Repository navigation
Add a write-up checklist to ETHOS and the READY template (GST-2755) - #4381
Merged
Merged
Conversation
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
😎 This pull request was merged. |
Review-Finding: p1/adversarial-native#1 reader=adversarial-native Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Merged
capy-ai Bot
added a commit
that referenced
this pull request
Nov 17, 2026
- /autoplan's approval page no longer hides a reviewer's product objection behind "keep your direction". (#4431) - Every skill that loads the shared preamble, on every host, now says to ask a question once and to check a file before handing it over. (#4383) - The Captain manuals now name the `Failed or skipped:` and `Also changed:` lines that READY and lane reports carry. (#4432) - gstack's shell locks hold again on Ubuntu 26.04, where `mkdir` reports success when another process won the race (GST-2247). (#4262) - `test/gstack-lock-race.test.ts` runs the old pattern and the helper against a PATH shim that behaves like uutils 0.8.0 `mkdir`, so it runs on any runner image: the old pattern lets two of four racers win, the helper admits exactly one in each of 60 races and never overlaps across take, hold and release loops, and parallel `gstack-config` writers keep every key. (#4262) - Windows Setup E2E now runs when `bin/gstack-lock.sh` changes. (#4433) - Claude Code's skill list now says when to use each gstack skill, so Opus loads /review and /plan-eng-review when a request fits. (#4387) - A pull request's merge head can no longer keep its `/ship` receipt without a full review. (#4365) - `/ship` now counts review rounds per pull request, and the head that merges always gets a full review. (#4360) - /ship's documentation audit no longer accepts a passing result when an earlier line from the same audit said "blocked". (#4434) - /ship's documentation audit no longer spends an attempt when the audit child writes text after its result. (#4285) - The README lists the two new guides, and the install doc counts its hooks right. (#4403) - docs/releases.md now says the stable release cut treats a failed commit status as red and a pending one as still going, as it has since #4257. (#4436) - /ship's `finish --docs-requested` now accepts a docs fix when the audit named the file with a line number. (#4437) - Document the `.gstack/approval-classes.json` schema, `gstack-approval-classes` CLI commands, and owner approval citation format in `docs/ship-policy.md#approval-classes`. (#4355) - `/eval-plan` now runs four result checks instead of leaving them to judgment. (#4384) - The /review coverage-audit eval no longer fails a run that really read the source file when zsh stops a command line at an `echo ====` separator. (#4364) - Sixteen in-repo documentation links reach their section again. (#4394) - gstack agents now open every status report with what failed, what they didn't verify and what else they changed. (#4273) - Two new short guides. (#4380) - A skill you wrote whose contract still lists `check_after_last_edit` keeps the rest of its contract. (#4439) - The ship policy guide now explains how to merge any pull request with `gstack-ship-queue land`, even in a repository with one maintainer. (#4377) - /ship's test step runs a large unit suite on Linux. (#4426) - Every skill that loads the shared preamble, on every host, now says never to print a whole environment, git config or process table. (#4382) - Pull requests from /ship now open with at most three plain lines, and every merge lands as one commit titled with the PR title. (#4438) - `gstack-pr-wait`, `gstack-ci-gate` and the release cut no longer call a commit green while a check on it failed. (#4257) - `gstack-runaway` now says what a thread's cold and empty wakes cost, not just how many there were (GST-2770). (#4385) - The optional Stop hook no longer checks for a test run after the last edit, and /verify asks for it in plain words instead. (#4428) - /ship's test step says when it ran out of time, and you can set its budget. (#4429) - The remote test command no longer puts every file on one command line. (#4429) - The stable release no longer waits on the nightly Windows tests (GST-2815). (#4400) - Ubicloud fan-outs can no longer overshoot the vCPU limit, and owners no longer delete each other's VMs. (#4430) - hono is pinned to 4.13.16, which fixes five advisories the weekly OSV scan found in 4.13.13 (gstack#4406). (#4408) - `package.json` overrides (#4408) - `test/dependency-security.test.ts`: the lockfile floor check now covers `hono >= 4.13.16`. (#4408) - The nightly Windows test run finishes again. (#4409) - A short write-up checklist in ETHOS.md. (#4381) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
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
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.
Adds a three-item write-up checklist to ETHOS.md: a post's words match the page it links, every number, "green" and "ready" names its source and is read at the current head, and a fresh model reads it cold once.
Why: posts that said more than their linked page, and numbers read from a stale tree, were the most common corrections in our own agent teams.
The READY template now points to the second item; nothing else changes for users.
Status: current. The docs audit for docs-4381-a1 found nothing to correct and made no edits.
Scope: base 0326b14 to head c25b0ee on
write-up-checklist: two commits touching 3 committed Markdown files (ETHOS.md, captain/templates/READY.md, changelog.d/write-up-checklist.md). Nothing staged, unstaged or untracked. Also checked docs that reference these files: crew/docs/captain.md (READY contract section), captain/templates/CREW.md, docs/TESTING_INTERNALS.md and NOTICE.md (ETHOS anchors), README.md (ETHOS link), CLAUDE.md and .github/PULL_REQUEST_TEMPLATE.md (ETHOS edit policy). The repo keeps no banned-terms list.Coverage:
Documentation Debt
Diagram drift: none. No diagrams reference the changed files.
Agent notes
What changed.
ETHOS.mdsection 8 (Explain the Number) gains a### Write-up checklistsubsection (anchor#write-up-checklist, so a later second-reader skill can defer to item 3 for the cold read) and two anti-patterns.captain/templates/READY.mdgains one paragraph: every number, "green" and "ready" in the block names its source and is read at the pinned head, and anything carried over goes underUnverified:. Plus a changelog fragment. No SKILL template changed, so no generated file moved (bun run gen:skill-docsleft the tree clean).Why ETHOS and not the shared preamble. Section 8 already holds the write-up rules (takeaways first), and the shared every-host preamble is owned by other work. This PR is separate from the guides PR (#4380) because ETHOS and the captain templates are text agents load, so it keeps full CI.
Evidence, in general terms. In our own agent teams: several readers of one post repeated a parity claim its linked page didn't make, and a draft said "as good as" where the page showed the other model ahead; and in two weeks agents corrected their own reports dozens of times, about a third of them retracting a number from a stale tree or a capped list. These figures come from our internal notes and were not re-checked for this PR. A separate claim, that several agents reported ready while the screen was red, was not checked by anyone and is not relied on here.
Why add it, and how we'll know (ETHOS 9, Earn Its Place). Stated reason above. Measure: over the next two weeks of write-ups and ready reports, count claims a reader or the cold read finds that the linked page doesn't support, and count retractions of stale numbers, against the earlier two-week count.
Checks run locally at this head.
bun test test/captain-skill.test.ts test/capy-skill-wrapper.test.ts test/parity-suite.test.ts test/inventory.test.ts: 92 pass, 0 fail.bun test test/gen-skill-docs.test.ts: 495 pass, 0 fail.scripts/check-doc-links.tson the changed files: ok.bin/gstack-docs-only: no (ETHOS.md is agent-loaded), as intended.Approvals
Plan: exempt: audited-list (Garry's "Do it" to the 2026-11-15 audit, item C1)
Closes GST-2755 on merge.
Review notes
Below the blocking floor (advisory, informational, test-gap or wording items); recorded here and not fixed in this PR.
test/helpers/touchfiles-data.ts:163ETHOS.md selects paid office-hours evals; cost/routing notecaptain/templates/READY.md:56first relative link in a captain template; breaks if the template is copied outside the checkoutAgent notes