Skip to main content

bm-orient

Orient Claude from Basic Memory before substantial repo work by reading active tasks, open decisions, recent checkpoints, and repo conventions. Use when resuming old work or when the user asks where things stand.

Datos de origen

Repositorio
basicmachines-co/basic-memory
Última actividad en el origen
24 de octubre de 2026 a las 17:18
Idioma detectado de SKILL.md
inglés
Estrellas
4494
Forks
350

Opciones de instalación

De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.

Revisa los archivos de origen

Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.

Mostrando SKILL.md

SKILL.md
Instrucciones de origen · Vista previa de solo lectura
name
bm-orient
description
Orient Claude from Basic Memory before substantial repo work by reading active tasks, open decisions, recent checkpoints, and repo conventions. Use when resuming old work or when the user asks where things stand.
argument-hint
(no arguments — reads the graph and summarizes)
# Orient From Basic Memory Use this before substantial work in a repo, before resuming an old thread, or when the user asks where things stand. The SessionStart hook already briefs the start of a session; this is the deliberate mid-session version with deeper reads. ## Steps 1. Resolve config: read the `basicMemory` block with the same precedence the hooks use. For the user-level base, append `settings.json` to the literal value of `CLAUDE_CONFIG_DIR` when that environment variable is present; do not trim it, expand `~`, or treat an empty value as unset. Use `~/.claude/settings.json` only when the variable is absent. Then the project's `.claude/settings.json` and `.claude/settings.local.json` override it per key. Use `primaryProject`, `secondaryProjects`, `recallTimeframe`, `sessionProfile`, `repository`, and `placementConventions`. If no config is present, continue against the default Basic Memory project and mention that setup has not been run. Scope queries to `primaryProject` by passing it as `project`, including when it is an `external_id` UUID. 2. Query the primary project with `bm_search`: - active tasks: `filters={"type": "task", "status": "active"}` - open decisions: `filters={"type": "decision", "status": "open"}` - recent sessions: `filters={"type": "session"}`, with `since=<recallTimeframe>` - recent coding sessions: `filters={"type": "coding_session", "repository": "<configured repository>"}`, with `since=<recallTimeframe>`, when `sessionProfile` is `coding` Always query `"type": "session"`; include `"type": "coding_session"` for a coding profile only with the configured `repository` metadata filter. Never run an unscoped coding-session query; if the repository is missing, report that setup is incomplete. Merge and deduplicate the results, sort them newest first, and prefer the highest-signal checkpoint regardless of which producer wrote it. `coding_session` carries schema-required, queryable Git context; `session` covers general checkpoints and PreCompact captures. Do not query lifecycle trace: `bm hook flush` archives it locally rather than promoting it into the graph. 3. Query configured `secondaryProjects` read-only for open decisions. Do not write to shared projects during orientation. 4. Read the highest-signal hits before summarizing. Prefer notes that match the current repository, branch, Git SHA, pull request, named route, issue, or file path. For coding sessions, use structured metadata filters before text search. 5. Present a compact orientation: - active work - decisions that constrain the next move - recent checkpoint cursor - likely next action - any missing setup or ambiguous project mapping Keep the summary evidence-backed. Include permalinks for notes you rely on.
Ver en GitHub