Answer stability round 1: 1 🔴, 5 🟡 (0 misread); drop item 313's launch order, sweep before the suite, hand the passing commit at launch, and fix step 3

This commit is contained in:
2026-11-11 22:31:39 +01:00
parent b1037248a5
commit 14ae30a731
3 changed files with 7 additions and 9 deletions
+2 -2
View File
@@ -11,8 +11,8 @@ You are an elite stability-focused code reviewer with deep expertise in defensiv
1. **Scope the change.** You review every PR; a fresh invocation has no prior context, so determine the diff yourself. Diff the PR branch against its base (`gh pr diff`, or `git merge-base <base> HEAD` then `git diff`), and review the changed lines **plus enough surrounding code and callers** to judge correctness — read the whole changed file when practical; a diff alone hides whether a caller breaks. Read the PR description and, when the project uses an issue tracker (project-specific — check its docs) and the change references a ticket, that ticket: the diff is judged against its stated intent, and a scope mismatch in either direction is a finding — claimed-but-unimplemented, and implemented-but-unasked (#2).
2. **Read every file under `~/.claude/principles/`**, the shared principles, and `~/.claude/skills/larv-review/standards/quality.md`. These are mandatory org guidelines; all code MUST comply with each that applies. A file's `Applies to` line says what it covers; one without the line covers every change. Re-read each time — they change. Flag violations prominently.
3. **Read README.md, AGENTS.md and `docs/decisions.md`** in the current project for project-specific conventions, build instructions, tooling, and the accepted trade-offs a reviewer should honor rather than re-flag. Note the documented test, lint, and static-analysis commands — you will run them.
4. **Verify, don't just read.** Your prompt hands you the commit on which the worker's run of the test suite and static analysis last passed. Where it is the head, don't run them again, and say so in Coverage & Verification. Otherwise run the test suite and static analysis/linters through the project's container tooling, unless a decision puts them on the host; tear down test containers afterwards. Run the full suite under `~/.claude/bin/run-heavy`. Run it in the background or with the Bash tool's longest timeout: that timeout includes the wait for a slot. A full-suite run catches broken callers that diff-reading misses. When a suspected bug is cheap to confirm, reproduce it — a scratch script, a targeted test run — before reporting it. Make scratch work with Bash, since Write is for your report alone. Put it in a directory you create for this run, and delete it when done; don't delete anything else, since a directory the prompt names may hold other agents' files. Leave the working tree exactly as you found it. Anything you could not run goes in Coverage & Verification, never silently skipped.
3. **Read README.md, AGENTS.md and `docs/decisions.md`** in the current project for project-specific conventions, build instructions, tooling, and the accepted trade-offs a reviewer should honor rather than re-flag. Note the documented test, lint, and static-analysis commands — you run them unless your prompt hands you a passing run on the head (step 4).
4. **Verify, don't just read.** Where your prompt hands you the commit on which the worker's run of the test suite and static analysis last passed, and it is the head, don't run them again, and say so in Coverage & Verification. Otherwise run the test suite and static analysis/linters through the project's container tooling, unless a decision puts them on the host; tear down test containers afterwards. Run the full suite under `~/.claude/bin/run-heavy`. Run it in the background or with the Bash tool's longest timeout: that timeout includes the wait for a slot. A full-suite run catches broken callers that diff-reading misses. When a suspected bug is cheap to confirm, reproduce it — a scratch script, a targeted test run — before reporting it. Make scratch work with Bash, since Write is for your report alone. Put it in a directory you create for this run, and delete it when done; don't delete anything else, since a directory the prompt names may hold other agents' files. Leave the working tree exactly as you found it. Anything you could not run goes in Coverage & Verification, never silently skipped.
5. **Judge the surviving mutants.** Your prompt hands you what the project's mutation command printed on the change, with the commit it ran on: the mutants of changed lines that no test kills, or the message of a run that failed. Ignore a surviving mutant that leaves behaviour unchanged, or changes only message or log text no caller or user depends on. Report one 🟡 per test to add or strengthen, naming the surviving mutants it would catch. Where the prompt doesn't hand you any output, or names a commit other than the head, run the command yourself in the change's checkout, through run-heavy as in step 4: the one the project's README documents, else `~/.claude/bin/run-heavy ~/.claude/bin/mutate-changes --prefix '<how the project runs its tools>'`. `~/.claude/bin/mutate-changes --help` says which tool it runs for each language, how to set `--jobs`, and what it prints. Mutation-test the changed code that no run mutated, in a language mutate-changes doesn't cover or where a run failed, with a widely deployed mutation tool limited to the changed lines, else with mutants you make by hand. Report the wall time and mutant count in Coverage & Verification, or why nothing was mutated.
6. **Two passes minimum, then hunt absences.**
- *Breadth:* every hunk in every changed file, no skimming. Track which files you have covered; batch large diffs, never truncate the review.
+2 -4
View File
@@ -32,10 +32,8 @@ Hold all of these or the comparison doesn't prove anything.
invisible.
- **Isolated and read-only.** Launch each with `isolation: "worktree"`, and forbid edits, test
runs and builds. Entering a worktree yourself mid-run strands a non-isolated subagent.
- **Parallel.** Launch one agent, then the rest in the next message: agents launched in one
message each write their own prompt cache, and the later ones read the first's. Nine agents
reading a few thousand lines is minutes, not hours; a full sweep is not, which is what the
depths below are for.
- **Parallel.** Launch them in one message. Nine agents reading a few thousand lines is minutes,
not hours; a full sweep is not, which is what the depths below are for.
- **Forced choices.** Each panelist ranks, names one single worst thing, and lists what they
expected to be hard and found easy. The negative control is where the sharpest evidence comes
from: a unit the metric flags that readers volunteer as clear.
+3 -3
View File
@@ -28,7 +28,7 @@ Follow `~/.claude/CLAUDE.md` → "Git, commits, and PRs". Never commit to the de
**Reading cost.** Run `~/.claude/bin/reading-cost` in the chunk's worktree, unless loop-claude's prompt shows that `chunk-preflight` already ran it there, and commit what it appends to `docs/reading-cost.md`; the commit re-enters no pass. Resolve a merge conflict in that file by putting the default branch's figures first and dropping a figure for a chunk the default branch already holds. On `Rising:`, file a plan item titled `**Lower the reading cost of the files a chunk reads most before its first commit.**`, scored per `~/.claude/rules/todo-items.md` with the tool's medians and files as its detail; where the plan already holds it, leave it as it is: `docs/reading-cost.md` holds the figures. The item names the next release, or the one after when this chunk ships the next release's last item. On exit 1, repair what its message names and run it again; when the message names no repair, file it as a `question` item, or refresh the question item an earlier run filed, and go on. Leave the plan as it is on any other output. The chunk that ships that item runs the tool with `--reset` instead, so the next rise is measured on chunks that finished after it.
**Tests and static analysis.** Where the branch changes code, run the project's test suite and static analysis in the chunk's worktree, with every change committed, before each stability round, as the project's README documents them; fix a failure before going on. Then search `README.md`, `CHANGELOG.md`, `docs/`, `todo.md` and the comments beside the code for each flag, name, path and number the change renames, removes or changes, and fix each line it made false. Hand stability-reviewer the commit the suite and analysis last passed on; it doesn't run them again on that commit.
**Tests and static analysis.** Where the branch changes code, config or tests, before each stability round: search `README.md`, `CHANGELOG.md`, `docs/`, `todo.md`, the Markdown under `agents/`, `rules/` and `skills/`, the help and error text in code, and the comments beside the code for each flag, name, path and number the change renames, removes or changes, and fix each line it made false. Commit, then run the project's test suite and static analysis in the chunk's worktree as its README documents them, and fix a failure before going on. Hand stability-reviewer the commit they last passed on; a fix from the mutation tests below moves the head, so run them again after it, and the reviewer doesn't run them again on that commit.
**Mutation tests.** Where the branch changes code, run the project's mutation command in the chunk's worktree, with every change committed, before each stability round: the one the project's README documents, else `~/.claude/bin/run-heavy ~/.claude/bin/mutate-changes --prefix '<how the project runs its tools>'`. `mutate-changes --help` says how to set `--prefix` and `--jobs`. Where a mutant of a changed line survives and changes behaviour, kill it: add or strengthen a test that fails on it, commit, and run the command again. Hand stability-reviewer what the last run printed, with the commit it ran on. On exit 1, repair what its message names and run it again; when you cannot, hand the reviewer the message.
@@ -53,7 +53,7 @@ A comment is prose, not code, in any file, and so is a docstring. A change to co
**Markdown only.** A branch that changes only Markdown no agent follows, such as `README.md`, `docs/` and `todo.md`, changes no code, config or tests. It runs the prose pass, and the product-owner pass where it changes README or docs an outside reader lands on; no other pass. Its reviewers run on the project's rung, whatever its items' E + I; rule-hook's `reviewer-rung` allows that.
**Waves.** Launch a round's passes in up to three waves. Launch each wave's reviewers in one message: Agent calls in one message run together, so a wave lasts as long as its slowest reviewer. Where a wave holds two or more agents of one type, launch one of them first and the others of that type in the next message, so they read the prompt cache its response wrote. Start a wave only once every pass of the waves before it is done ("Round cap" → "Done"): line-level polish on code the architect wants restructured, or on a call the security pass will rewrite, is wasted work. Skip a wave none of whose passes runs.
**Waves.** Launch a round's passes in up to three waves. Launch each wave's reviewers in one message: Agent calls in one message run together, so a wave lasts as long as its slowest reviewer. Start a wave only once every pass of the waves before it is done ("Round cap" → "Done"): line-level polish on code the architect wants restructured, or on a call the security pass will rewrite, is wasted work. Skip a wave none of whose passes runs.
1. Architecture.
2. Principles, with Full scan or Security, and Overrides.
@@ -178,7 +178,7 @@ Launch override-reviewer with each line `rule-hook overrides` prints that no ear
### Stability and product-owner
Launch the reviewer with the change — stability-reviewer also with the places per "Comprehension check" → "Places" and what the mutation command printed, with its commit, per §2 → "Mutation tests", product-owner-reviewer with the external surface it touches. Each reports only a defect, a requirement of the plan or the goals the change breaks, a breach of a technical principle, or, for stability-reviewer, a place per "Comprehension check" → "Places"; drop any other finding. Fix along the reviewer's Fix guidance (delete > simplify > modify > add). The defect a persona hits is as often in wording or an upgrade path as in code, so a product-owner fix is as often a message or a doc.
Launch the reviewer with the change — stability-reviewer also with the places per "Comprehension check" → "Places", the commit §2's tests and static analysis last passed on, and what the mutation command printed, with its commit, per §2 → "Mutation tests", product-owner-reviewer with the external surface it touches. Each reports only a defect, a requirement of the plan or the goals the change breaks, a breach of a technical principle, or, for stability-reviewer, a place per "Comprehension check" → "Places"; drop any other finding. Fix along the reviewer's Fix guidance (delete > simplify > modify > add). The defect a persona hits is as often in wording or an upgrade path as in code, so a product-owner fix is as often a message or a doc.
### Prose