원클릭으로
recall
Search Wenlan's local memory from Codex by query. Targeted lookup, not session orientation. Invoked as /recall <query>.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Search Wenlan's local memory from Codex by query. Targeted lookup, not session orientation. Invoked as /recall <query>.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Frictionless Wenlan setup for Codex. Detects a missing local runtime, installs or repairs it, and verifies the plugin to MCP to local runtime round-trip. Run when the user says "set up wenlan", "is wenlan working", or "fix wenlan".
Frictionless setup. Detects a missing local runtime, installs or repairs it, configures local memory, and verifies the full plugin -> MCP -> local runtime round-trip. Run after `/plugin install wenlan@7xuanlu-wenlan`, or any time the user says "set up wenlan", "is wenlan working", "fix wenlan".
Show a one-screen Codex reference for the Wenlan plugin. Use when the user asks for Wenlan help, command list, or invokes /help.
Run Wenlan diagnostics or resolve every finding into a ready repair, review item, system action, or blocker.
One-screen quick reference for the Wenlan plugin. Lists the daily verbs, the daily flow, where data lives, and how to view it without a GUI. Use when the user says "help", "what can I do", "list wenlan commands", "how do I use wenlan", or invokes `/help`.
Run Wenlan diagnostics or resolve every finding into a ready repair, review item, system action, or blocker.
| name | recall |
| description | Search Wenlan's local memory from Codex by query. Targeted lookup, not session orientation. Invoked as /recall <query>. |
| argument-hint | <query> |
| allowed-tools | ["Bash","mcp__wenlan__recall"] |
| user-invocable | true |
Search Wenlan memory by natural-language query. Use /brief for broad session
orientation and /recall for a specific fact, decision, lesson, or preference.
Accept one optional inline token of the form space:<name> anywhere in the
argument string. Extract it before treating the rest as the query:
raw_args="<the full argument string passed to /recall>"
space_arg="$(printf '%s\n' "$raw_args" | grep -oE 'space:[A-Za-z0-9_-]+' | head -1 | cut -d: -f2)"
query="$(printf '%s\n' "$raw_args" | sed -E 's/[[:space:]]*space:[A-Za-z0-9_-]+[[:space:]]*/ /g' | sed -E 's/^[[:space:]]+|[[:space:]]+$//g')"
If query is empty, ask the user what they want to search for.
Call the Codex resolver:
resolved="$(plugin-codex/bin/resolve-space.sh --cwd "$PWD" ${space_arg:+--arg "$space_arg"} --topic "$query" 2>/dev/null)"
space="$(printf '%s\n' "$resolved" | cut -f1)"
source_layer="$(printf '%s\n' "$resolved" | cut -f2)"
If space is non-empty, print:
Resolved space: <space> (from <source-layer>)
If space is empty, print:
Resolved space: none (unscoped)
Pass space="<resolved>" to mcp__wenlan__recall only when space is
non-empty. Do not substitute personal for an unscoped result.
Rewrite the query only enough to improve retrieval:
Do not issue multiple recall calls. Use one call:
mcp__wenlan__recall(
query="<expanded query>",
space="<resolved if non-empty>",
memory_type="<only if the query names a type>"
)
Infer memory_type only when the user names a type, such as "decision on X",
"lesson about Y", or "preference for Z". Otherwise omit it.
Rerank the returned memories against the user's original query:
Render revision context only when it matters:
<id> v<N> (merged <K> memories)
<id> v<N>, pending revision against <id>
<id> v<N> - <last_delta_summary>
<id> v<N>
Skip that tag line when the memory is a fresh v1 with no merge or pending revision fields.
/brief./capture.