Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Command
Part of presence
Bundle install verify + doctor report + recent warnings + state sizes into a paste-friendly markdown blob for filing issues at https://github.com/sara-star-quant/presence/issues. Read-only.
Command
Part of presence
Compress the project model. Invokes the model-curator subagent to consolidate observations in model.md into a tighter form.
Command
Part of presence
Show presence diagnostic report. Active preset, warnings, error counts, state sizes, integrity status. Run this when something seems off.
Command
Part of presence
List or switch presence presets. Run with no args to list; with "use " to activate.
Command
Part of presence
Wipe presence state for the current project, all projects, or specific subsystems. Asks for confirmation before destructive action.
Command
Part of presence
Quick presence status. Active preset, current repo id, model size, recent reverts. Pass --zerotrust for the full Zero-Trust controls checklist.
Command
Part of presence
Temporarily allow settings.json writes under the zerotrust preset. Creates a 60-second unlock window. Outside zerotrust, settings are always writable and this command is a no-op.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: