Data Freshness
✓Metrics data5.23.26 (0d old)
Source: dashboards/dashboard_data.js · Mtime: 0d ago
✓Recommendation events0d old
Source: data/processed/recommendation_events.csv
Top Buys (0)
Top BF Combo
ROIC/Ebitda Spread + Risk to Value Growth
Open BF Combo Dashboard →★Win rate100%
Lift: +79.5pp vs 20.5% baseline · n=17
·Combo metricsROIC/Ebitda Spread + Risk to Value Growth
Each metric screens independently against its threshold (AND-gate). Tickers must pass ALL rules simultaneously.
Active Gate (5 rules)
Live from mde_rules_config.RULES_6
Open Gate Alternatives →✓?dist=? · ?
sm_col: 65 · scripts_dist: ? · direction: ?
✓?dist=? · ?
sm_col: 31 · scripts_dist: ? · direction: ?
✓?dist=? · ?
sm_col: 59 · scripts_dist: ? · direction: ?
✓?dist=? · ?
sm_col: 52 · scripts_dist: ? · direction: ?
✓?dist=? · ?
sm_col: 57 · scripts_dist: ? · direction: ?
Health Check
⛔Errors2
Errors must be 0 before any pipeline run. Open metric_discovery_engine/data/processed/health_check_report.html for details.
⚠Warnings63
Review warnings before next pipeline run. They do not block execution but indicate drift, staleness, or governance gaps.
Gate Alternatives (18 alts)
Above current: 9/18 · current composite: 51.5
Open Gate Alternatives Dashboard →·Current Gate (Production Baseline)composite=51.5 · v12 — User Curated Lean Gate
gate_id: 949 · sel=80 · ctrl=8.7 · mps=68.4 · dir=100 · pass_all=11 · n_rules=5
✓Swap: ROIC-EBITDA QC → ROIC/Ebitda Spreadcomposite=59.3 · Δ +7.8
gate_id: 2784 · group: quick_swap · n_rules: 5 · pass_all: 9 · Auto: replace ROIC-EBITDA QC with top-SIL non-gate L2 candidate ROIC/Ebitda Spread (sil=60) · top3: ASND, SNDK, AMSC
✓Swap: ROIC-EBITDA QC → ROICcomposite=58.3 · Δ +6.8
gate_id: 6404 · group: quick_swap · n_rules: 5 · pass_all: 9 · Auto: replace ROIC-EBITDA QC with top-SIL non-gate L2 candidate ROIC (sil=69) · top3: BW, SGML, SEAT
✓Swap: ROIC-EBITDA QC → ROEcomposite=57.5 · Δ +6.0
gate_id: 1360 · group: quick_swap · n_rules: 5 · pass_all: 10 · Auto: replace ROIC-EBITDA QC with top-SIL non-gate L2 candidate ROE (sil=61) · top3: TVTX, BRCC, SGML
✓Swap: ROIC-EBITDA QC → P/Ccomposite=57.2 · Δ +5.7
gate_id: 9129 · group: quick_swap · n_rules: 5 · pass_all: 6 · Auto: replace ROIC-EBITDA QC with top-SIL non-gate L2 candidate P/C (sil=60) · top3: SEAT, METC, ZIP
✓Swap: ROIC-EBITDA QC → ROAcomposite=57.2 · Δ +5.7
gate_id: 7423 · group: quick_swap · n_rules: 5 · pass_all: 5 · Auto: replace ROIC-EBITDA QC with top-SIL non-gate L2 candidate ROA (sil=52) · top3: SGML, SEAT, CREX
✓Swap: ROIC-EBITDA QC → Rev Growth Efficiencycomposite=57.0 · Δ +5.5
gate_id: 7335 · group: quick_swap · n_rules: 5 · pass_all: 1 · Auto: replace ROIC-EBITDA QC with top-SIL non-gate L2 candidate Rev Growth Efficiency (sil=66) · top3: CLFD, OSS, ASND
✓Swap: Avg EPS Growth → Quality Value Scorecomposite=55.0 · Δ +3.5
gate_id: 9143 · group: quick_swap · n_rules: 5 · pass_all: 23 · Auto: replace Avg EPS Growth with top-SIL non-gate L2 candidate Quality Value Score (sil=78) · top3: OSS, ASND, SNDK
✓Swap: Avg EPS Growth → Quality Value Score (Test Version)composite=54.4 · Δ +2.9
gate_id: 4776 · group: quick_swap · n_rules: 5 · pass_all: 23 · Auto: replace Avg EPS Growth with top-SIL non-gate L2 candidate Quality Value Score (Test Version) (sil=58) · top3: OSS, ASND, SNDK
✓Mixed Tiercomposite=52.9 · Δ +1.4
gate_id: 9272 · group: experimental · n_rules: 5 · pass_all: 22 · Best L1 signal anchored by top L2 quality checks — tests if raw signals add lift · top3: PAMT, CATO, ELSE
★SIL-Driven Fixcomposite=51.5 · Δ +0.0 · 📌 pinned
gate_id: 949 · group: quick_swap · n_rules: 5 · pass_all: 11 · No swap-outs recommended — gate is healthy at this severity tier · top3: OSS, ASND, SNDK
Data Pulls
See references/METRIC_UPDATE_RUNBOOK.md
✓finviz_pull2026-05-23 (0d ago)
Source: data/processed/finviz_pull_*.csv · Cadence: weekly (warn ≥7d)
✓ratio_pull2026-05-23 (0d ago)
Source: data/processed/ratio_pull_*.csv · Cadence: weekly (warn ≥7d)
✓newresearch2026-05-17 (6d ago)
Source: data/processed/newresearch_*.csv · Cadence: weekly (warn ≥7d)
Control Lab
No edge yet — treatment at -13.2pp vs control (p=0.155, N=42)
Open Control Group Lab →⚠Treatment N42/150 (28%)
Sample size of FORMAL recs with priced returns. Target N≥150 for statistical significance per SYSTEM_STANDARDS.md §3.
·Control N priced494/500
Active control group: 494/500. Stale prices skipped (>0d).
⚠Treatment excess-8.56pp
Mean treatment return minus market baseline.
·Control excess (all-universe)+4.60pp
Mean control group return minus market baseline — all 500 random tickers (coin-flip baseline).
★Gate-Filtered Random (PRIMARY)+30.81pp (N=8)
Mean excess of control tickers passing 4+ rules — authoritative gate-effectiveness measurement, isolated from rec-process noise (added 2026-05-21).
⚠Rec-process gap-39.4pp
FORMAL recs minus Gate-Filtered Random — measures rec-curation value-add (>0) or destruction (<0) on top of the gate.
·SPY since seed+17.59%
Market baseline return since control seed date.
⚠p-value0.155
Welch's two-tailed t-test, treatment vs control. <0.05 = statistically significant edge.
·VerdictNo edge yet — treatment at -13.2pp vs control (p=0.155, N=42)
No edge yet — treatment at -13.2pp vs control (p=0.155, N=42)
⚠Direction disagreements33
Metrics where control direction disagrees with cohort direction. Investigate before acting.
★Buy candidates2
Control tickers scoring 4+/6 + outperforming. See Control_Group_Lab.html.
★New signal candidates5
New metric signals identified by the lab — review in dashboard.
Signal Intelligence (top 5 of 71)
Run date: 2026-05-23
★FCF Efficency★★★★★ · lower wins · in_gate=yes
5-star | lower wins | 152 sessions held | IN GATE | control agrees · FCF Efficency confidence has been oscillating rather than trending over recent runs. This suggests direction lock may be unstable or a metric input is noisy. Hold off on gate decisions until trend stabilizes over 3+ consecutive runs.
★Quality Value Score★★★★★ · lower wins · in_gate=no
5-star | lower wins | 150 sessions held | not in gate | control agrees · Quality Value Score has 5-star confidence and is not in your screening gate. It has held its direction (lower scores win) for 150 consecutive sessions. Every run you screen without it, you leave a validated signal unused. This is your clearest ADD candidate right now. || Quality Value Score confiden
✓SM3: Quality-Overvaluation Wildcard★★★★☆ · lower wins · in_gate=no
4-star | lower wins | 62 sessions held | not in gate | control disagrees · SM3: Quality-Overvaluation Wildcard has 4-star confidence and is not in your screening gate. It has held its direction (lower scores win) for 62 consecutive sessions. Every run you screen without it, you leave a validated signal unused. This is your clearest ADD candidate right now. || SM3: Quality-
✓Avg. EPS Growth★★★★☆ · higher wins · in_gate=yes
4-star | higher wins | 0 sessions held | IN GATE | control agrees · Avg. EPS Growth is in your gate but its direction is AT RISK — the last 30 consecutive runs of data are pointing the opposite way from what the gate is filtering. Every screening run using it may be filtering the wrong tickers. Consider suspending it from gate decisions until the conflict resolves (
✓RSI-Net EBITDA Signal★★★★☆ · higher wins · in_gate=yes
4-star | higher wins | 30 sessions held | IN GATE | control disagrees · RSI-Net EBITDA Signal has been in your gate for 30 sessions but the 500-stock random control group consistently disagrees with its direction. Historical winners passed this rule, but random stocks that also passed it are keeping pace or outperforming. The rule may be less predictive than it looks. W
SIL — Top Combos
✓Quality Value Score + Avg. EPS Growth + RSI-Net EBITDA Signal + FCF Quality Scorewin ?% · ?
n: ? · ctrl_n: ? · score: ?
✓FCF Efficency + Quality Value Score + Avg. EPS Growth + RSI-Net EBITDA Signalwin ?% · ?
n: ? · ctrl_n: ? · score: ?
✓Quality Value Score + Avg. EPS Growth + FCF-EBITDA Convergence Score + RSI-Net EBITDA Signalwin ?% · ?
n: ? · ctrl_n: ? · score: ?
✓Quality Value Score + Avg. EPS Growth + RSI-Net EBITDA Signalwin ?% · ?
n: ? · ctrl_n: ? · score: ?
✓Avg. EPS Growth + RSI-Net EBITDA Signal + FCF Quality Scorewin ?% · ?
n: ? · ctrl_n: ? · score: ?
Gate Alerts (9)
★SM3: Quality-Overvaluation WildcardADD · in_gate=no · BF#3
Score=50/100 (MPS:30 D:0 Ctrl:0 BF:20). MPS: B (67.45). Direction: accurate. Control: disagrees (higher, sep=6.42pp · strong). BF rank #3.
★Risk to Value GrowthADD · in_gate=no · BF#4
Score=50/100 (MPS:30 D:0 Ctrl:0 BF:20). MPS: B (70.72). Direction: not_enough_data. Control: disagrees (lower, sep=10.49pp · strong). BF rank #4.
⚠Avg. EPS GrowthREVIEW · in_gate=yes · BF#7
Direction AT_RISK — capped at REVIEW regardless of evidence score. Score=52 (MPS:18 D:0 Ctrl:20 BF:14). Control: agrees (higher, sep=13.02pp · strong).
★Quality Value ScoreADD · in_gate=no · BF#8
Score=78/100 (MPS:30 D:14 Ctrl:20 BF:14). MPS: B (64.44). Direction: accurate. Control: agrees (lower, sep=10.93pp · strong). BF rank #8.
★P/BADD · in_gate=no · BF#32
Score=60/100 (MPS:40 D:20 Ctrl:0 BF:0). MPS: A (75.07). Direction: accurate. Control: disagrees (lower, sep=17.97pp · strong). BF rank #32.
★ROIADD · in_gate=no · BF#41
Score=80/100 (MPS:40 D:20 Ctrl:20 BF:0). MPS: A (91.67). Direction: accurate. Control: agrees (lower, sep=33.18pp · strong). BF rank #41.
⚠ROIC-EBITDA Quality CompositeREVIEW · in_gate=yes · BF#44
Score=20/100 (MPS:0 D:20 Ctrl:0 BF:0). MPS: F (28.23). Direction: accurate. Control: disagrees (lower, sep=2.24pp · moderate). BF rank #44.
★ROICADD · in_gate=no · BF#62
Score=80/100 (MPS:40 D:20 Ctrl:20 BF:0). MPS: A (93.33). Direction: accurate. Control: agrees (lower, sep=33.18pp · strong). BF rank #62.
★ROICADD · in_gate=no · BF#77
Score=0/100 (MPS:0 D:0 Ctrl:0 BF:0). MPS: n/a (n/a). Direction: not_enough_data. Control: disagrees (lower, sep=33.18pp · strong). BF rank #77.
Metric Build Recs
Top SUPER METRIC PROMPT (ctrl_n ≥ 10)
✓Quality Value Score + Avg. EPS Growth + RSI-Net EBITDA Signal + FCF Quality Scorescore=79.62 · holdings=88.46% (n=26) · ctrl=84.62% (n=13)
k=4 · direction: INVESTIGATE
Direction Alerts (13)
⚠ROIC Cap ValuationINVESTIGATE · conf=n/a
Signals split — Control says (d=None, n=0out/0under, sep=n/a), Cohen's says higher (d=0.8061, n=29w/312l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠SM Watson 5INVESTIGATE · conf=n/a · ⚠ AT RISK
Signals split — Control says lower (d=-0.17, n=52out/133under, sep=5.78pp · strong), Cohen's says higher (d=0.14, n=31w/294l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠ROIC-FCF Quality GateINVESTIGATE · conf=n/a · ⚠ AT RISK
Signals split — Control says lower (d=0.0604, n=78out/228under, sep=2.70pp · moderate), Cohen's says higher (d=0.8743, n=28w/318l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠Watson-ROIC Confidence IndexINVESTIGATE · conf=n/a · ⚠ AT RISK
Signals split — Control says (d=None, n=0out/0under, sep=n/a), Cohen's says higher (d=0.8559, n=29w/304l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠SM3: Quality-Overvaluation WildcardINVESTIGATE · conf=n/a
Signals split — Control says higher (d=-0.0429, n=49out/139under, sep=6.42pp · strong), Cohen's says lower (d=-0.4154, n=29w/255l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠Rev Growth EfficiencyINVESTIGATE · conf=n/a
Signals split — Control says lower (d=-0.3639, n=61out/154under, sep=8.23pp · strong), Cohen's says higher (d=0.31, n=29w/280l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠Avg. EPS GrowthINVESTIGATE · conf=n/a · ⚠ AT RISK
Signals split — Control says higher (d=0.299, n=99out/229under, sep=13.02pp · strong), Cohen's says lower (d=-0.0471, n=31w/340l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠ROIC-EBITDA Quality CompositeINVESTIGATE · conf=n/a
Signals split — Control says lower (d=-0.3761, n=50out/140under, sep=2.24pp · moderate), Cohen's says higher (d=0.509, n=29w/290l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠ROI Liquidity / FCFINVESTIGATE · conf=n/a · ⚠ AT RISK
Signals split — Control says lower (d=-0.5321, n=30out/108under, sep=0.96pp · weak), Cohen's says higher (d=0.7371, n=27w/262l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠RSI x Avg Eps GrowthINVESTIGATE · conf=n/a · ⚠ AT RISK
Signals split — Control says higher (d=0.3994, n=99out/229under, sep=18.94pp · strong), Cohen's says lower (d=-0.0237, n=31w/340l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠Beta x ROE x EV/EBITDAINVESTIGATE · conf=n/a
Signals split — Control says lower (d=-0.1288, n=54out/148under, sep=0.55pp · weak), Cohen's says higher (d=0.342, n=31w/306l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠Risk to Value GrowthINVESTIGATE · conf=n/a
Signals split — Control says lower (d=0.3792, n=127out/367under, sep=10.49pp · strong), Cohen's says higher (d=0.2636, n=31w/351l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
⚠RSI-Net EBITDA SignalINVESTIGATE · conf=n/a
Signals split — Control says lower (d=-0.0489, n=127out/367under, sep=20.90pp · strong), Cohen's says higher (d=0.1732, n=31w/358l). Manual review required before any flip. · Resolution: Control group is primary signal (N≥50, unbiased). Cohort (secondary metrics) disagrees. Control direction holds by default. Watch: if cohort reaches 10+ consecutive opposing sessions + |d| >= 0.15 -> bring to user. User decides whether to align with cohort or trust control.
Open Tasks (4)
CRITICAL + VERY HIGH + HIGH from TASKS.md
Open TASKS.md →·[BUILD] 5 G-fixes for dormant-subsystem silent-drift class of failure — preventi…
[BUILD] 5 G-fixes for dormant-subsystem silent-drift class of failure — prevention machine controls — 2026-05-22. Why CRITICAL (Q1 — class-of-failure prevention; almost caused data-integrity event today): GDE near-miss postmortem (references/INCIDENT_POSTMORTEM_2026-05-22_dormant_system_silent_drift.md) revealed system has zero machine signal for (G1) replicated canonical formulas drifting silently — GDE's hardcoded composite_score replication was wrong for 28 days because Gate Alts swapped MPS→SIL and nothing scanned for replication sites; (G2) BUILD_*.md plans accumulating false premises across dormancy — v2 plan's M-of-N parity claim was false from day one; (G3) subsystem unique-value condition not validated — GDE's bucket-override capability is currently dormant (no qualifying metric) but system would have happily re-invested ~5-7h; (G4) no-placeholder mobile CHECK (already filed as HIGH today — Phase 2 of placeholder kill); (G5) references/SUBSYSTEM_ROLES.md doc — codify each subsystem's unique question + when it earns its keep. Build: (G1) CHECK in mde_health_check.py — scan for "replicated from" / "mirrors" comments + function-signature replication; ERROR if canonical mtime > replica mtime; (G2) CHECK + session-digest section — for every open references/BUILD_*.md age > 30d, WARN "re-validate premises before resume"; (G3) new UNIQUE_VALUE_FIRES_WHEN field in PROJECT_MAP subsystem entries + CHECK validates condition currently fires; if dormant > 30d → deprioritization-review prompt; (G4) reuse Phase 2 of placeholder-kill plan; (G5) write SUBSYSTEM_ROLES.md, list every active subsystem with its unique-question + earning-conditions + relationship to other subsystems. Why CRITICAL not HIGH: the next dormant subsystem could just as easily corrupt a primary dashboard if auto-promotion logic ships before this CHECK exists. Same root cause as 2026-03-28 FIELDNAMES contract incident. *Filed 2026-05-22 from postmortem.*
·[DECISION] GDE path forward — (A) kill / (B) harvest composite_score extraction …
[DECISION] GDE path forward — (A) kill / (B) harvest composite_score extraction only / (C) full sweep-revised v2 plan — 2026-05-22. Why CRITICAL (Q1 — decision gates the SHADOW Phase D path): /sweep on BUILD_gde_v2_remaining_gaps_20260424.md revealed plan is structurally compromised: stale composite formula, false M-of-N premise, zero verification tests, governance violations. GDE's unique value (bucket-override for 5★ bucket-blocked metrics) is currently dormant. Three paths: (A) kill GDE entirely (~30 min — close 4 GDE tasks, delete mde_08, kill mobile gdedisc card + DESKTOP_COPIES entry + dashboard); (B) harvest composite_score extraction only into SHADOW Phase D (~1.5h — clean win, gives SHADOW 7th component a canonical home); (C) full sweep-revised v2 (~5-7h — hard to justify given dormant unique value). Recommendation: (B). Decision blocks both SHADOW Phase D execution path (needs to know where composite lives) and how to scope/close 4 open GDE tasks. *Filed 2026-05-22 from /sweep result + postmortem.*
·[BUILD] SIL Output Quality + Audit Trail Closure — execute Streams 2 + 1 — 2026-…
[BUILD] SIL Output Quality + Audit Trail Closure — execute Streams 2 + 1 — 2026-05-22. Why CRITICAL (Q1 — autonomous SIL wiring gate; data-integrity prerequisite for Phases 2-5): references/BUILD_sil_intent_vs_actual_closure_20260516_v2.md was PARKED 2026-05-16 by user direction. Un-parked 2026-05-22 after /sweep re-validation confirmed plan still functions; v2.1 patch block applied (CHECK 51-55 → 73-77 renumber, Step 0.1/0.2/0.6 marked shipped, new Step 0.2b unit test, line-ref refresh, governance hooks). Phase 0 remaining: 0.0a snapshot, 0.0b ground-truth violation count, 0.2b unit test creation, 0.3+0.4 evidence_refs deposit writer + backfill, 0.7 UNHOOK_LOG entries, 0.8 CHANGELOG, 0.9 PROJECT_MAP. Then Phase 1 (P2 WARN→BLOCK flip). Total ~3-4h, LOW risk. Gates downstream Phase 2-5 (authority hierarchy, decision lineage, synthesis, autonomous promotion). Pre-execution: /risk-check on revised plan before Phase 0 first Edit. *Un-parked 2026-05-22 after /inspect + /sweep + delta application.* *(auto-moved from VERY HIGH 2026-05-22 — user-approved promotion: digest flag; prior "closed" annotation stripped — no matching CHANGELOG entry confirmed false-positive)*
·[BUILD] Wire SHADOW gate-accuracy into Gate Alternatives composite_score (7th co…
[BUILD] Wire SHADOW gate-accuracy into Gate Alternatives composite_score (7th component) — 2026-05-09. Why CRITICAL (Q1 — closes the only empirical gate-validation feedback loop; north-star aligned): SHADOW is the only subsystem that empirically answers "did our gate actually predict winners?" Yet gate_alternatives.py:1179-1273 composite_score's 6 components are blind to it. Closes the SHADOW → SIL → Gate Alts feedback loop. Scope: 7th component "SHADOW gate accuracy" weighted ~10-15%, read via SIL. Was blocked by: [REVIEW] Phase D consumer audit — UNBLOCKED 2026-05-15 (Phase D shipped per CHANGELOG line 767) + 2026-05-21 (SIL load_rec_events() magnitude guard shipped — completes the reader-side closure). Ready to execute. *Surfaced 2026-05-09 Session 207.* *(auto-moved from HIGH 2026-05-21 — user-approved promotion: compounds today's SIL ship)* *(blocker-status reconciled 2026-05-21 via /align triage)* *(auto-moved from VERY HIGH 2026-05-22 — user-approved promotion: digest flag)*
Recent Plans (5)
·ingest-review-assess-determine-cozy-eclipse.md2026-04-26
Path: ~/.claude/plans/ingest-review-assess-determine-cozy-eclipse.md
·mellow-painting-sphinx.md2026-04-26
Path: ~/.claude/plans/mellow-painting-sphinx.md
·go-into-plan-mode-eager-coral.md2026-04-26
Path: ~/.claude/plans/go-into-plan-mode-eager-coral.md
·ok-lets-assess-the-sharded-canyon.md2026-04-24
Path: ~/.claude/plans/ok-lets-assess-the-sharded-canyon.md
·rippling-waddling-haven.md2026-04-24
Path: ~/.claude/plans/rippling-waddling-haven.md
Governance Reminders
·Pre-BuildQ0–Q9 in investments/CLAUDE.md
Run before any new build/script/dashboard. Pre-Build Assessment fires Q0 (LESSONS_LEARNED) → Q9 (Constitution).
·Pre-FixSteps 1–6 in investments/CLAUDE.md
Run before modifying any existing file. Visible checklist required, not prose.
⚠run_pipeline.pyExplicit "yes go ahead" required
Master orchestrator — Danger Zone. Present full plan, wait for unambiguous approval, do not infer from context.
·/risk-check skillFires full Pre-Build + Pre-Fix in one pass
Run before any build or fix. Skill: ~/.claude/skills/risk-check/SKILL.md