菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Set up the Basic Memory plugin for this project — a short guided interview that configures the project mapping, seeds note schemas, learns or suggests placement conventions, and enables capture reflexes. Use when the user runs /basic-memory:bm-setup, says "set up basic memory", or asks to configure/bootstrap the plugin.
Show the Basic Memory plugin's current state for this project — active project, capture folders, output style, recent session checkpoints, and whether Basic Memory is reachable.
Save a deliberate Codex work checkpoint to Basic Memory with changed files, verification, decisions, blockers, and the next action.
Orient Codex from Basic Memory before substantial repo work by reading active tasks, decisions, recent Codex checkpoints, and repo conventions.
Set up Basic Memory for Codex at user or project level by mapping a Basic Memory project and seeding schemas.
Report the Basic Memory for Codex configuration, reachability, hook expectations, recent Codex checkpoints, and active tasks.
基于 SOC 职业分类
| 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) |
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.
Resolve config: read the basicMemory block with the same precedence the
hooks use — user-level ~/.claude/settings.json as the base, 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, or as project_id if it's an external_id UUID.
Query the primary project with search_notes:
metadata_filters={"type": "task", "status": "active"}metadata_filters={"type": "decision", "status": "open"}metadata_filters={"type": "session"}, after
recallTimeframemetadata_filters={"type": "coding_session", "repository": "<configured repository>"}, after recallTimeframe, when
sessionProfile is codingAlways 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.
Query configured secondaryProjects read-only for open decisions. Do not write
to shared projects during orientation.
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.
Present a compact orientation:
Keep the summary evidence-backed. Include permalinks for notes you rely on.