feat(prioritize): make command workspace-agnostic (drop pillar-slug + sub-spike requirements) - #41
Open
lapc506 wants to merge 2 commits into
Open
feat(prioritize): make command workspace-agnostic (drop pillar-slug + sub-spike requirements)#41lapc506 wants to merge 2 commits into
lapc506 wants to merge 2 commits into
Conversation
… sub-spike requirements)
Drops the four hard couplings of the original dogfood design while preserving
full backward compatibility with existing pillars.<slug> configs:
1. Scope: first positional arg is now optional. Resolution order is
pillars.<slug> (legacy) -> projects.<slug> (agnostic) -> Linear MCP
exact-name match -> interactive. New --label / --filter scope flags.
2. Evidence anchor: optional --evidence <path-or-issue-id> flag 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.
3. Vision audit: auto-discovery only fires in legacy pillar mode. Agnostic
mode requires explicit --audit <path>.
4. Output path: default is ./priority-<DATE>.md in cwd. Override with --out.
Legacy pillar mode keeps the audits/<pillar>/ default.
Also splits MoSCoW scoring rules into evidence-driven (skip when no anchor)
vs label-driven (always fire) families, and adds explicit
moscow/{must,should,could,wont} label rules so workspaces using MoSCoW labels
get deterministic coverage without an evidence anchor.
Rationale: the original command was opinionated against a pillar taxonomy
that does not exist in typical Linear workspaces (per Andres analysis,
2026-06-02). Dogfood configs continue to work unchanged.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
![dojo-code-reviewer[bot]](https://avatars.githubusercontent.com/in/3092887?s=60&v=4){kind=small}
There was a problem hiding this comment.
✅ Approved
Approved — 0 blockers, 2 P3. Confidence: 4/5.
🔵 P3 — Minor
skills/prioritize/SKILL.md:258— 🔵 P3 (minor) — The reference to the comment template is outdated. It points to "Sub-spike comment template", but that section has been renamed to "Evidence-anchor comment template" inreferences/linear-mutations.md.
`references/linear-mutations.md` "Evidence-anchor comment template".
skills/prioritize/references/linear-mutations.md:209— 🔵 P3 (minor) — There is an outdated reference in the## Mutation failure handlingsection (around line 290) that still refers to "Sub-spike comment template". Please update that mention to "Evidence-anchor comment template" so that it matches the newly renamed heading in this file.
Total findings: 2 business context (2 total)
ℹ️ The findings below could not be anchored to a diff line (line not part of any hunk); they are listed here instead.
skills/prioritize/SKILL.md:258— 🔵 P3 (minor) — The reference to the comment template is outdated. It points to "Sub-spike comment template", but that section has been renamed to "Evidence-anchor comment template" inreferences/linear-mutations.md.
`references/linear-mutations.md` "Evidence-anchor comment template".
| @@ -201,13 +209,21 @@ First priority snapshot. No comparison available. | |||
|
|
|||
There was a problem hiding this comment.
🔵 P3 (minor) — There is an outdated reference in the ## Mutation failure handling section (around line 290) that still refers to "Sub-spike comment template". Please update that mention to "Evidence-anchor comment template" so that it matches the newly renamed heading in this file.
main advanced 8 commits while this branch sat open. Only CHANGELOG.md conflicted; the branch's actual contribution (commands/prioritize.md, skills/prioritize/SKILL.md and its three references) merged cleanly. CHANGELOG: the two sides were never in competition — the branch's block sits under [Unreleased] and main's side is the released 1.35.0...1.24.0 entries. Both kept, in that order. Also aligned two README rows that main carries and this branch's own change contradicts. README advertised `/make-no-mistakes:prioritize <pillar-slug>` as requiring a pillar taxonomy, a PIBER+IDCF sub-spike and a vision audit — exactly the four couplings this branch drops. Left as-is, merging would have shipped a README documenting requirements the command no longer has. Rows now match the command's own argument-hint; nothing else in README touched. Verified on the merge result: vitest 60/60, hooks/test-hooks.sh 328/328, hooks/test-sentinel-walkup.sh 5/5, and `npm run build-rules` leaves hooks/rules/rules.json unchanged.
There was a problem hiding this comment.
✅ Approved
Approved — 0 blockers, 1 P3. Confidence: 4.80/5.00. NITs: 1 (shown).
Walkthrough
main branch directly. Per standard GitFlow practices, features should target develop first (i.e. feature → develop → main). Since this PR targets main directly, please proceed with merge only if authorized by repository governance or if hotfixing/force-merging is intentionally allowed in this instance.
PR Walkthrough
This PR transitions the /make-no-mistakes:prioritize command from its original, opinionated pillar taxonomy to a workspace-agnostic model. It makes the <pillar-slug> positional argument optional (allowing project, label, or filter scopes), decouples the sub-spike and vision audit requirements (providing robust defaults like a 0.8 Confidence score when absent), and introduces new explicit MoSCoW label-driven scoring rules.
Areas Reviewed
I reviewed all modified specification and documentation files:
commands/prioritize.md(argument parsing, run-control flags, modes of invocation)skills/prioritize/SKILL.md(subagent instructions, Main Flow Paso A/B/E, output resolution)skills/prioritize/references/frameworks/moscow-rice.md(agnostic mode edge cases)skills/prioritize/references/linear-mutations.md(Priority report template, evidence-anchor comments)skills/prioritize/references/scoring-rules.md(evidence-driven vs. label-driven scoring rule families)README.mdandCHANGELOG.md
Safety Rationale
This is a documentation-driven skill specification with no executable code logic changes, and legacy configuration schemas and execution modes are fully preserved, ensuring complete backward compatibility.
Approved — 0 blockers, 1 P3.
🔵 P3 — Minor
skills/prioritize/SKILL.md:236— 🔵 P3 (minor) — The section reference 'Sub-spike comment template' does not match the renamed 'Evidence-anchor comment template' header inreferences/linear-mutations.md. A reader looking for this template will experience confusion. Changing the reference name keeps the files synchronized.
[pass 1]
⚪ P4 — Nitpicks
commands/prioritize.md:166— [NIT] ⚪ P4 (nit) — The word 'espanol' is missing the tilde 'ñ'. Writing it as 'español' matches standard spelling.
[pass 1]
Total findings: 1 business context, 1 nit (2 total)
|
|
||
| Si el `pillar-slug` no existe en `linear-setup.json`, preguntar: | ||
| If the user invokes `/prioritize` without positional args AND without | ||
| `--label`/`--filter`: |
There was a problem hiding this comment.
[NIT] ⚪ P4 (nit) — The word 'espanol' is missing the tilde 'ñ'. Writing it as 'español' matches standard spelling.
[pass 1]
| - `description.length < 100` -> Reach/Impact inferidos solo del titulo. | ||
| - `--no-audit` fue pasado pero el audit existe -> Confidence default=0.8. | ||
| - Subagent-2 parse warnings presentes (ambiguity en spike sections). | ||
| Mark each issue with `low-confidence-estimate` if: |
There was a problem hiding this comment.
🔵 P3 (minor) — The section reference 'Sub-spike comment template' does not match the renamed 'Evidence-anchor comment template' header in references/linear-mutations.md. A reader looking for this template will experience confusion. Changing the reference name keeps the files synchronized.
[pass 1]
lapc506
added a commit
that referenced
this pull request
Jul 31, 2026
Measured on origin/main @ ee0ba47: the three version files all read 1.36.0, and `gh pr diff 55 | grep -E '^\+.*"version"'` shows #55 already bumps to 1.37.0 in package.json, plugin.json and marketplace.json. Taking 1.37.0 here collides with it in all three. The same probe over #52, #46, #44 and #41 returns nothing, so 1.38.0 is free. Skipping a version costs nothing; colliding does. Minor and not major, decided by reading. A skill auto-activates on its `description` rather than being invoked by name like a command, so a renamed `name:` changes no call site. The reference search returns nothing: grep -rniI "rebase.advisor" . --exclude-dir=node_modules \ --exclude-dir=.git --exclude=CHANGELOG.md -> no hits That negative is real and not a broken search -- the same grep for `spike-recommend` returns 10 files, so cross-references of this shape are found when they exist. One surface does break and is stated rather than folded in: a user who typed `/make-no-mistakes:rebase-advisor` explicitly (README:137 documents that skills can be invoked that way) now gets an unknown skill. It fails loudly, the replacement is one row away in the same table, and the installer prunes the old file rather than leaving both live. The `[1.37.0]:` CHANGELOG reference slot is deliberately left for #55 to fill. Suite: 337/337 hooks, 60/60 vitest. Created by Claude Code on behalf of @lapc506
lapc506
added a commit
that referenced
this pull request
Jul 31, 2026
…(v1.38.0) (#56) * feat(skills): sync-advisor — measure the drift before naming the fix (v1.37.0) Renames `rebase-advisor` to `sync-advisor` and turns a blind router into an advisor that measures. The old skill was 43 lines and measured nothing. Its step 1 was "Confirm the user wants a full team sync" -- a question back to the user about something three git commands answer. Its description then over-routed: it triggered on "align with develop" and "branches are behind", both of which are `git pull`, and sent them to /make-no-mistakes:rebase, which stashes every worktree, rebases every local branch and auto-merges PRs. Between `git pull` and that the toolkit offered nothing, and nothing read-only at all. Six read-only predicates now run before anything is named: distance, fast-forward possible, dirty tree split by stage, untracked files the ref already tracks, worktrees behind, and branches with unpushed commits. The fifth is the threshold between a plain pull and the team command. The fourth is the one nothing else reports, and it was verified on a throwaway pair of repos rather than asserted. An untracked local file at a path the ref tracks aborts the pull outright while being invisible everywhere else: `git status` shows a plain `?? newfile.txt`, distance reports a clean 0 ahead 1 behind, and `merge-base --is-ancestor` says a fast-forward is possible. The pull then exits 1 with "The following untracked working tree files would be overwritten by merge ... Please move or remove them before you merge" -- the message names the user's own file and offers deletion as the remedy, which is the one irreversible move available. The skill reports these by name and recommends copying them out of the repo, never deleting them. Both controls were run: the pipeline printed nothing before the collision existed and named the file after. It never acts. Every fix is printed for the user to run. The single write is `git fetch origin --quiet`, which touches remote-tracking refs and nothing else, and the skill says so out loud -- without it every measurement is taken against a stale origin/<base> and reports a drift that stopped being true days ago, which is the failure this skill exists to catch. Adds `syncAdvisor.governedPaths` to make-no-mistakes.config.json: the paths whose changes get reported by name, turning "you are 12 behind" into "three hooks changed, two of them fix defects you may be looking at right now". No default -- with the key unset the skill drops the consequence line rather than falling back to a built-in list, which would be wrong in every repo but the one it was copied from and would read as measured. commands/rebase.md is untouched and stays a real destination. What changed is who decides when it applies. Origin (2026-07-31, as reported): a developer filed two bug reports against a hook with clean reproductions. One was a real defect; the other described behaviour fixed days earlier against a stale checkout, and nothing in the report separated them. Suite: 337/337 hooks, 60/60 vitest. Created by Claude Code on behalf of @lapc506 * chore(release): take 1.38.0 instead of 1.37.0 — #55 owns 1.37.0 Measured on origin/main @ ee0ba47: the three version files all read 1.36.0, and `gh pr diff 55 | grep -E '^\+.*"version"'` shows #55 already bumps to 1.37.0 in package.json, plugin.json and marketplace.json. Taking 1.37.0 here collides with it in all three. The same probe over #52, #46, #44 and #41 returns nothing, so 1.38.0 is free. Skipping a version costs nothing; colliding does. Minor and not major, decided by reading. A skill auto-activates on its `description` rather than being invoked by name like a command, so a renamed `name:` changes no call site. The reference search returns nothing: grep -rniI "rebase.advisor" . --exclude-dir=node_modules \ --exclude-dir=.git --exclude=CHANGELOG.md -> no hits That negative is real and not a broken search -- the same grep for `spike-recommend` returns 10 files, so cross-references of this shape are found when they exist. One surface does break and is stated rather than folded in: a user who typed `/make-no-mistakes:rebase-advisor` explicitly (README:137 documents that skills can be invoked that way) now gets an unknown skill. It fails loudly, the replacement is one row away in the same table, and the installer prunes the old file rather than leaving both live. The `[1.37.0]:` CHANGELOG reference slot is deliberately left for #55 to fill. Suite: 337/337 hooks, 60/60 vitest. Created by Claude Code on behalf of @lapc506 * fix(sync-advisor): make the collision predicate correct from any subdirectory Reviewer P3 on `ea8c46e` claimed `git ls-tree` "always outputs repository-relative paths" while `git ls-files` is prefix-relative, so the two would fail to match from a subdirectory, and proposed `--full-name` on `ls-files`. Measured: the premise is false and the proposed fix introduces the bug it claims to prevent. From `sub/`, `ls-tree -r --name-only` prints `newfile.txt`, not `sub/newfile.txt` -- it strips the prefix exactly like `ls-files` does, so the original command matched fine and found the collision. Adding `--full-name` alone then makes `ls-files` emit `sub/newfile.txt` against `ls-tree`'s `newfile.txt`, they stop matching, and `comm -12` returns empty -- a clean bill of health for a tree about to abort the pull. But it pointed at a real weakness of a different kind. From a subdirectory both commands are SCOPED to that subtree, so a collision at the repo root is not seen at all. That is scope, not format, and no combination of format flags fixes it: `--full-name` changes how a path prints, never which paths are considered. The pathspec does. Shipped: `--full-name -- :/` on ls-files, `--full-tree` on ls-tree. Four cases run, with the command extracted verbatim from SKILL.md so the test cannot drift from the doc -- negative control from the root and from `sub/` (both empty), positive from the root and from `sub/` with one collision in each location (both list `rootfile.txt` and `sub/newfile.txt`). Suite: 340/340 hooks, 60/60 vitest. Created by Claude Code on behalf of @lapc506 * fix(sync-advisor): resolve the base ref correctly, and in a bare form Reviewer P2 on `00e2c08`, and it is right. Step 0 returned values carrying the remote prefix while every predicate interpolates `origin/$BASE`, so the run died on `origin/origin/develop`: $ git rev-list --left-right --count "HEAD...origin/origin/main" fatal: ambiguous argument … unknown revision exit=128 Fixed by normalising unconditionally (`${BASE#refs/remotes/}`, `${BASE#origin/}`) whichever branch of the resolution produced the value. Verified both branches with a control that must fail: where `origin/HEAD` IS set it returns `origin/main`, normalises to `main`, and `origin/main` resolves; the un-normalised form exits 128. The P2 understated it. Step 0's first command resolved the base from `@{upstream}`, which on a feature branch is that branch's OWN remote copy -- here `origin/andres/sync-advisor`. That answers "am I pushed?", which is predicate 6's question, and would report 0 behind on a branch far behind the real base. Stripping a prefix would have left it pointing at the wrong ref, so the command is gone from base resolution rather than patched. Also measured while there: `git symbolic-ref --short refs/remotes/origin/HEAD` fails outright in this repo (`not a symbolic ref`), so it is documented as a fall-through into the develop/main/master/trunk probe rather than as a step that is expected to succeed. P4 (`--abbrev-ref` and `--symbolic-full-name` redundant) is also correct -- both forms return `origin/andres/sync-advisor` here -- and is moot: that command no longer appears. Suite: 340/340 hooks, 60/60 vitest. Created by Claude Code on behalf of @lapc506
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
HUMAN LAYER
Summary
The
/make-no-mistakes:prioritizecommand was opinionated against a pillartaxonomy that's not portable to typical Linear workspaces (per Andrés analysis,
session 2026-06-02 0500 CST). This PR drops the four hard couplings of the
original dogfood design while preserving full backward compatibility with
existing
pillars.<slug>configs.Four coupling fixes
<pillar-slug>validated againstpillars.<slug>pillars.<slug>(legacy) →projects.<slug>(agnostic) → Linear MCP exact-name match → interactive. Plus--label <name>and--filter <query>as alternative scopes.--evidence <path-or-issue-id>flag. Accepts a Linear issue ID OR a local markdown path. Without it, evidence-driven MoSCoW rules are skipped; Confidence defaults to 0.8.<codebase>/audits/<pillar>/vision-audit-*.md--audit <path>(no flag → no enrichment).<codebase>/audits/<pillar>/priority-<DATE>.md./priority-<DATE>.mdin cwd, with~/expansion.--out <path>overrides. Legacy pillar mode keeps the original default.Backward compatibility table
prioritize pathways(withpillars.pathwaysin config)prioritize pathways(withprojects.pathwaysonly)prioritize agent --evidence APP-101prioritize --label "team/frontend"prioritize --filter "label:Frontend state:Backlog"prioritize(no args)linear-setup.json+ MCP.prioritize pathways --evidence ./vision.md --audit ./audit.md --out ~/p.mdMoSCoW rule split
Scoring rules now annotated as:
--evidencewas provided (MUST-1..4, SHOULD-1..3, COULD-1..2, WONT-1..2).New explicit MoSCoW-label rules (
MUST-5,SHOULD-4,COULD-4,WONT-4)give workspaces using
moscow/{must,should,could,wont}labels deterministiccoverage without needing an evidence anchor.
Files touched
commands/prioritize.md— args + flag surface + workflows + legacy sectionskills/prioritize/SKILL.md— added "Workspace-agnostic mode (v1.23+)" section, rewrote Paso A/B/E for optional anchors, expanded error tableskills/prioritize/references/scoring-rules.md— annotated rules as evidence-driven vs label-driven, added explicit MoSCoW-label rulesskills/prioritize/references/linear-mutations.md— generalized "Sub-spike comment" → "Evidence-anchor comment" + agnostic report templateskills/prioritize/references/frameworks/moscow-rice.md— updated edge cases 4-8 for agnostic modeCHANGELOG.md— Unreleased entryOut of scope
command flow; no existing tests cover the pillar-slug path either, so
nothing to regress.
linear-setup.jsonconfigs (none in this repo).AGENT LAYER
Acceptance criteria
prioritize pathways(legacypillars.pathwaysconfig) still works as before.prioritizewith no args enters interactive selection (no pillar-slug error).prioritize --label "x"andprioritize --filter "y"are accepted as valid scopes.--evidence,--audit,--out,--codebaseare all optional, with documented defaults.--evidenceaccepts both a Linear issue ID and a local file path../priority-<DATE>.mdin cwd; legacy is<codebase>/audits/<pillar>/priority-<DATE>.md.--evidence, evidence-driven MoSCoW rules are skipped; label-driven rules continue to fire.--audit, RICE Confidence defaults to 0.8.--evidenceLinear issue when it is an issue ID; skipped for local files or absent evidence; legacy mode still targetspillars.<slug>.spike.[Unreleased]entry documents all four coupling fixes.Context files
commands/prioritize.md— entrypoint with the new arg parsing rules.skills/prioritize/SKILL.md— full skill flow with optional-anchor branches.skills/prioritize/references/scoring-rules.md— evidence-driven vs label-driven rule families.skills/prioritize/references/frameworks/moscow-rice.md— RICE formula + agnostic edge cases (4–8).skills/prioritize/references/linear-mutations.md— generalized comment + report template.Decision rationale
Why preserve
pillars.<slug>as legacy mode rather than delete it?The author dogfooded the command against two production pillars in early
2026; deleting that path silently would break those configs. Keeping it as
the first resolution step costs no UX (users with
projects.<slug>onlynever see it) and gives a clear migration runway.
Why accept both Linear issue ID and local markdown for
--evidence?A PRD/spec/vision doc often lives outside Linear (Notion export, repo doc).
Forcing it to be a Linear issue would reintroduce the "must own a sub-spike"
coupling we're explicitly removing.
Why split rules into evidence-driven vs label-driven instead of dropping
evidence-driven rules entirely?
The killshot-thesis / anti-pattern / P0-feature rules are the highest-
signal rules in the engine when an anchor exists. Dropping them would
regress the dogfood pillars. Annotating them lets the runtime cleanly skip
them when no anchor is supplied.
Why default output to cwd instead of a temp dir or
~/.cache?Reports are meant to be committed alongside the codebase / Linear backlog
snapshot. Cwd default lets the user
git add priority-*.mddirectly.Constraints honored
feedback_never_force_push_without_authorization)..wt-prioritize-agnostic/.Created by Claude Code on behalf of @lapc506.