feat(prioritize): make command workspace-agnostic (drop pillar-slug + sub-spike requirements)

CHANGELOG.md

@@ -18,6 +18,38 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+- **`/make-no-mistakes:prioritize` is now workspace-agnostic.** Drops four hard
+  couplings from the original dogfood design while preserving full backward
+  compatibility with `pillars.<slug>` configs:
+  - **Scope**: the first positional arg is now optional. Resolution order is
+    `pillars.<slug>` (legacy) → `projects.<slug>` (agnostic) → Linear MCP
+    `list_projects` exact-name match → interactive. Two new alternative
+    scope flags: `--label <name>` and `--filter <query>`.
+  - **Evidence anchor**: the required PIBER+IDCF sub-spike is now optional via
+    `--evidence <path-or-issue-id>`. Accepts a Linear issue ID OR a local
+    markdown path. Without it, evidence-driven MoSCoW rules are skipped and
+    RICE Confidence defaults to 0.8. Label-driven rules and LLM fallback
+    continue to work.
+  - **Vision audit**: auto-discovery at `<codebase>/audits/<pillar>/vision-audit-*.md`
+    only fires in legacy pillar mode. Agnostic mode requires the explicit
+    `--audit <path>` flag (no flag → no audit enrichment).
+  - **Output path**: default is now `./priority-<YYYY-MM-DD>.md` in cwd, with
+    `~/` expansion when `--out <path>` is provided. Legacy pillar mode keeps
+    the original `<codebase>/audits/<pillar>/priority-<DATE>.md` default.
+  - **Snapshot comment artifact**: posted on the `--evidence` Linear issue
+    when evidence is an issue ID; skipped when evidence is a local file or
+    absent. Legacy pillar mode continues to post on `pillars.<slug>.spike`.
+  - **MoSCoW rule split**: scoring rules are now annotated as
+    *evidence-driven* (skip when no anchor) vs *label-driven* (always fire).
+    New label-driven rules added for explicit `moscow/{must,should,could,wont}`
+    labels so that workspaces using MoSCoW labels directly get deterministic
+    coverage without needing an evidence anchor.
+
+  Rationale: the original command was opinionated against a pillar taxonomy
+  that does not exist in typical Linear workspaces (per Andrés analysis,
+  2026-06-02). Dogfood configs continue to work unchanged.
+
 ## [1.35.0] - 2026-07-29
 
 ### Added

README.md

@@ -80,7 +80,7 @@ Deliberate actions you invoke explicitly.
 | Command | Description |
 |---------|-------------|
 | [`/make-no-mistakes:implement <ISSUE-ID>`](commands/implement.md) | Disciplined execution of Linear issues — worktree isolation, all-reviewer loops, CI verification, clean merges |
-| [`/make-no-mistakes:prioritize <pillar-slug>`](commands/prioritize.md) | MoSCoW + RICE-adapted applied to a pillar's Linear issues, traceable to its PIBER+IDCF sub-spike and the latest vision audit. Outputs priority report + description-footer per issue + snapshot comment on the sub-spike. Chain: `product-vision-audit → prioritize → spike-recommend → implement` |
+| [`/make-no-mistakes:prioritize [scope]`](commands/prioritize.md) | MoSCoW + RICE-adapted applied to any slice of a Linear backlog. Workspace-agnostic: scope by project slug, `--label`, or `--filter`; a pillar taxonomy, a PIBER+IDCF sub-spike, and a vision-audit doc are all optional enrichment rather than requirements. Outputs priority report + description-footer per issue, and a snapshot comment when `--evidence` names a Linear issue. Legacy `pillars.<slug>` configs keep working unchanged |
 | [`/make-no-mistakes:rebase <repo>`](commands/rebase.md) | Team release sync — rebase all branches, auto-merge ready PRs, health report |
 | [`/make-no-mistakes:linear-projects-setup`](commands/linear-projects-setup.md) | Bootstrap Linear workspace with full label taxonomy, projects, and integrations |
 | [`/make-no-mistakes:e2e-test-builder <source>`](commands/e2e-test-builder.md) | Generate a TestSprite-compatible `test-suite.json` from docs or PRDs |
@@ -132,7 +132,7 @@ Auto-activate by context — you don't need to remember the command name.
 | [`audit-engine`](skills/audit-engine/SKILL.md) | Run any of the six repo-health audits (schema-drift, contract-drift, ddd, explicit-architecture, strangler, enforcement-hooks). Hybrid LLM-first detection + deterministic verification + cure-mapping |
 | [`domain-driven-advisor`](skills/domain-driven-advisor/SKILL.md) | Ask "which audit do I need?" / "where do I start with repo health?" — routes you to the right audit(s) and runs a premortem |
 | [`premortem`](skills/premortem/SKILL.md) | Say "premortem this", "what could kill this", "stress test this plan", "what am I missing", or "find the blind spots" on a plan/launch/decision |
-| [`prioritize`](skills/prioritize/SKILL.md) | Ask to "prioritize issues", "rank the backlog", "apply MoSCoW", or "RICE scoring" for a product pillar (suggests `/make-no-mistakes:prioritize`) |
+| [`prioritize`](skills/prioritize/SKILL.md) | Ask to "prioritize issues", "rank the backlog", "apply MoSCoW", or "RICE scoring" for any Linear project, label, or filter (suggests `/make-no-mistakes:prioritize`) |
 
 Skills can also be invoked explicitly: `/make-no-mistakes:spec-recommend T0-4`