Memory Rule Clusters — Decision-Time Consultation Map

This hub is the authoritative aggregator of all 92 feedback rules in /home/opsadmin/.claude/projects/-home-opsadmin/memory/, organized into the 11 Decision-Time Consultation Map clusters defined in MEMORY.md. Read the relevant cluster before acting, asking, or writing code. Rules are incident-derived (tagged incident_derived: true in frontmatter) and MUST live above MEMORY.md line 150 per feedback_memory_fold_protection.

Quick reference

FieldValue
Gate IDG-MEMORY-FOLD-PROTECTION
CLAUDE.md section§Cascade-Failure Gates, G-MEMORY-FOLD-PROTECTION
Enforcement modememory-load (auto-loaded via on-session-start.sh)
Validator scriptn/a
Discord alertyes:#ops (on incident recurrence)
Feedback rulesfeedback_memory_fold_protection, feedback_blocker_surfacing
Incidents derived fromoomd-cascade-2026-05-01, vault-leak-2026-05-03, aurora-soul-overwrite-2026-04-16, 374-dup-sms, 9870-wrong-inbox
Violable byClaude, agent
Last known violation2026-05-03 (vault-leak from plaintext creds in synced plans)
Amendment§A1 2026-05-01
Phase statusactive
Last audit2026-05-03

Cluster 1 — Before asking Henry any question

Trigger: Any time Claude is about to surface a question, request, or blocker to Henry.

RuleSummaryEnforcement
feedback_question_disciplineDo not ask questions that can be answered by reading existing files or logsmemory-load
feedback_check_resources_before_askingGREP/read existing memory, plans, and KB docs BEFORE forming a questionmemory-load
feedback_options_listed_verticallyWhen presenting options, list A/B/C vertically with trade-offs — never inlinememory-load

Rule count: 3


Cluster 2 — Before asking Henry for any API key / credential

Trigger: Any time Claude needs a credential, token, or API key.

RuleSummaryEnforcement
reference_1password_op_accessop CLI auth via OP_SERVICE_ACCOUNT_TOKEN; vault=Aurora; use op://Aurora/<item>/<field>memory-load
reference_hetzner_credentials_1pHetzner web login + Cloud API token in vault Aurora — never ask Henry to paste in chatmemory-load

Rule count: 2

Gate: This cluster enforces feedback_no_plaintext_creds (G-NO-PLAINTEXT-CREDS). See also Cluster 7.


Cluster 3 — Before claiming “X exists/doesn’t exist/works/is broken”

Trigger: Any factual claim about system state, API behavior, file existence, or service health.

RuleSummaryEnforcement
feedback_no_assumptionsNever assume a file, table, service, or field exists without checking live statememory-load
feedback_never_assumptive_auditRun actual commands to verify; never audit from memory alonememory-load
feedback_audit_before_architectCheck what exists before proposing new architecturememory-load
feedback_live_over_memoryLive API/service state always overrides cached memory when in conflictmemory-load
feedback_tier_0_first_before_amendmentsRun Phase 0 audit before any plan amendment — verify current state firstmemory-load
feedback_source_master_env_before_checkingCheck master.env (111+ vars, 19 sections) before claiming a credential is missingmemory-load
feedback_systemctl_cat_before_env_claimsRun systemctl cat <unit> before claiming a service has no env varsmemory-load
feedback_sshd_client_timeout_vs_vps_stressSSH timeout ≠ VPS crash; distinguish client disconnect from server stressmemory-load
feedback_macos_firewall_blocks_tailscaledmacOS firewall blocks tailscaled socket; check firewall before assuming Tailscale is brokenmemory-load

Rule count: 9 (+ Skill: audit-before-architecting)


Cluster 4 — Before any plan amendment / status claim / canonicalization

Trigger: Before amending a plan, claiming a phase is done, or declaring a file canonical.

RuleSummaryEnforcement
feedback_tier_0_first_before_amendmentsPhase 0 audit before amending any plan — verify current state is as assumedmemory-load
feedback_plan_status_inline_and_verifyPlan status must be inline AND verified via live commands, not inferredmemory-load
feedback_plan_amendments_additiveAmendments are additive only — never overwrite prior decisions or phasesmemory-load
feedback_post_audit_persistenceAfter completing an audit, persist findings before ending sessionmemory-load
feedback_plan_completeness_gateAll plan phases must have exit criteria, rollback steps, and verification commandsmemory-load
feedback_visual_map_requiredAny plan touching ≥3 subsystems requires a visual map (Mermaid or Canvas)memory-load
feedback_pre_build_index_verificationBefore creating any new file, verify it does not already exist (search first)memory-load

Rule count: 7


Cluster 5 — Before claiming “X has no Y dependency” or scoping a change

Trigger: Before scoping a change, claiming independence, or estimating impact radius.

RuleSummaryEnforcement
feedback_full_data_pipeline_traceTrace the full data pipeline (ingest → transform → store → serve) before any changememory-load
feedback_reread_code_before_scoping_editsRe-read the actual file before estimating edit scope — never estimate from memorymemory-load
feedback_verify_schema_before_designingCheck actual Supabase schema (CHOKEPOINT-1 tables) before designing new writesmemory-load
feedback_chokepoint_principleAll state mutations route through CHOKEPOINT-1/2/3 — no silent side-channel writesmemory-load
feedback_completeness_map_requiredEvery scope change requires a completeness map showing what is and isn’t coveredmemory-load
feedback_cost_root_requiredEvery cost change must trace to root cause before recommending a fixmemory-load
feedback_dual_write_requiredAny write to Supabase must also write the corresponding audit/log rowmemory-load

Rule count: 7


Cluster 6 — Before any side-effect action (write / delete / restart / config / outbound)

Trigger: Before any action that changes system state: file writes, deletes, service restarts, config changes, or outbound API calls with side effects.

RuleSummaryEnforcement
feedback_action_gate_violation_repeatedService restarts and file writes require explicit Henry authorization per sessionmemory-load
feedback_probe_before_executeRun a dry-run or read probe before any destructive or stateful commandmemory-load
feedback_time_boxed_confirmState intended action + wait for confirmation before executing side-effectsmemory-load
feedback_scope_echo_requiredEcho the scope of what will be changed before executingmemory-load
feedback_never_send_without_authNever send SMS, email, or outbound message without explicit per-send authorizationmemory-load
feedback_archive_not_deleteArchive files and configs instead of deleting — keeps audit trail intactmemory-load
feedback_cloudflare_plan_before_executeAny Cloudflare change (Tunnel, WAF, DNS) requires a written plan reviewed firstmemory-load
feedback_tailscale_serve_strict_approvalTailscale Funnel changes require explicit approval + FUNNEL-REGISTRY.md updatememory-load
feedback_user_slice_cap_patternCap user-1001.slice AND user@1001.service together — one without the other is incompletememory-load
feedback_substrate_right_size_to_working_setRight-size infrastructure to actual working set, not aspirational loadmemory-load

Rule count: 10


Cluster 7 — Before any credential touch

Trigger: Before reading, writing, rotating, or referencing any credential, token, secret, or API key.

RuleSummaryEnforcement
feedback_credentials_in_chatNever paste credentials in chat — always use op://Aurora/<item>/<field> referencesmemory-load
feedback_credential_pipe_requiredPipe credentials through env var or op:// — never inline in script argumentsmemory-load
feedback_credentials_via_1password_cliAll credentials fetched via op CLI; OP_SERVICE_ACCOUNT_TOKEN requiredmemory-load
feedback_credentials_repeat_exposureAfter any credential appears in context, immediately redact and rotatememory-load
feedback_always_redact_grep_outputRedact grep output before sharing if it might match API keys or tokensmemory-load
feedback_no_plaintext_credsZero plaintext creds in any tracked file — G-NO-PLAINTEXT-CREDS hard stopmemory-load

Rule count: 6

Gate: G-NO-PLAINTEXT-CREDS. Violations must be reported to ops immediately. See 1password for op:// pattern.


Cluster 8 — Before writing or editing a memory/feedback file

Trigger: Before creating a new feedback_*.md rule or editing an existing one.

RuleSummaryEnforcement
feedback_check_resources_before_askingGREP existing memory first — does a similar rule already exist?memory-load
feedback_archive_not_deleteArchive old rules instead of deleting; append _deprecated suffixmemory-load
feedback_memory_fold_protectionIncident-derived rules MUST live above MEMORY.md line 150memory-load

Rule count: 3 (+ meta: check Decision-Time Consultation Map for cluster fit)


Cluster 9 — Before completing / closing any phase or audit

Trigger: Before marking a phase complete, closing a plan, or ending a session.

RuleSummaryEnforcement
feedback_no_partial_completionNever mark a phase complete with known gaps — document them explicitlymemory-load
feedback_post_audit_persistencePersist all audit findings before the session endsmemory-load
feedback_heartbeat_disciplineWrite SESSION-AUDIT.md and bridge file before stoppingmemory-load
feedback_blocker_surfacingMirror all open blockers from plan files to SESSION-AUDIT.md NEXT ACTIONSmemory-load

Rule count: 4

Gate: G-BLOCKER-SURFACING. Plan-level blockers hidden from SESSION-AUDIT are a governance violation.


Cluster 10 — Before model dispatch / planning vs execution

Trigger: Before dispatching any subagent or deciding which model handles a task.

RuleSummaryEnforcement
feedback_model_routing_patternOpus plans/audits (main); Sonnet executes via 8-element dispatch prompt; Haiku trivial lookups onlymemory-load

Rule count: 1 (but 8-element Sonnet dispatch prompt is the key enforcement surface)

Source: /home/opsadmin/.claude/projects/-home-opsadmin/memory/feedback_model_routing_pattern.md


Cluster 11 — During long-running async waits or context-tight sessions

Trigger: Mid-session when waiting on a background process, approaching context limit, or facing a long-running async operation.

RuleSummaryEnforcement
feedback_proactive_parallel_prepDuring async waits, prepare next steps in parallel — don’t idlememory-load
feedback_save_state_before_context_limitAt 80% context capacity, write bridge file + SESSION-AUDIT update before compactingmemory-load
feedback_push_through_to_completionPrefer completing a phase over stopping mid-way; incomplete work accumulates driftmemory-load

Rule count: 3


Cluster 12 — Cascade-failure gates (Amendment §A1, 2026-05-01)

Trigger: Any time a new plan is created, a new KB dir is added, a service is started, or governance files go stale. These 8 gates are directly incident-derived.

RuleGateIncident OriginEnforcement
feedback_plan_index_requiredG-PLAN-INDEX-REQUIRED89% orphan-plan rate (Binance/EU plan loss)manual
feedback_memory_fold_protectionG-MEMORY-FOLD-PROTECTIONRules invisible below fold caused 9870 wrong-inbox + 374-dup-SMS + Aurora SOUL overwritememory-load
feedback_blocker_surfacingG-BLOCKER-SURFACING47 hidden blockers across 32 plans silently dormantmanual
feedback_no_plaintext_credsG-NO-PLAINTEXT-CREDSTOOLS.md 15+ plaintext production secrets in rw-rw-r— file 24+ daysmemory-load
feedback_service_pre_start_docG-SERVICE-PRE-START-DOC23 undocumented live services causing conflictsmanual
feedback_kb_sync_with_claude_mdG-KB-SYNC-WITH-CLAUDEMD51% KB docs invisible to Sources First protocolmanual
feedback_governance_log_freshnessG-GOVERNANCE-LOG-FRESHNESSCHANGELOG 72d stale, WORKFLOW-PATTERNS 44d stalecron
feedback_failed_service_mttrG-FAILED-SERVICE-MTTRSilent-failed services masking live data outagescron

Rule count: 8

Amendment: §A1 2026-05-01 in openclaw-fragmentation-fix-2026-05-01.md. Full enforcement cron ships in Phase 2.


Cluster 13 — Domain-specific rules (consult when working in that domain)

These rules are organized by domain. Scan the relevant sub-cluster when entering that domain.

Aurora agent behavior

RuleSummary
feedback_agent_identity_firstRead SOUL.md before proposing any agent change
feedback_aurora_outbound_guardrailsAurora outbound message guardrails — never bypass
feedback_aurora_slack_behaviorAurora Slack posting behavior constraints
feedback_quo_lineid_requiredQuo dispatch requires explicit line_id — never omit
feedback_never_use_henry_nameNever use “Henry” in agent-facing messages

Local LLM (M1 Ultra / Ollama)

RuleSummary
feedback_mlx_coreml_rejectedMLX/CoreML rejected for production — Ollama only
feedback_kv_quant_num_ctx_pairingKV cache quant paired with num_ctx for memory safety
feedback_mmap_paging_sparse_moeMMap paging strategy for sparse MoE models
feedback_16_item_optimization_triage16-item triage before any Ollama optimization
feedback_rag_context_gap_in_benchRAG context gap in benchmark interpretation

Plan governance

RuleSummary
feedback_plan_governance_standardUniversal plan governance standard (phases, exit criteria, rollback)
feedback_plan_labels_requiredAll plans require status + priority labels
feedback_universal_execution_rulesUniversal execution rules apply to all plan phases
feedback_gsd_midphase_workflowGSD mid-phase workflow for context handoffs
feedback_system_audit_formatDefault 10-section system audit output format
feedback_skill_trigger_registrySkill trigger registry — auto-invoke on keyword match

SalesMsg / SMS

RuleSummary
feedback_salesmsg_api_firstCheck SalesMsg API before writing any SMS code
feedback_salesmsg_mention_syntaxSalesMsg @mention syntax — agent tagging protocol
feedback_blast_inbox_requiredBlast operations require inbox selection
feedback_sms_160_char_at_scaleSMS 160-char limit critical at scale — enforce always

Trading / betting

RuleSummary
feedback_event_driven_architectureEvent-driven architecture for trading/betting data
feedback_live_event_betting_workflowLive event betting workflow constraints
feedback_polymarket_fee_structurePolymarket fee structure — LP vs market-order

Email / messages

RuleSummary
feedback_email_formattingEmail formatting standards for TC comms
feedback_no_em_dashNo em dash in agent messages (parsing hazard)
feedback_em_dash_section_dividers_okEm dash OK as section divider in documentation

Data

RuleSummary
feedback_supabase_paginationAll Supabase queries must paginate — default limit=1000
feedback_master_env_export_patternmaster.env export pattern — source correctly in scripts
feedback_dispo_scorer_rulesDispo deal scoring rules — weights and thresholds

InvestorLift

RuleSummary
feedback_il_enrichment_runs_on_mac_ultraIL enrichment runs on EC2 Mac Ultra only — VPS is 403’d
feedback_il_acq_negotiation_mindsetIL acquisition negotiation mindset — wholesale framing
feedback_il_contact_precedence_ruleIL contact precedence rule — owner > listing agent
feedback_il_dispo_price_formulaIL dispo price formula — ARV-based calculation

Acquisitions behavioral

RuleSummary
feedback_acq_no_pass_and_pivotNever “pass and pivot” in acquisitions — commit to position
feedback_acq_thread_history_aware_gatesAcquisitions thread history gates before re-engagement
feedback_acq_mentor_voice_cadenceAcquisitions mentor voice + cadence constraints

AI architecture

RuleSummary
feedback_ai_native_interaction_architectureCRITICAL Henry directive 2026-04-29 — all agent interactions must be AI-native

Agent infra

RuleSummary
feedback_models_guardian_patternagent models.json overwritten by gateway on restart — edit models-backups/ instead

Dispo SMS / buyer comms

RuleSummary
feedback_dispo_sip_vs_tenantDispo SIP vs tenant SMS routing — separate channels

Domain-specific rule count: 37


Feedback rule inventory (full — all 92 rules cross-referenced)

RuleClusterEnforcementLast fire / Notes
feedback_question_discipline1-Before asking Henrymemory-loadAsk only what can’t be self-answered
feedback_check_resources_before_asking1-Before asking Henry / 8-Before writing memorymemory-loadDual-cluster
feedback_options_listed_vertically1-Before asking Henrymemory-loadA/B/C vertical format
reference_1password_op_access2-Before asking for credentialsmemory-loadop:// pattern anchor
reference_hetzner_credentials_1p2-Before asking for credentialsmemory-loadHetzner vault ref
feedback_no_assumptions3-Before claiming Xmemory-load
feedback_never_assumptive_audit3-Before claiming Xmemory-loadincident_derived
feedback_audit_before_architect3-Before claiming Xmemory-load
feedback_live_over_memory3-Before claiming Xmemory-load
feedback_tier_0_first_before_amendments3-Before claiming X / 4-Before plan amendmentmemory-loadDual-cluster
feedback_source_master_env_before_checking3-Before claiming Xmemory-load
feedback_systemctl_cat_before_env_claims3-Before claiming Xmemory-load
feedback_sshd_client_timeout_vs_vps_stress3-Before claiming Xmemory-load
feedback_macos_firewall_blocks_tailscaled3-Before claiming Xmemory-load
feedback_plan_status_inline_and_verify4-Before plan amendmentmemory-load
feedback_plan_amendments_additive4-Before plan amendmentmemory-loadincident_derived
feedback_post_audit_persistence4-Before plan amendment / 9-Before completing phasememory-loadDual-cluster
feedback_plan_completeness_gate4-Before plan amendmentmemory-load
feedback_visual_map_required4-Before plan amendmentmemory-load
feedback_pre_build_index_verification4-Before plan amendmentmemory-load
feedback_full_data_pipeline_trace5-Before scoping changememory-load
feedback_reread_code_before_scoping_edits5-Before scoping changememory-load
feedback_verify_schema_before_designing5-Before scoping changememory-load
feedback_chokepoint_principle5-Before scoping changememory-loadG-CHOKEPOINT
feedback_completeness_map_required5-Before scoping changememory-load
feedback_cost_root_required5-Before scoping changememory-load
feedback_dual_write_required5-Before scoping changememory-loadG-DUAL-WRITE
feedback_action_gate_violation_repeated6-Before side-effectmemory-loadincident_derived
feedback_probe_before_execute6-Before side-effectmemory-load
feedback_time_boxed_confirm6-Before side-effectmemory-load
feedback_scope_echo_required6-Before side-effectmemory-load
feedback_never_send_without_auth6-Before side-effectmemory-loadincident_derived: 374-dup-sms
feedback_archive_not_delete6-Before side-effect / 8-Before writing memorymemory-loadDual-cluster
feedback_cloudflare_plan_before_execute6-Before side-effectmemory-load
feedback_tailscale_serve_strict_approval6-Before side-effectmemory-load
feedback_user_slice_cap_pattern6-Before side-effectmemory-loadincident_derived: oomd-cascade
feedback_substrate_right_size_to_working_set6-Before side-effectmemory-loadincident_derived: oomd-cascade
feedback_credentials_in_chat7-Before credential touchmemory-loadincident_derived
feedback_credential_pipe_required7-Before credential touchmemory-load
feedback_credentials_via_1password_cli7-Before credential touchmemory-load
feedback_credentials_repeat_exposure7-Before credential touchmemory-loadincident_derived
feedback_always_redact_grep_output7-Before credential touchmemory-load
feedback_no_plaintext_creds7-Before credential touch / 12-Cascade gatesmemory-loadG-NO-PLAINTEXT-CREDS
feedback_memory_fold_protection8-Before writing memory / 12-Cascade gatesmemory-loadG-MEMORY-FOLD-PROTECTION
feedback_no_partial_completion9-Before completing phasememory-load
feedback_heartbeat_discipline9-Before completing phasememory-load
feedback_blocker_surfacing9-Before completing phase / 12-Cascade gatesmemory-loadG-BLOCKER-SURFACING
feedback_model_routing_pattern10-Before model dispatchmemory-loadOpus/Sonnet/Haiku split
feedback_proactive_parallel_prep11-Long-running waitsmemory-load
feedback_save_state_before_context_limit11-Long-running waitsmemory-load
feedback_push_through_to_completion11-Long-running waitsmemory-load
feedback_plan_index_required12-Cascade gatesmanualG-PLAN-INDEX-REQUIRED
feedback_service_pre_start_doc12-Cascade gatesmanualG-SERVICE-PRE-START-DOC
feedback_kb_sync_with_claude_md12-Cascade gatesmanualG-KB-SYNC-WITH-CLAUDEMD
feedback_governance_log_freshness12-Cascade gatescronG-GOVERNANCE-LOG-FRESHNESS
feedback_failed_service_mttr12-Cascade gatescronG-FAILED-SERVICE-MTTR
feedback_agent_identity_first13-Domain: Auroramemory-loadincident_derived: soul-overwrite
feedback_aurora_outbound_guardrails13-Domain: Auroramemory-load
feedback_aurora_slack_behavior13-Domain: Auroramemory-load
feedback_quo_lineid_required13-Domain: Auroramemory-load
feedback_never_use_henry_name13-Domain: Auroramemory-load
feedback_mlx_coreml_rejected13-Domain: Local LLMmemory-load
feedback_kv_quant_num_ctx_pairing13-Domain: Local LLMmemory-load
feedback_mmap_paging_sparse_moe13-Domain: Local LLMmemory-load
feedback_16_item_optimization_triage13-Domain: Local LLMmemory-load
feedback_rag_context_gap_in_bench13-Domain: Local LLMmemory-load
feedback_plan_governance_standard13-Domain: Plan governancememory-load
feedback_plan_labels_required13-Domain: Plan governancememory-load
feedback_universal_execution_rules13-Domain: Plan governancememory-load
feedback_gsd_midphase_workflow13-Domain: Plan governancememory-load
feedback_system_audit_format13-Domain: Plan governancememory-load
feedback_skill_trigger_registry13-Domain: Plan governancememory-load
feedback_salesmsg_api_first13-Domain: SalesMsgmemory-load
feedback_salesmsg_mention_syntax13-Domain: SalesMsgmemory-load
feedback_blast_inbox_required13-Domain: SalesMsgmemory-loadincident_derived: 374-dup-sms
feedback_sms_160_char_at_scale13-Domain: SalesMsgmemory-load
feedback_event_driven_architecture13-Domain: Tradingmemory-load
feedback_live_event_betting_workflow13-Domain: Tradingmemory-load
feedback_polymarket_fee_structure13-Domain: Tradingmemory-load
feedback_email_formatting13-Domain: Emailmemory-load
feedback_no_em_dash13-Domain: Emailmemory-load
feedback_em_dash_section_dividers_ok13-Domain: Emailmemory-load
feedback_supabase_pagination13-Domain: Datamemory-load
feedback_master_env_export_pattern13-Domain: Datamemory-load
feedback_dispo_scorer_rules13-Domain: Datamemory-load
feedback_il_enrichment_runs_on_mac_ultra13-Domain: InvestorLiftmemory-load
feedback_il_acq_negotiation_mindset13-Domain: InvestorLiftmemory-load
feedback_il_contact_precedence_rule13-Domain: InvestorLiftmemory-load
feedback_il_dispo_price_formula13-Domain: InvestorLiftmemory-load
feedback_acq_no_pass_and_pivot13-Domain: Acquisitionsmemory-load
feedback_acq_thread_history_aware_gates13-Domain: Acquisitionsmemory-load
feedback_acq_mentor_voice_cadence13-Domain: Acquisitionsmemory-load
feedback_ai_native_interaction_architecture13-Domain: AI archmemory-loadincident_derived: 2026-04-29
feedback_models_guardian_pattern13-Domain: Agent inframemory-load
feedback_dispo_sip_vs_tenant13-Domain: Dispo SMSmemory-load
feedback_obsidian_sync_external_changes_unreliable13-Domain: Vault/Obsidianmemory-loadincident_derived

Total rules catalogued: 92 (55 primary clusters + 37 domain-specific)


Components

  • ~/.claude/projects/-home-opsadmin/memory/MEMORY.md — Decision-Time Consultation Map source (lines 39-88)
  • ~/.claude/projects/-home-opsadmin/memory/SAFETY-RAILS.md — ~30 incident-derived rules, auto-loaded
  • ~/.claude/projects/-home-opsadmin/memory/feedback_*.md — 92 individual rule files
  • /home/opsadmin/.openclaw/workspace/CLAUDE.md — §Cascade-Failure Gates (G-MEMORY-FOLD-PROTECTION master spec)
  • /home/opsadmin/.openclaw/tools/hooks/on-session-start.sh — auto-loads SAFETY-RAILS + MEMORY at session start

How it’s used

  • Trigger: Claude scans the relevant cluster map BEFORE acting, asking, or writing code
  • Workflow: Match the incoming action type to the cluster → scan all rules in that cluster → self-check compliance → proceed or escalate
  • Agents involved: All 42 active agents (rules apply fleet-wide); Aurora has additional domain-specific cluster
  • Failure mode: Rules invisible below MEMORY.md fold — G-MEMORY-FOLD-PROTECTION requires incident-derived rules above line 150
  • Success criteria: Zero incident recurrence traceable to a rule that exists but was invisible or skipped

Governance hubs that own specific clusters

Integration hubs enforced by these clusters

  • 1password — Clusters 2 and 7 (credential layer anchor)
  • supabase — Cluster 5 (schema + CHOKEPOINT writes)
  • portkey — Cluster 10 (model routing — CHOKEPOINT-1)
  • cloudflare — Cluster 6 (cloudflare plan before execute)
  • salesmsg — Cluster 13 domain: SalesMsg
  • investorlift — Cluster 13 domain: InvestorLift

Plans that govern this

System maps

Open issues / TODOs

  • Phase 1.7 of fragmentation-fix promised 22 gates; only 8+2 (G-CHOKEPOINT+G-DUAL-WRITE) in CLAUDE.md. Remaining 12 pending.
  • G-GOVERNANCE-LOG-FRESHNESS + G-FAILED-SERVICE-MTTR enforcement crons ship in Phase 2 (not yet live)
  • feedback_obsidian_sync_external_changes_unreliable.md not yet in MEMORY.md Decision-Time Map — candidate for Cluster 3

Recent activity

  • 2026-05-04: incident-timeline hub created (incident-timeline) — all incident-derived feedback rules now have historical anchor
  • 2026-05-03: hub created by W2-S2 (Wave 2 governance reference batch)