claude

context-map

Two-layer agent docs: a committed agent-docs/ navigation tree (MAP + per-domain deep docs) and a gitignored context-map-<slug>/ memory tree (decisions, known issues, gotchas, tasks). Generate, decompose, update, audit, reconcile, and conflict-check project docs for AI coding agents — navigation that survives a big codebase plus memory that survives a context reset.

0 on GitHubby kyzdesupdated 1 month ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin context-map in kyzdes/context-map-skill. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • context-map

    Build and maintain agent-facing project documentation in two linked layers: a COMMITTED `agent-docs/` navigation tree (a MAP router + per-domain deep docs + optional per-folder CLAUDE.md, so an agent reads only the slice it needs) and a GITIGNORED `context-map-<slug>/` memory tree (decisions, known

Hooks (2)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/auto-update.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/staleness-notice.sh"

View source on GitHub

Maintain context-map?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted