Spell the review pipeline once, in the larv-review skill

This commit was merged in pull request #12.
This commit is contained in:
2026-09-24 22:03:03 +02:00
parent 9ecfb1a99d
commit 84dc83f942
3 changed files with 5 additions and 6 deletions
+1 -1
View File
@@ -43,7 +43,7 @@ How work proceeds in any repo, unless that repo's `AGENTS.md` says otherwise.
- **A release is the human's, and a finished one stops the session.** The version bump and the publishing credentials are the human's whatever any other rule says; prepare everything around it so the release is one decision. Open every session with one line: the last version cut, what is unreleased (`CHANGELOG.md`'s `## Unreleased`, else the log since the last tag), and the release this chunk ships into; a repo that publishes nothing says so once. Where the earliest unreleased release has no items left and work has shipped toward it, that is the terminal state: report what it holds and that it is ready to cut, and stop. A security fix still lands, into the waiting release. Never roll forward into a later release's items, and never plan a new release, while a finished one waits — the bump is the next decision. Under `/loop`, that stop ends the loop.
- **One chunk per session**, the smallest PR-able unit; split a milestone into sub-items in `todo.md` before starting it. A finding inside the chunk is fixed in the chunk; outside it, it becomes a `todo.md` item under a release.
- **A done item leaves `todo.md`; its release heading stays until the version is cut.** Where the repo publishes something a consumer takes — a package, an image, an API — the line is reworded for that consumer and moves to `CHANGELOG.md` under `## Unreleased`; a CHANGELOG is written for the public, never for the next agent. Everywhere else the line is simply deleted, because git history is already the record.
- **Ship every chunk with `/larv-review`**, which carries the review pipeline through to a merged PR. A chunk touching only prose takes the skill's prose-only path, which keeps the product-owner and prose passes for anything public: a goal change, a README, a CHANGELOG.
- **Ship every chunk with `/larv-review`.**
- **Ask, don't guess — and fix the goals rather than the question.** Before asking, check whether the goals already settle it; where they nearly do, propose the goal change and show what falls out of it for the instance, because one answered question settles one instance and a goal settles the class. Every answer lands where its kind belongs, and nowhere else: a goal in `README.md`, a working rule in `AGENTS.md`, a standing choice in `docs/decisions.md`. Where an answer is more than one of these, the goal wins — write the goal, and record a decision only for what it still leaves open. Never in chat alone.
## Working with the codebase
+4 -4
View File
@@ -1,11 +1,11 @@
---
name: larv-review
description: One-stop shipping pipeline for a work chunk - branch, commit, push, draft PR, then a gated whole-application architecture review (systems-architect), a security pass over the diff, the stability-reviewer in a loop until no 🔴 or 🟡 remains, a product-owner-reviewer loop whenever a reviewer escalates to it, a closing stability round over what that loop changed, and a prose pass that deletes documentation the code already says, then CI watched until green, the PR marked ready, any external auto-reviewer answered, and the PR merged once it aligns with the project's goals. Decisions land in the repo's decision log so repeated reviews converge. Use when the user asks for /larv-review, says "implement X then run larv-review", or wants a chunk shipped, reviewed and merged.
description: Ship a work chunk through review to a merged PR; decisions land in the repo's decision log so repeated reviews converge. Use when the user asks for /larv-review, says "implement X then run larv-review", or wants a chunk shipped, reviewed and merged.
---
# larv-review — ship the chunk, review until clean, gate green, merge
You orchestrate, fix, and ship; the reviewer agents only report. Run every reviewer synchronously (`run_in_background: false`) — each step depends on the previous result. Watch CI in the foreground too: a headless run exits when the turn ends, and a background watcher or a scheduled wakeup dies with it. A reviewer's report is input to the next step; the turn runs on until §11. Architecture strictly before security, security before stability: line-level polish on code the architect wants restructured, or on a call the security pass will rewrite, is wasted work. The full order is architecture → security → stability → product-owner when escalated → a closing stability round over what that changed.
You orchestrate, fix, and ship; the reviewer agents only report. Run every reviewer synchronously (`run_in_background: false`) — each step depends on the previous result. Watch CI in the foreground too: a headless run exits when the turn ends, and a background watcher or a scheduled wakeup dies with it. A reviewer's report is input to the next step; the turn runs on until §11. Architecture strictly before security, security before stability: line-level polish on code the architect wants restructured, or on a call the security pass will rewrite, is wasted work.
**Forge-neutral.** Five PR operations recur below: read a PR's diff, open a draft PR, read check status, mark ready, merge. Resolve the tooling from the remote per `~/.claude/CLAUDE.md` → "Git, commits, and PRs"; on any other forge, achieve the same intents through its CLI or API — discover how rather than assuming. A forge without a native draft state gets the closest equivalent (a `WIP:`/`Draft:` title prefix); note any approximation in the summary.
@@ -15,7 +15,7 @@ Verdicts, severities, round caps, declining a finding and where decisions are re
- Not a git repo → say so and stop.
- Someone else's PR, or the user asked for opinions only → single stability pass, report findings, done (skip shipping, fixing, the loops and the merge).
- Prose only — markdown, docs, comments, no code — → the reviewer loops add nothing: ship the branch (§1), the prose pass (§7), green gate (§8), merge (§10). Say so in the summary. Prose an outside reader lands on — public API docs, README, error or deprecation text — still takes §6's product-owner pass. The chunk that first writes the goals and audience is the exception — a later change to a goal is not: the human's approval is its whole review, since a reviewer's findings on it could only be declined by citing the goals it exists to write.
- Prose only — markdown, docs, comments, no code — → the reviewer loops add nothing: ship the branch (§1), the prose pass (§7), green gate (§8), merge (§10). Say so in the summary. Prose an outside reader lands on — public API docs, README, CHANGELOG, error or deprecation text — still takes §6's product-owner pass. The chunk that first writes the goals and audience is the exception — a later change to a goal is not: the human's approval is its whole review, since a reviewer's findings on it could only be declined by citing the goals it exists to write.
- Issue trackers are project-specific — the project's own docs say whether it has one. When it does and the work has a ticket, follow that tracker's conventions for assignment and status.
- The repo states its goals and audience under literal `## Goals` and `## Audience` headings in `README.md` — `~/.claude/CLAUDE.md` → "Working loop" gates all planned work on it. Neither heading present, or a version too vague to settle a decision → this chunk cannot be judged against them: stop, say so, and write them with the user as the chunk instead. The same content in `AGENTS.md`, in `docs/` or in a decision log does not satisfy it, and neither does an earlier session having passed it; nothing merges and nothing is reported done while it is unmet. Only what that section lets past its gate reaches review without them.
@@ -131,4 +131,4 @@ Marking the PR ready is what summons CodeRabbit and its kind, so this follows §
## 11. Wrap up
Summarize: PR URL and final state, every verdict reached (architecture, security, stability, product-owner, external), rounds used per loop, findings fixed vs declined vs open — each decline with the goal it rests on — CI status, decisions recorded (file paths), `todo.md`/`CHANGELOG.md` updated, and any 🔀 escalation left for the user.
Summarize: PR URL and final state, every reviewer's verdict, rounds used per loop, findings fixed vs declined vs open — each decline with the goal it rests on — CI status, decisions recorded (file paths), `todo.md`/`CHANGELOG.md` updated, and any 🔀 escalation left for the user.
-1
View File
@@ -4,7 +4,6 @@
Nine-seat comprehension panel, 2026-09-24, depth 1: Navigation 7.6, Locality 5.0, Shape 6.2, Self-sufficiency 5.3, overall 5.9. Every seat was capped by Locality or Self-sufficiency, and seven of nine named `bin/loop-claude`'s round loop as the unit they would least want to modify. The items below are ordered by how many seats named the place and how much of the cap it carries; each is one chunk.
- Keep the pipeline order and the prose-only path in `skills/larv-review/SKILL.md` alone; its frontmatter, its §8 preamble, its §12 summary list and `CLAUDE.md`'s working loop each spell it today.
- State in `bin/loop-claude`'s docstring the Claude Code internals it rests on, with the version they were observed on (2.1.281): the transcript entry shapes `human_turns` reads, the `<id>.jsonl` file and its `.superseded-*`/`.orphaned-*` siblings, `~/.claude.json`'s `hasTrustDialogAccepted`, and `--json-schema` returning `structured_output`. Seven seats reconstructed these from the tests.
- Fix in `bin/loop-claude`: a judge failure re-judges after a minute instead of re-running the worker with "stopped before it was finished"; the failure counter survives a reload; `reload_if_edited` runs the new file with `--help` before exec so an import-time error keeps the old one; every directory `archive` creates is 0700, not only the leaf; `human_turns` states the list case positively; `project_path` and `session_name` share one branch; `sections` stops at any heading. Add a test for `run_round`'s resume decision against a stub `claude`.
- Replace `/home/lilleman` in `settings.json` (lines 9, 16, 59) and the three agents' principles pointers with a form that holds on another machine, and read the status line's time zone from the environment instead of `statusline.sh:65`.