@mindrian_os/cli 2.0.0-beta.3 → 2.0.0-beta.31

package/templates/room-skeleton/section-contracts/competitive-analysis.md

@@ -0,0 +1,33 @@
+# competitive-analysis - who else, what survives copying
+
+**Statement:** This section holds who else is solving this, and what would still be true if a competitor copied us.
+
+One job: hold who else is solving this, and what would still be true if a competitor copied us.
+
+## Inputs
+- Working (this room): `solution-design/`'s claimed defensibility. This is the reciprocal half of the moat cross-link: `solution-design` records the claim that a technical choice enables a feature that is hard to copy; this section is where that claim gets tested against a real competitor.
+- Working (this room): `market-analysis/`'s segments.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the financial model or the legal structure. Competitive positioning is about the market, not the numbers or the paperwork behind it.
+
+## Process
+1. Enumerate real competitors.
+2. Compare on the dimension the customer actually buys on, not the dimension easiest to compare.
+3. Test the `solution-design` moat claim against them: does the claimed defensibility survive the strongest competitor named here?
+
+## Outputs
+- One folder per artifact at `competitive-analysis/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- Take the defensibility claim recorded in `solution-design` and ask whether it survives the strongest competitor named here. If it does not, the claim is a feature, not a moat, and `solution-design` needs updating.
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): `/mos:compare-ventures`
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:challenge-assumptions`
+
+Note: the Reverse Salient family moved to `strategy` in Phase 275 (D-06).

package/templates/room-skeleton/section-contracts/financial-model.md

@@ -0,0 +1,30 @@
+# financial-model - the numbers and what breaks them
+
+**Statement:** This section holds the numbers, the assumptions under them, and what breaks them.
+
+One job: hold the numbers, the assumptions under them, and what breaks them.
+
+## Inputs
+- Working (this room): `business-model/`'s revenue model; `market-analysis/`'s sizing.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the funding pipeline. That is `funding/`, a separate section as of Phase 275: this model says what the venture needs, the pipeline tracks where the money is coming from.
+
+## Process
+1. Build the projection.
+2. Surface every assumption it rests on.
+3. Name the assumption that breaks it first.
+
+## Outputs
+- One folder per artifact at `financial-model/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- Change the single most load-bearing assumption by half and see whether the conclusion survives. If the model has no such assumption identified, it is not finished.
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): none direct today. This section relies on the wildcard `/mos:build-thesis`, which produces to `room/**/thesis/*`, plus the grading commands. Also a named structural gap.
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:build-thesis`, `/mos:grade`, `/mos:deep-grade` (the PWS Triple Validation Compass, specifically its "Is It Worth It" gate)

package/templates/room-skeleton/section-contracts/funding.md

@@ -0,0 +1,41 @@
+# funding - the pipeline from discovery to outcome
+
+**Statement:** This section tracks funding paths, dilutive and non-dilutive, from discovery through submission to outcome.
+
+One job: track funding paths from discovery through submission to outcome, so no deadline is missed and no application is silently abandoned.
+
+## Inputs
+- Working (this room): `financial-model/`'s stated need (how much, by when).
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+**Reads from:** `opportunity-bank/`. Every entry here starts life as a banked opportunity promoted by `/mos:funding create`, and carries a `[[opportunity-bank/<source>]]` wikilink back to its discovery.
+
+Do NOT load: the financial model's internals. This section tracks where money comes from, not what the venture does with it.
+
+## Process
+1. Promote: `/mos:funding create <opportunity-slug>` moves an opportunity from `opportunity-bank/` into this pipeline at initial stage Discovered.
+2. Advance: move a funding entry to the next stage. Stage and outcome are two orthogonal dimensions, named separately because conflating them is the error the command's own Design Note exists to prevent:
+   - **Stage** is lifecycle position, sequential and enforced: Discovered, then Researched, then Applying, then Submitted. No skipping. No going backward. Each transition is recorded in `transition_history`.
+   - **Outcome** is the result, not a stage: `awarded`, `rejected`, `withdrawn`. `awarded` and `rejected` are only valid once an entry has reached Submitted; `withdrawn` is valid at any stage.
+3. Record outcome once a result exists.
+
+The full sub-schema lives in `../references/SUB-SCHEMAS.md`; this contract points at the schema rather than duplicating it.
+
+**Scope: two funding types, one implemented.** The 2026-04-14 primary source nests exactly two types under Funding Options: **Dilutive Funding** (equity and venture capital; you give up ownership) and **Non-Dilutive** (grants and similar; you do not). This section's contract covers both. The command surface today implements only the non-dilutive half: `/mos:funding` and `/mos:opportunities scan` are 100 percent Grants.gov and Simpler-Grants sourced, with zero equity, VC, loan, crowdfunding or angel support (grep-confirmed). Dilutive tracking is a named, deliberate deferral from Phase 275, not an oversight and not a claim that dilutive funding does not matter. Until it is built, record dilutive conversations as ordinary dated entry folders in this section; they will not have a stage machine.
+
+Honest command gap: ground truth is none today. No methodology command produces directly into this section. That absence is exactly what the icm-architect audit found at the room level (an empty `funding/` shell) and what the command sweep confirmed at the command level; the two are the same gap seen from two angles.
+
+## Outputs
+- One folder per artifact at `funding/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- For every entry not at Submitted, is there a next action with a date on it. An entry that has not moved in fourteen days is either dead or being avoided; say which.
+
+## Commands that write here
+- Ground truth: none today.
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:mullins`, `/mos:grade`, `/mos:deep-grade`
+- Utility surface (operates on the pipeline rather than producing methodology content into it): `/mos:funding`

package/templates/room-skeleton/section-contracts/legal-ip.md

@@ -0,0 +1,30 @@
+# legal-ip - structure, agreements, what is protected
+
+**Statement:** This section holds the legal structure, the agreements, and what is actually protected.
+
+One job: hold the legal structure, the agreements, and what is actually protected.
+
+## Inputs
+- Working (this room): `solution-design/`'s technical choices (what is patentable or trade-secret depends on them); `business-model/`'s revenue model (what needs contracting).
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: market sizing or competitive positioning. Those live in `market-analysis/` and `competitive-analysis/`.
+
+## Process
+1. Name the entity.
+2. Name the agreements.
+3. Name the IP position and the regulatory surface, using the 2026-04-14 Notion primary source's own four nested sub-areas under Legal Docs as the working structure: Regulatory Compliance, Incorporation docs, Contracts and Agreements, Intellectual Property.
+
+## Outputs
+- One folder per artifact at `legal-ip/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- For each thing claimed as protected, name the mechanism and its expiry.
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): none today. No methodology command produces directly into this section. This is a real, named structural gap (SEED-084 `## ADDENDUM 2026-09-04e`), not an omission in this contract.
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:challenge-assumptions` (Red Teaming, whose risk-surfacing fits legal and IP exposure review)

package/templates/room-skeleton/section-contracts/market-analysis.md

@@ -0,0 +1,32 @@
+# market-analysis - who has it, how many, doing what
+
+**Statement:** This section holds who has this problem, how many of them there are, and what they do about it today.
+
+One job: hold who has this problem, how many of them there are, and what they do about it today.
+
+## Inputs
+- Working (this room): `problem-definition/`'s stated problem.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the funding pipeline, or marketing and sales strategy. Marketing and Sales is a real, deliberately deferred gap: the 2026-04-14 Notion primary source names a distinct "Marketing & Sales" section (Marketing Strategies, Sales Strategies & Pipelines) that Phase 275 chose NOT to build. Do not silently absorb that content into this section; if it shows up, name it as belonging to a section that does not exist yet, rather than filing it here.
+
+## Process
+1. Size the market: how many people or organizations actually have this problem.
+2. Segment it: which of them are alike enough to sell to the same way.
+3. Name the job being hired for: the outcome the segment is actually paying to get, not the feature they ask for.
+
+## Outputs
+- One folder per artifact at `market-analysis/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- Is there a real number here, sourced, or is an adjective standing in for one?
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): `/mos:analyze-needs` (produces `room/market-analysis/jtbd-analysis/*`, refiled here from `team-execution` in Phase 275 per D-05), `/mos:user-needs`
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:macro-trends`, `/mos:analyze-timing`, `/mos:diffusion`, `/mos:explore-trends`, `/mos:dominant-designs`, `/mos:mullins`
+
+Note: `/mos:scenario-plan` used to be cited here under the dead slug `scenario-analysis` and now lives in `strategy` (D-05, D-06).

package/templates/room-skeleton/section-contracts/opportunity-bank.md

@@ -0,0 +1,39 @@
+# opportunity-bank - the opportunities found but not yet chosen
+
+**Statement:** This section banks the opportunities found but not yet chosen, each with its Knight position and confidence.
+
+One job: bank the opportunities found but not yet chosen, so none is lost and none is prematurely committed to.
+
+## Inputs
+- Working (this room): `problem-definition/`'s ladder position; `market-analysis/`'s segments; external grant discovery via `/mos:opportunities scan` against Grants.gov and Simpler Grants.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the funding pipeline's own stage state. That is `funding/`'s job; this section holds candidates, not applications.
+
+## Process
+1. Bank each opportunity with its Knight position and confidence score. Do not collapse risk and uncertainty into a single undifferentiated "opportunity."
+2. Keep the two source kinds distinguished: grant-sourced (via `/mos:opportunities scan`) and cascade-sourced (extracted automatically by any methodology command that triggers analyze-room).
+3. Promote only when a candidate earns it, never on a timer.
+
+Quoted verbatim from `commands/opportunities.md:60`: every opportunity carries a Knight position (risk vs uncertainty vs mixed) and a confidence score. Risk is a known problem with quantifiable odds. Uncertainty is an unknown problem requiring exploration. Mixed is a contradiction that could go either way. The full sub-schema (Knight position plus confidence score, and the two source kinds) lives in `../references/SUB-SCHEMAS.md`; this contract points at the schema rather than duplicating it.
+
+**Feeds:** this section feeds `funding/`. `/mos:funding create <opportunity-slug>` promotes a banked opportunity into the funding pipeline at initial stage Discovered, and writes a `[[opportunity-bank/<source>]]` wikilink from the funding entry back to this one, creating a real graph edge back to the discovery. That wikilink is the existing cross-reference mechanism; no other syntax is invented here.
+
+Ground this section's own standing, honestly and briefly: this is the only one of the three sections Phase 275 adds that has a verbatim book-canon hit. Theo's `growth` chapter names "build a bank of opportunities" as the defining action of the Ill-Defined rung of the PWS ladder.
+
+## Outputs
+- One folder per artifact at `opportunity-bank/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- For each banked opportunity, is the Knight position argued or just asserted. A confidence score with no reason behind it is a number, not a judgment.
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): `/mos:futures`, `/mos:score-innovation`, `/mos:trending-to-absurd`, `/mos:whitespace`
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:explore-futures`
+- Utility surface (operates on the bank rather than producing methodology content into it): `/mos:opportunities`
+
+Note: `/mos:trending-to-absurd` used to be cited under `problem-definition` and was refiled here in Phase 275 (D-05), because that is where it actually produces.

package/templates/room-skeleton/section-contracts/problem-definition.md

@@ -0,0 +1,32 @@
+# problem-definition - the problem, not a solution
+
+**Statement:** This section holds the problem this venture is actually trying to solve, stated so a stranger can restate it.
+
+One job: hold the problem this venture is actually trying to solve, stated so a stranger can restate it.
+
+## Inputs
+- Working (this room): meeting notes and uploads in `meetings/`, and this room's own `STATE.md` venture stage.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the solution. That is `solution-design/`'s job. Pulling solution content in here is the single most common way a problem write-up quietly turns into a solution pitch.
+
+## Process
+1. State the problem in one sentence, the way it would be said to a stranger with no context.
+2. Place it on the PWS ladder: Un-Defined, Ill-Defined, or Well-Defined. Wicked is not a fourth, co-equal rung; it is a score-triggered escalation off any of the three, for a problem that resists decomposition.
+3. Decompose the stated problem into its parts only after it is placed on the ladder. Do not decompose before placing it, and do not let the decomposition quietly restate the solution instead of the problem.
+
+## Outputs
+- One folder per artifact at `problem-definition/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- Does this read as a problem, or as a solution wearing a problem's clothes?
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): `/mos:beautiful-question`, `/mos:diagnose`, `/mos:explore-domains`
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:root-cause`, `/mos:causal`, `/mos:map-unknowns`, `/mos:build-knowledge`, `/mos:validate`, `/mos:research`
+
+Note: `/mos:trending-to-absurd` used to be cited here and is NOT, as of Phase 275. It produces into `room/opportunity-bank/trending-to-absurd/*`; the misfiling was corrected in Phase 275 (D-05).

package/templates/room-skeleton/section-contracts/solution-design.md

@@ -0,0 +1,36 @@
+# solution-design - the solution and why
+
+**Statement:** This section holds the solution and the technical choices behind it, and why each choice was made.
+
+One job: hold the solution and the technical choices behind it, and why each choice was made.
+
+## Inputs
+- Working (this room): `problem-definition/`'s stated problem; `market-analysis/`'s named job.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the financial model.
+
+## Process
+1. State the solution.
+2. Name the technology stack.
+3. Name the features each stack choice enables. The 2026-04-14 Notion primary source nests Technology Stack directly beside Feature Planning under Solution and Product; that adjacency is why both live in this one section rather than split across two.
+
+## Outputs
+- One folder per artifact at `solution-design/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- **Moat:** does this technical choice enable a feature that is hard to copy, or does it just solve the immediate problem? If the answer is "hard to copy," `competitive-analysis` is the section that tests whether the claimed defensibility actually holds against a real competitor: record the claim here, run the test there.
+
+  The doctrine behind this question, quoted verbatim from this plugin's own `.claude/includes/moat.md`: "Prompts can be copied. The graph that knows WHEN to use WHICH prompt, in WHAT SEQUENCE, calibrated by REAL teaching data, is the moat." The same causal shape, a copyable surface plus an uncopyable underlying capability, applied one level down: to the venture this room holds, not to the plugin itself (Canon Part 6 dog-fooding).
+
+  Name this honestly: it is a repeated Larry heuristic, not a book-canon framework. It shows up in Lean Canvas's Unfair Advantage box, in Build-Thesis's "defensible go / no-go" tagline, and in Larry's own investment-mode line, "That's a feature, not a moat. What happens when someone copies it?" Theo's book has no dedicated moat chapter. State that plainly; do not present this heuristic as canon it is not.
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): `/mos:bono` (produces `room/solution-design/*`)
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:find-analogies`, `/mos:find-connections`, `/mos:analyze-systems`, `/mos:systems-thinking`, `/mos:hat-briefing`
+
+Note: the Reverse Salient family (`/mos:rs-experts`, `/mos:rs-explain`, `/mos:rs-fetch`) used to be framework-matched here and moved to `strategy` in Phase 275 (D-06), where it is ground truth instead.

package/templates/room-skeleton/section-contracts/strategy.md

@@ -0,0 +1,35 @@
+# strategy - the futures and the bottlenecks
+
+**Statement:** This section holds where this venture could go and what is holding it back: the scenarios and the reverse salients.
+
+One job: work the futures and the bottlenecks. Where could this venture go, and what is holding it back right now.
+
+## Inputs
+- Working (this room): `problem-definition/`'s ladder position (Scenario Planning addresses Un-Defined, Ill-Defined AND Wicked problems, so it is broadly applicable rather than narrow); `market-analysis/`'s trends; `solution-design/`'s current architecture (a reverse salient is usually a technical or organisational bottleneck inside it).
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the financial model. A scenario is a story about a plausible future, not a prediction with a number on it; do not turn scenarios into forecasts.
+
+## Process
+1. Find the reverse salient, the specific lagging component holding the whole system back (Thomas Hughes' bottleneck theory, the founding case).
+2. Build scenarios around it (Royal Dutch Shell's 1960s Group Planning department, the founding case).
+3. Name what each scenario would require you to decide differently.
+
+State the grounding for the pairing directly: the book's own graph asserts `Reverse Salient Analysis FEEDS_INTO Scenario Planning` with confidence 0.65 and the transform label `bottleneck-to-scenario`. These are not two unrelated tools filed under a label of convenience; the pairing is a graph-asserted relationship, not an engineering shortcut.
+
+Evidence-tier honesty, stated the way SEED-084 itself states it: `opportunity-bank` earned its place with a single verbatim book-canon hit defining one taxonomy rung; `strategy` is two strong, separately-chaptered frameworks that the book never groups under the name "Strategy." The organising label is a room-design choice; the two frameworks under it are canon. This is not inflated to canon it does not have, and it is not undersold either.
+
+## Outputs
+- One folder per artifact at `strategy/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- For each scenario, name the one thing that would have to be observed for you to believe it is the one actually happening. A scenario with no such signal is a story, not a planning tool.
+
+## Commands that write here
+- Ground truth (locked by D-06): `/mos:scenario-plan`, `/mos:find-bottlenecks`, `/mos:rs-experts`, `/mos:rs-explain`, `/mos:rs-fetch`, `/mos:rs-thesis`
+
+Note: the dead slug `scenario-analysis` was cited by `market-analysis`, `business-model` AND `financial-model`; its live replacement `/mos:scenario-plan` now has a proper home here rather than three patched citations. The Reverse Salient family, previously framework-matched for `competitive-analysis` and `solution-design` and ground truth nowhere, is ground truth here.

package/templates/room-skeleton/section-contracts/team-execution.md

@@ -0,0 +1,36 @@
+# team-execution - who works, who advises, what next
+
+**Statement:** This section holds who does the work, who advises it, and what happens next.
+
+One job: hold who does the work, who advises it, and what happens next.
+
+## Inputs
+- Working (this room): `meetings/` (the structural directory where conversations land); the room's `team/` directory.
+- Reference (every run): ../references/SECTION-SCHEMA.md
+- Reference (when relevant): ../references/SUB-SCHEMAS.md
+
+Do NOT load: the market analysis.
+
+## Process
+1. Name who does the work: roles, not just names.
+2. Name who advises it, using the Mentor-Profiles sub-structure below.
+3. Name what happens next: the concrete execution step each person owns.
+
+**D-12, stated explicitly:** Mentor-Profiles is real sub-structure of this section, not a gesture. A mentor profile carries who they are, what domain they cover (their role and their domain expertise), what question they are the right person to answer, their availability, and when they were last consulted, cross-linked back to the meeting or entry that consulted them. The full field list lives in `../references/SUB-SCHEMAS.md` (plan 275-07 writes it); this contract points at that schema instead of duplicating it.
+
+Three spellings are live in this room, named here because a reader will otherwise conflate them: `team-execution/` is this ICM section, a scored destination for methodology content. `team/` is a structural directory (`STRUCTURAL_DIRS`), holding the people layer and, via `/mos:persona`, AI personas at `team/ai-personas/`. `meetings/` is the other structural directory, a source that feeds sections, not a destination. Phase 275 changed none of these; they are named here because the fourth-spelling confusion was found in passing during D-05's citation sweep.
+
+## Outputs
+- One folder per artifact at `team-execution/<artifact-slug>/<artifact-slug>.md` (the Obsidian-nested convention, Key Decision 16). The folder IS the artifact.
+- Never inline content into `ROOM.md`. `ROOM.md` is ICM Layer 0 identity only: statement, purpose, stage relevance, default methodologies. Real content is ICM Layer 4 and lives in its own dated entry folder. Five of twelve sections in the audited `launchpad-02` room had already drifted this way; this line is why the contract exists.
+
+## Human check
+- Feynman: can a stranger restate this section's governing thought in one sentence, without jargon?
+- Minto: does the apex claim sit on MECE-grouped, non-overlapping support?
+- For each named person, is there one sentence saying what only they can answer?
+
+## Commands that write here
+- Ground truth (the command's own `produces` path names this section): `/mos:leadership`
+- Framework-matched (a wildcard command whose framework fits this section's job): `/mos:hat-briefing`, `/mos:think-hats`
+
+Note: `/mos:analyze-needs` used to be cited here and was refiled to `market-analysis` in Phase 275 (D-05), because that is where it actually produces.