brd-proposal

Author the programme-level effort proposal for the resolved BRD container: $ARGUMENTS

Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.

/brd-proposal is the programme effort-proposal step (PM phase) — it takes one BRD- container and writes the document a vendor sends a customer for the whole programme, by rolling each slice's own proposal.md into one. It prices nothing itself: every slice's hours were computed by /product-workflows:prd-proposal on that slice, and this run reads them. The canonical shape of both artifacts — their section sets, the two identifier namespaces, the readiness tiers, the confidence grades, the closed evidence set, and §14's umbrella rules — is ${CLAUDE_PLUGIN_ROOT}/references/proposal-format.md. This command executes that file; it never restates it.

Usage: /brd-proposal <ADDRESS> [--no-brief] [--profile] [--redo]

/brd-proposal's natural altitude is the root, joining /brd-intake and /brd-split — the route's other four commands, /prd-ground, /brd-interview, /brd-package and /brd-reconcile, each refuse a container and demand a slice, and this one inverts that. It takes no --baseline: a prior estimate reconciles against the slice that was estimated, not against the umbrella over it.

<ADDRESS> resolves through workflows-core:addressing §3 resolve-address, taken after $SPECS_PATH is settled — a resolution taken before the variable is known returns absent for a folder that exists, which is the ordering /create-prd and /create-ard state for the same reason.

This command gates nothing on the build ladder and nothing on it waits. It gates its own input — each included slice's proposal.md — and nothing beyond it. No command of the build ladder reads a proposal, and every targeted read of the umbrella this run writes is an own-folder one — a later run of this same command, anchoring its re-estimate on it (§8), and proposal-reviewer inside this run (Phase 10); /product-workflows:brd-reconcile's stale cross-reference sweep reads it only as prose, among every file under the parent, and never edits it: /create-ard, /specify, /epics, /dev-workflows:design, /dev-workflows:implement and /dev-workflows:ready each resolve a slice folder and neither know nor care whether anything above it holds a proposal, and no readiness tier withholds permission to build. The umbrella offers no forward advance — it is the end of this branch, not a phase in the build ladder. A proposal is a document a vendor sends a customer.

No money for human hours, at any tier, under any flag — no rate, no currency symbol, no monetary total, in either artifact or in the profile (${CLAUDE_PLUGIN_ROOT}/references/proposal-format.md §1). The USD figures this run emits at the end are model spend and are a different quantity.

Both artifacts are prose, and prose is never hard-wrapped — one unbroken line per paragraph, per workflows-core:prose-formatting, so a straight copy-paste into a review tool or a message needs no cleanup. This governs what the run writes; this command file itself stays wrapped like its neighbours.

There is no writer agent, and that is deliberate. The umbrella is authored inline by this command, exactly as /prd-proposal authors the slice proposal: the authoring is the command's purpose, and a handoff to a writer would only add a place for the resolved data set to be lost between derivation and rendering.

This command takes no --no-docs and does no documentation grounding at all. That is a decision, not an omission. docs-grounder retrieves shipped product-documentation pages, which bear on how a feature is described and not at all on what it costs to build — and this run's inputs are narrower still: the slice proposals, the root ledger and the profile. There is no flag to turn off, no resolve-docs-grounding call, and no docs grounding: line in this command's report.