or results. The host agent may use model tokens while following these instructions.
Commands, APIs and runtime behavior described below are conditional examples for a compatible upstream installation; they are not evidence of execution in this package.
Open the read-only top-center overlay manually:
python -m skills.ambient_hud .The collapsed line shows host token savings beside project-local/cloud routes.
Click the bar or title to expand the rich dark card with model tier chips,
local/cloud ratio bar, detailed metric tiles (LOCAL, CLOUD, CACHE, ESCALATE),
and success/escalation rates.
Drag anywhere on the header or title bar to reposition the floating widget anywhere
on your screen. Click 📊 Full Report (or press R / D) to generate and view
the complete project dashboard in your browser. Press Escape or click × to close it.
python -m skills.ambient_hud --interval 10 . # slower local refresh
python -m skills.ambient_hud --monitor cursor . # monitor under mouse (default)
python -m skills.ambient_hud --monitor primary . # explicit primary fallback
python -m skills.ambient_hud --print . # headless one-line previewBoundaries
- The upstream overlay uses
tkinter; opening its full report may launch a browser. Check the separately installed runtime and its dependencies. - Reads
ambient-status-v1directly; it never parses prompts or session text. - Consumes only snapshots accepted by the upstream contract validator.
- Never exposes project paths in the window.
- Missing measurements remain
unavailable; they are not rendered as zero. - Partial or invalid local ledgers degrade one scope without hiding the other.
- No launch-at-login or automatic startup. Opening the HUD is always explicit.
- On Windows, stdlib
ctypesreads the native monitor work area throughGetCursorPos,MonitorFromPoint, andGetMonitorInfoW. Virtual desktop coordinates may be negative. Other systems and API failures fall back to the primary Tk screen. - Monitor selection happens once at launch; the HUD does not follow the mouse.
Related: [[statusline]], [[dashboard]], [[events]], [[control-loop]].
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

