hacksurvivor

Pathmark

Name: Pathmark
Author: hacksurvivor

AI community

SOURCE https://github.com/hacksurvivor/pathmark

Description

Pathmark — local-first memory for Codex, Claude Code, Gemini CLI, Cursor and MCP agents, created by B2B AI specialist Sergey Moloman.

Installation

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

README

Pathmark

Carry intent across agents without turning stale code facts into hidden memory.

What's New — v0.1.14

Pathmark v0.1.14 fixes scoped conversational recall for conclusions created from workspace evidence:

chat and ask_memory can recover an approved conclusion when the requested workspace:, project:, or namespace: tag is shared by all of its cited evidence, even if the conclusion itself carries only a legacy project tag;
direct conclusion tags remain authoritative, while missing, foreign, mixed-scope, or conclusion-as-evidence provenance cannot grant scope;
exhaustive scoped candidate selection prevents relevant conclusions from disappearing behind unrelated global search results;
batched provenance reads keep scoped chat responsive as evidence sets grow.

See the [v0.1.14 release notes](docs/releases/v0.1.14.md) or the complete [changelog](CHANGELOG.md). The npm badge above always shows the currently published version.

Pathmark local intent and provenance shared by Codex, Claude Code, opencode, and Gemini CLI