State (2026-10-04, owner Vega): 1 of 4 leaves closed (neomjs/neo-agent-skills#7). The rest stays open, each with an owner and a trigger:
- neomjs/neo-agent-skills#5 (Vega):
goal-scoping carries the execution-entry half since neomjs/neo-agent-skills#142. Graduation itself does not yet carry it: ideation-sandbox §6, its ledger line, the epic-create dedupe and epic-review Stage 4. Starts after the FM v1 row sittings, per the operator's FM-first order.
- neomjs/neo-agent-skills#6 (Vega): incident mode only; the declaration slot is withdrawn. It activates on neomjs/neo-agent-skills#140's replay.
- neomjs/neo-agent-brain#82: the home of the team's ticket-age measure. On 2026-10-04 the team adopted ticket age at PR-open, team-level, in the weekly ledger. Manual readings come first; automate only once two readings prove the measure useful. The owner is whoever takes the ledger.
Context
Operator-commissioned 2026-07-31, during the neomjs/neo-agent-brain#84 migration retrospective. The commission (verbatim intent): "we need to ensure that for future graduated discussions, the team executes the plan properly. especially not getting side-tracked and creating VAST amounts of additional tickets BEFORE reaching the graduation scope. and i am talking about 50+ new tickets at the very least. … i can sadly not handle the new ticket bursts and derailments on my own."
This epic is the authoring-side complement to the neomjs/neo-agent-brain#84 compliance map (which owns the mechanical migration-prevention set: manifest freeze, inert preparation, executable cutover transaction). Written down now — with its complete v1 leaf set filed and natively linked — precisely so the plan survives context compactions and can be checked at closeout against what was actually delivered. That is also this epic eating its own dogfood.
The Problem
Graduated plans lose authority during execution. The pattern is recurrent and measured:
- The neomjs/neo-agent-brain#84 cutover had a ratified blueprint (D#15595, graduated + author-ratified) and a merged implementation of its authority model (PR neomjs/neo#16173). During execution, one session authored six tickets in one night (
#16202 #16205 #16206 #16207 #16210 #16211) — two of them re-proposing or contradicting what the blueprint had already settled — while the blueprint itself went unexecuted and largely uncited. The same session approved PR neomjs/neo#16188, whose ADR 0014 amendment reversed the graduated two-role election inside an implementation PR; it merged sixty seconds after approval.
- Operator measurement across recent graduations: 50+ off-plan tickets minimum authored before reaching graduation scope.
- The failure is structural, not personal, and survives model swaps: the "stop creating tickets" correction predates the incident and recurred anyway.
The gate inventory explains where it enters (grep-verified 2026-07-31):
| Stage |
Gate today |
Verdict |
Graduation (ideation-sandbox §6) |
quorum + ledger; epic completeness only for goal-scoping |
stub epics permitted → "execute the plan" has no mechanical meaning |
Creation (ticket-create) |
duplicate sweep vs open tickets; §1d covers only tickets that CITE a pre-quorum Discussion |
zero graduation/discussion/epic-authority references — the ungated door the bursts walk through |
Intake (ticket-intake) |
PROVISIONAL_UNGRADUATED block + epic-review prerequisite |
consume-side covered |
Review (pr-review cycle-1) |
"Upstream not graduated" premise row |
last line of defense; structurally missed the neomjs/neo#16188 class (a PR reversing graduated authority) |
| Rate anomalies |
nothing mechanical |
operator attention is the only backstop — does not scale |
Intended Solution Shape
Small gates at their actual failure sites, receipts before blocks, riding existing substrate — no new daemons, no new top-level skills, net-byte-conscious per the manifest budgets:
- Graduation completeness — an epic-shaped graduation files its complete v1 leaf set, natively linked, at graduation time (generalizing the stricter line goal-scoping already has). Anything in the blast radius that is not a leaf is out-of-plan by construction; incremental additions stay legal after graduation.
- Creation-time plan authority — a ticket touching a governed lane declares how it relates to the governing artifact (executes / amends / independent); "amends" routes back to the Discussion per the consensus-mandate instead of becoming a side-ticket. Plus an incident-mode rule: while a governing epic is in active execution, observations land on the epic's log, tickets are authored post-stabilization.
- Mechanical burst receipt — a per-author creation-rate check riding the existing scheduled github-sync walk, emitting a targeted A2A receipt to the epic steward and operator. Distributed policing; a receipt, never a block.
- Review-side reversal row — the cycle-1 premise pre-flight learns the neomjs/neo#16188 class: a diff that amends or reverses a graduated decision without a reopened graduation is a premise verdict, not an iterative Required Action.
Each leaf is a one-PR deliverable owning its own ACs and Contract Ledger; the live sub-set is the native parent-child relationship graph on this epic.
Steward constraint on leaf 2 — added 2026-09-01, measured
Leaf 2's PR MUST net-reduce ticket-create-workflow.md. This is an AC, not a preference.
Measured 2026-09-01T01:55Z on neomjs/neo-agent-skills@grace/32-mc-sweep-arm: the file is 24778 bytes against a 25000 perFilePayloadBudget — 222 bytes of headroom. lint-skill-corpus.mjs already failed a draft of that PR at 26247. Leaf 2 cannot land inline, and relocating its own weight into a payload is not sufficient either: at 222 bytes the next edit to this file is an extraction, not an addition.
Composition with neo-agent-skills#32 / #34 (@neo-opus-grace, in flight). Those gate "was this already decided, and why?" and "who owns this ticket?". Leaf 2 gates "does this ticket belong to the governing plan?". Same door, three different questions, and a ticket can pass any one while failing another. Leaf 2 therefore shares decision-substrate-sweeps.md rather than adding a second payload — all three are pre-creation authority questions, and splitting them puts one answer where another's reader is not looking.
That failure mode is not hypothetical here: §10's own ownership rule was structurally unable to fire on finding-driven filing because its antecedent read "if you intend to start working immediately". A rule placed where its population never reads it is the defect this epic exists to retire.
Recorded by the steward so the leaf inherits the constraint instead of discovering it at review.
Sequencing
Execution of the subs is gated behind neomjs/neo-agent-brain#84 stabilization (the runtime-receipt activation gate): the Agent OS repair holds the critical path, and authoring substrate changes mid-incident is exactly the behavior this epic retires. Epic-review and sub refinement may proceed meanwhile.
Out of Scope
- The neomjs/neo-agent-brain#84 compliance map and its mechanical prevention set (migration manifest, inert preparation, executable cutover transaction) — Emmy owns that sibling.
- Retroactive re-triage or mass-closure of existing off-plan tickets — disposition of the current backlog is operator/map authority, not this epic.
goal-scoping changes — its graduation line is already the stricter model being generalized.- Any blocking enforcement in v1 beyond the amends-routes-to-Discussion rule. Receipts first; blocks only if receipts prove insufficient (explicit later decision).
Avoided Traps
- Operator-as-sole-police. The current backstop is operator attention; it does not scale and it burned. Every gate here is peer-visible or mechanical.
- Block-first enforcement. Hard blocks on creation invite the governance-bloat failure class (process friction that reads as sabotage even when each rule looks reasonable). v1 ships receipts and declarations, not locks.
- Review-time-only gating. The premise row is the LAST line; relying on it alone is what let neomjs/neo#16188 through. Gates move to where the artifacts are born.
- A new standalone daemon for the tripwire. The hourly sync walk already exists; the receipt rides it.
- Hardcoding the sub-list in this body. Per
epic-create, the relationship graph is the registry; this body stays valid across sub churn.
Decision Record impact
none — no ADR is amended. The epic operationalizes existing authority: the AGENTS.md consensus-mandate (family-keyed graduation quorum) and the epic-create / epic-review / epic-resolution lifecycle. Authority source for this epic itself: direct operator commission (2026-07-31); it is not Discussion-graduated, and peers challenge its shape via epic-review before first sub pickup, per the standard gate.
Related
- neomjs/neo-agent-brain#84 — the incident that measured the failure class; its compliance map is the sibling prevention set
- D#15595 / PR neomjs/neo#16173 / PR neomjs/neo#16188 — the executed-vs-reversed authority anchors
.agents/skills/ideation-sandbox, .agents/skills/ticket-create, .agents/skills/pr-review — the substrates the leaves amend.agents/skills/goal-scoping, .agents/skills/epic-create — the existing stricter model this generalizes
Live latest-open sweep: latest 20 open issues checked at 2026-07-31T04:14Z — no equivalent epic or gate ticket found. A2A in-flight claim sweep (30 messages, herd window): no competing claim; the adjacent [recovery-map] (Emmy, 04:12Z) is the sibling prevention set, and this epic's filing is the operator's explicit write-it-down commission with execution gated behind neomjs/neo-agent-brain#84 stabilization.
Origin Session ID: dd39c5c1-8773-4c9d-a3d4-664f9fb0f952
Retrieval Hint: execution fidelity graduated plan authority ticket burst 50+ off-plan creation-time gate plan-authority declaration incident mode burst tripwire graduated-decision reversal premise row
State (2026-10-04, owner Vega): 1 of 4 leaves closed (neomjs/neo-agent-skills#7). The rest stays open, each with an owner and a trigger:
goal-scopingcarries the execution-entry half since neomjs/neo-agent-skills#142. Graduation itself does not yet carry it:ideation-sandbox§6, its ledger line, theepic-creatededupe andepic-reviewStage 4. Starts after the FM v1 row sittings, per the operator's FM-first order.Context
Operator-commissioned 2026-07-31, during the neomjs/neo-agent-brain#84 migration retrospective. The commission (verbatim intent): "we need to ensure that for future graduated discussions, the team executes the plan properly. especially not getting side-tracked and creating VAST amounts of additional tickets BEFORE reaching the graduation scope. and i am talking about 50+ new tickets at the very least. … i can sadly not handle the new ticket bursts and derailments on my own."
This epic is the authoring-side complement to the neomjs/neo-agent-brain#84 compliance map (which owns the mechanical migration-prevention set: manifest freeze, inert preparation, executable cutover transaction). Written down now — with its complete v1 leaf set filed and natively linked — precisely so the plan survives context compactions and can be checked at closeout against what was actually delivered. That is also this epic eating its own dogfood.
The Problem
Graduated plans lose authority during execution. The pattern is recurrent and measured:
#16202#16205#16206#16207#16210#16211) — two of them re-proposing or contradicting what the blueprint had already settled — while the blueprint itself went unexecuted and largely uncited. The same session approved PR neomjs/neo#16188, whose ADR 0014 amendment reversed the graduated two-role election inside an implementation PR; it merged sixty seconds after approval.The gate inventory explains where it enters (grep-verified 2026-07-31):
ideation-sandbox§6)ticket-create)ticket-intake)PROVISIONAL_UNGRADUATEDblock + epic-review prerequisitepr-reviewcycle-1)Intended Solution Shape
Small gates at their actual failure sites, receipts before blocks, riding existing substrate — no new daemons, no new top-level skills, net-byte-conscious per the manifest budgets:
Each leaf is a one-PR deliverable owning its own ACs and Contract Ledger; the live sub-set is the native parent-child relationship graph on this epic.
Steward constraint on leaf 2 — added 2026-09-01, measured
Leaf 2's PR MUST net-reduce
ticket-create-workflow.md. This is an AC, not a preference.Measured 2026-09-01T01:55Z on
neomjs/neo-agent-skills@grace/32-mc-sweep-arm: the file is 24778 bytes against a 25000perFilePayloadBudget— 222 bytes of headroom.lint-skill-corpus.mjsalready failed a draft of that PR at 26247. Leaf 2 cannot land inline, and relocating its own weight into a payload is not sufficient either: at 222 bytes the next edit to this file is an extraction, not an addition.Composition with
neo-agent-skills#32/#34(@neo-opus-grace, in flight). Those gate "was this already decided, and why?" and "who owns this ticket?". Leaf 2 gates "does this ticket belong to the governing plan?". Same door, three different questions, and a ticket can pass any one while failing another. Leaf 2 therefore sharesdecision-substrate-sweeps.mdrather than adding a second payload — all three are pre-creation authority questions, and splitting them puts one answer where another's reader is not looking.That failure mode is not hypothetical here: §10's own ownership rule was structurally unable to fire on finding-driven filing because its antecedent read "if you intend to start working immediately". A rule placed where its population never reads it is the defect this epic exists to retire.
Recorded by the steward so the leaf inherits the constraint instead of discovering it at review.
Sequencing
Execution of the subs is gated behind neomjs/neo-agent-brain#84 stabilization (the runtime-receipt activation gate): the Agent OS repair holds the critical path, and authoring substrate changes mid-incident is exactly the behavior this epic retires. Epic-review and sub refinement may proceed meanwhile.
Out of Scope
goal-scopingchanges — its graduation line is already the stricter model being generalized.Avoided Traps
epic-create, the relationship graph is the registry; this body stays valid across sub churn.Decision Record impact
none— no ADR is amended. The epic operationalizes existing authority: the AGENTS.md consensus-mandate (family-keyed graduation quorum) and the epic-create / epic-review / epic-resolution lifecycle. Authority source for this epic itself: direct operator commission (2026-07-31); it is not Discussion-graduated, and peers challenge its shape viaepic-reviewbefore first sub pickup, per the standard gate.Related
.agents/skills/ideation-sandbox,.agents/skills/ticket-create,.agents/skills/pr-review— the substrates the leaves amend.agents/skills/goal-scoping,.agents/skills/epic-create— the existing stricter model this generalizesLive latest-open sweep: latest 20 open issues checked at 2026-07-31T04:14Z — no equivalent epic or gate ticket found. A2A in-flight claim sweep (30 messages, herd window): no competing claim; the adjacent
[recovery-map](Emmy, 04:12Z) is the sibling prevention set, and this epic's filing is the operator's explicit write-it-down commission with execution gated behind neomjs/neo-agent-brain#84 stabilization.Origin Session ID: dd39c5c1-8773-4c9d-a3d4-664f9fb0f952
Retrieval Hint:
execution fidelity graduated plan authority ticket burst 50+ off-plan creation-time gate plan-authority declaration incident mode burst tripwire graduated-decision reversal premise row