{"definition_raw":"---\nid: claude-mem-value-eval\nname: Weekly claude-mem value evaluation\nschedule: \"0 9 * * 1\"\nenabled: true\ncriticality: low\ntimeout: 1800\nretry: false\nrun_as: shell\nnotify_on: always\nruntime_profile: claude_sonnet_medium\ntags: [memory, evaluation]\ncommand: |\n  cd ~/workspace && timeout -k 30 1500 claude -p 'Weekly claude-mem value evaluation. Decide whether claude-mem still earns its place in the Luci memory stack. Steps: (1) Inspect claude-mem stored data and usage \u2014 look in ~/.claude-mem/ and note how much was captured in the last week and whether it is being queried. (2) Compare against the other memory layers: vault.db plus SecondBrain (knowledge base), file auto-memory at ~/.claude/projects/-home-lucienne-workspace/memory/, and the MC database work-state. (3) Decide whether claude-mem surfaces anything the other layers do not, and whether it is worth running both. Output a short verdict on the first line \u2014 exactly one of KEEP BOTH, CLAUDE-MEM REDUNDANT, or NEEDS REVIEW \u2014 then 3 to 5 lines of reasoning. Be concise.' --settings ~/.claude/settings-worker.json --allowedTools Bash,Read,Grep,Glob --strict-mcp-config --no-session-persistence < /dev/null > /tmp/claude-mem-eval.txt 2>&1; python3 ~/workspace/scripts/notify.py \"Weekly claude-mem value eval:\" \"$(cat /tmp/claude-mem-eval.txt)\"\n---\n\nMonday 09:00 SAST. Evaluates whether claude-mem adds value over the rest of\nLuci's memory stack (vault.db + SecondBrain, file auto-memory, MC-DB) \u2014 so we\ncan decide if running both is worth it.\n\nRuns `claude` (Sonnet) to do the judgement, writes a verdict to\n`/tmp/claude-mem-eval.txt`, and Telegrams Elmar the result. `notify_on: always`\nso the verdict lands every week, not just on failure.\n\nContext: claude-mem was installed by Lucienne and runs side-by-side with the\nauto-memory layer (see memory `claude-mem-sanctioned`). This task is the\nrecurring check that the side-by-side arrangement still earns its keep.\n`runtime_profile: claude_sonnet_medium` matches the actual `claude` CLI call.\n\nHeadless-hang hardening (MC-3772): the `claude -p` call uses `--strict-mcp-config`\n(boots zero MCP servers \u2014 the eval needs only Bash/Read/Grep/Glob, and MCP server\nspawns are the slowest, most memory-hungry part of boot on this OOM-pressured\nbox), `--no-session-persistence`, and `< /dev/null` stdin. It is wrapped in\n`timeout -k 30 1500` so a stalled `claude` is killed below the 1800s task ceiling\nand `notify.py` still reports the outcome instead of the whole task being reaped\nsilently.\n","id":"claude-mem-value-eval","last_run":{"duration_s":140.427973,"log_path":"/home/lucienne/workspace/logs/task-runs/claude-mem-value-eval/393148.log","output":"Telegram send failed: HTTP Error 400: Bad Request\nSent\n","started_at":"2026-06-08T09:00:00.573360+02:00","status":"completed"},"next_run":"2026-06-15 09:00","next_run_iso":"2026-06-15T09:00:00+02:00","runs":[{"duration_s":140.427973,"finished_at":"2026-06-08T09:02:21.134478+02:00","id":393148,"log_path":"/home/lucienne/workspace/logs/task-runs/claude-mem-value-eval/393148.log","output":"Telegram send failed: HTTP Error 400: Bad Request\nSent\n","started_at":"2026-06-08T09:00:00.573360+02:00","status":"completed","task_id":"claude-mem-value-eval","task_name":"claude-mem-value-eval"}],"runs_limit":20,"schedule":"0 9 * * 1","schedule_label":{"description":"Mon at 09:00","is_custom":false,"label":"Weekly (Mon)","sort":6,"sort_time":"09:00"},"stats":{"avg_duration":140.427973,"completed":1,"failed":0,"timeout":0,"total":1},"task":{"_description":"Monday 09:00 SAST. Evaluates whether claude-mem adds value over the rest of\nLuci's memory stack (vault.db + SecondBrain, file auto-memory, MC-DB) \u2014 so we\ncan decide if running both is worth it.\n\nRuns `claude` (Sonnet) to do the judgement, writes a verdict to\n`/tmp/claude-mem-eval.txt`, and Telegrams Elmar the result. `notify_on: always`\nso the verdict lands every week, not just on failure.\n\nContext: claude-mem was installed by Lucienne and runs side-by-side with the\nauto-memory layer (see memory `claude-mem-sanctioned`). This task is the\nrecurring check that the side-by-side arrangement still earns its keep.\n`runtime_profile: claude_sonnet_medium` matches the actual `claude` CLI call.\n\nHeadless-hang hardening (MC-3772): the `claude -p` call uses `--strict-mcp-config`\n(boots zero MCP servers \u2014 the eval needs only Bash/Read/Grep/Glob, and MCP server\nspawns are the slowest, most memory-hungry part of boot on this OOM-pressured\nbox), `--no-session-persistence`, and `< /dev/null` stdin. It is wrapped in\n`timeout -k 30 1500` so a stalled `claude` is killed below the 1800s task ceiling\nand `notify.py` still reports the outcome instead of the whole task being reaped\nsilently.","_file":"claude-mem-value-eval.md","_path":"/home/lucienne/workspace/tasks/claude-mem-value-eval.md","command":"cd ~/workspace && timeout -k 30 1500 claude -p 'Weekly claude-mem value evaluation. Decide whether claude-mem still earns its place in the Luci memory stack. Steps: (1) Inspect claude-mem stored data and usage \u2014 look in ~/.claude-mem/ and note how much was captured in the last week and whether it is being queried. (2) Compare against the other memory layers: vault.db plus SecondBrain (knowledge base), file auto-memory at ~/.claude/projects/-home-lucienne-workspace/memory/, and the MC database work-state. (3) Decide whether claude-mem surfaces anything the other layers do not, and whether it is worth running both. Output a short verdict on the first line \u2014 exactly one of KEEP BOTH, CLAUDE-MEM REDUNDANT, or NEEDS REVIEW \u2014 then 3 to 5 lines of reasoning. Be concise.' --settings ~/.claude/settings-worker.json --allowedTools Bash,Read,Grep,Glob --strict-mcp-config --no-session-persistence < /dev/null > /tmp/claude-mem-eval.txt 2>&1; python3 ~/workspace/scripts/notify.py \"Weekly claude-mem value eval:\" \"$(cat /tmp/claude-mem-eval.txt)\"\n","criticality":"low","enabled":true,"id":"claude-mem-value-eval","name":"Weekly claude-mem value evaluation","notify_on":"always","retry":false,"run_as":"shell","runtime_profile":"claude_sonnet_medium","schedule":"0 9 * * 1","tags":["memory","evaluation"],"timeout":1800}}