← back to Docs source: system/specs/CONSEQUENCE.md

CONSEQUENCE — The Stakes Rubric and the One Dial

Status: DRAFT v2.0 — command-center reviewed 2026-07-20 · ML review pending What this is: the mechanical contract for evidence scales with consequence (LAWS.md). v1 hand-set fifteen per-gate thresholds and got them wrong in both directions — dead checks, overkill retire thresholds, threshold-1 build cliffs. v2 replaces the per-gate threshold table with one dial: grade the decision's stakes with five yes/no questions, read every control off the tier. The gate stays dumb everywhere; only its threshold moves.


1. The five questions

For any decision a gate must judge, answer five binary questions. No weights, no partial credit, no clever scoring — a yes-count. A counter cannot be argued with.

#QuestionYes when the decision…
Q1Does it touch a commit?…creates, changes, or removes permanent state: a page, a worker, a directive, a standard, a schedule, a config.
Q2Does it touch the world?…crosses the sandbox boundary: publishes, sends, posts, requests, purchases — anything an outsider can observe.
Q3Does it touch ML's attention?…pushes to ML: escalations, Discord pings, brief content, anything on the four-category contact surface.
Q4Does it touch privileged access?…uses or alters credentials, keys, payment instruments, publishing rights, or the grant ledger.
Q5Does it touch the values floor?…is within reach of a VALUES.md floor clause: proof-grade legality (VF1), scam-shaped presentation or transaction (VF2/VF3), operator-integrity invariants (reporting valence, granted perimeter). Quality/thin-content judgments are NOT Q5 — they are mission machinery graded by Q1/Q2.

Tier = the yes-count (0–5), with one override: a yes on Q5 sets tier 5 regardless of the other answers. Values-boundary touches are never averaged down by an otherwise-low-stakes decision.

One asymmetry modifier: a decommit (retire a worker, prune a page, revoke a capability, unpublish) grades one tier above the equivalent commit, capped at tier 4 (Q5 still owns tier 5). Removing capacity demands stronger evidence than adding it (SYSTEM.md §6); this is where that law becomes arithmetic.

Grading is mechanical: each gate's ramp-config entry carries its five pre-graded answers (stakes: [Q1..Q5]) reviewed at commissioning. Workers do not grade their own proposals; the gate reads the tier from config. A decision class whose answers change (e.g., a knowledge artifact starts feeding published pages) is re-graded through the worker-update path.

2. The tier table

The dial. Every control that used to be a hand-set per-gate constant reads off this row. Numeric values are launch defaults — placeholders pending calibration from deployment data [OPEN — flag for command center: the numbers, not the shape].

TierCorroboration threshold (distinct run × provenance pairs)Generation budgetReview requirementSpot-check samplingModel class allowed
01unbounded (sandbox economics)none2%script / DeepSeek-tier
12high — flood freelynone; reviewer samples5%DeepSeek-tier
23standard per-class budgetreviewer on sample10%GLM-tier
34, min_distinct_provenance ≥ 2reduced; per-item accountingreviewer required, every item25%GLM-tier (ceiling)
45, min_distinct_provenance ≥ 2, consecutive_runs ≥ 2minimal; each generation justifiedreviewer + command-center verdict100%command center
5n/a — default answer is BLOCKzero until clearedcommand center mandatory; ML notified (category-gated); unappealable in the operating layer100%command center only

Reading the columns:

Tier 5 semantics: a values-boundary touch is judged by the values gate first (GATES.md §6) — block + log, unappealable in the operating layer. What escalates is the question, not the action; the action waits. Bias toward inaction at the boundary (V6).

3. Migration table — the fifteen v1 hand-set thresholds → the dial

Grades shown as Q1 Q2 Q3 Q4 Q5 (Y/n). Where v2 differs from v1, that is the dial working: v1 numbers were cadence-denominated guesses; these are stakes-denominated.

v1 gatev1 settingStakes gradeTierv2 thresholdNotes
strategy-consensus3 / 7d consecutive-daysY Y n n n23, consecutive_runs per rampConsecutive runs replace calendar-day adjacency (audit R6).
playbook2 / 14d + AUTO_PASS_SOURCESY n n n n12The source: auto-pass bypass is deleted (GATES.md §5).
worker-create2 / 14d + budget 60/65Y n n n n12Budget cap survives as a deterministic pre-filter (§4).
worker-update3 / 14d + dead MIN_DAYSY n n n n12v1's 3 was a guess; dead-code MIN_DAYS deleted. Updates to workers holding elevated scope re-grade Q4=Y → tier 2.
worker-retire5 / 30d + 2 lensesY Y n n n2 +1 decommit → 34v1's 5 approximated the decommit asymmetry by hand; the modifier makes it systematic.
voice-pattern2 / 14dY n n n n12
concept map(template, ungated in v1 scripts)Y n n n n12Additive knowledge; ramp builds at 1, graduates on coverage-stabilized (Decision 19).
pulse(template, ungated in v1 scripts)Y n n n n12Internal knowledge only.
content-pruning2 / 30dY Y n n n2 +1 decommit → 34v1 undervalued removing live pages; pruning is a decommit of world-facing state.
rich-media-opportunity2 / 7d + 50/day capY n n n n12Daily cap survives as deterministic pre-filter, re-based to newly admitted keys (fixes audit R5).
rich-media-budgetpure budget filteroutside dialDeterministic filter, §4.
link-qualitytiered DA/spam auto-pass + 2-date borderlineborderline: Y Y n n n23DA/spam metric tier survives as deterministic pre-filter; only the borderline judgment is consensus.
link-building-strategy3 / 7dY Y n n n23Outreach touches the world.
personality-ethos2 / 14dY Y n n n23 (locked phase: ramp raises to tier-4 controls)Pre-lock-in the ramp phase drops to threshold 1 (personality is a correctable hypothesis); post-lock-in the ladder applies tier-4-equivalent settings — strongest consensus in the system. RESOLVED (ML, F3): locked-ethos changes are NOT values events — personality is fully system-governed through consensus gating; human input optional.
positioning-framework2 / 14dY n n n n12
domain-knowledge(template, ungated in v1 scripts)Y n n n n12

Grading notes:

4. What stays outside the dial

The dial governs consensus — how much corroboration a judgment needs. Deterministic filters are not consensus and are not on the dial. They remain plain scripts with config-file parameters, unchanged in kind from v1:

FilterParameters (in gate-ramp.yaml under params:)Character
rich-media-budgettotal_budget, conservation_at: 0.80, block_at: 1.00Arithmetic over spend records. Exit 4 on block.
link-quality DA tierauto_pass_da: 30, auto_pass_spam: 30, borderline boundsMetric comparison; only borderline cases enter consensus at tier 2.
worker-create budgetbudget_soft: 60, budget_hard: 65Census count vs. cap; counts commissioned workers from the census, never files in a directory (fixes audit R7).
rich-media daily capdaily_cap: 50Counts newly-admitted direction keys per UTC day.
velocity valvesper valve-mapTrust-canary-driven caps (V1 enforcement); close on degradation regardless of any tier.

A deterministic filter can block and can never pass anything into commit by itself — passing is the dial's job. Filters compose with the dial as pre-filters (cheaper check first) and their blocks are ledgered as verdict/block with the filter named in reason.

5. Interaction with the ramp

The tier is the steady-state setting. gate-ramp.yaml ladders (GATES.md §2) modulate within a tier during build — lower thresholds, mandatory reviewers as compensation, evidence-based graduation back to the tier row. The dial answers "how much evidence at maturity"; the ramp answers "how do we get there from a cold start." Neither overrides the other's column: a build-phase gate at threshold 1 still carries its tier's review requirement or stricter, and tier-5 semantics are never ramp-loosened.

Worked example: strategy-consensus in build phase sits at tier 2 (steady threshold 3). Its ladder's build phase runs threshold 2 with consecutive_runs: 2 — within the "at most 2 below steady, never below 1" floor — and graduates back to the tier row when market data is live and the first graded outcomes exist. The dial never moved; the ramp moved within it.

6. Amendment

The five questions and the Q5 override are doctrine — command-center proposal, ML-reviewed (they define contact with the values boundary). Tier-table numerics are calibration — command-center amendable with ledgered rationale and a trial where one is possible. Per-gate stakes grades live in gate-ramp.yaml and change only through the worker-update path with the new grade in the proposal.

Provenance: rubric from LAWS.md "evidence scales with consequence" and the three real surfaces (SYSTEM.md §8); v1 settings from the gate-mechanic audit §1.1; decommit asymmetry from SYSTEM.md §6; model columns from SYSTEM.md §7 (ML, locked).