From 82e983df317bb555111523cf1c7e7f268e6b21ed Mon Sep 17 00:00:00 2001 From: garrytan Date: Thu, 29 Oct 2026 21:04:08 +0000 Subject: [PATCH] docs(capy/README): everyday words (two weeks, plain-English summary, gut feel, merge commit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- capy/README.md | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/capy/README.md b/capy/README.md index b7e21add8..60ed605a1 100644 --- a/capy/README.md +++ b/capy/README.md @@ -18,10 +18,10 @@ The 14 days from the 2026-10-15 fix waves (the Captain took over the next day) against the 14 days before, measured from git and GitHub[^1]: - **197 PRs merged to gstack's main, up from 65 (3.0x).** That is 98.5 a week. -- **194 versions shipped, 13.9 a day, up from 62 (3.1x).** Under stamp-at-merge, - each merged PR ships as its own version. -- **Nearly twice gstack's best fortnight before Capy.** The March launch - shipped 99 versions in its busiest 14 days; this fortnight shipped 194. +- **194 versions shipped, 13.9 a day, up from 62 (3.1x).** Nearly every merged PR + gets its own version number when it merges. +- **Nearly twice gstack's best two weeks before Capy.** The March launch + shipped 99 versions in its busiest 14 days; these two weeks shipped 194. - **36 PRs merged and 36 versions shipped in one day** (UTC), on October 25 and again on October 26. - **A reported issue is fixed in a median 2.4 days**, from the issue opening to the @@ -72,7 +72,7 @@ flowchart LR C -->|brief| L1[Lane: plan with /autoplan] C -->|brief| L2[Lane: build] C -->|brief| L3[Lane: fix wave] - L1 -->|ELI5 plan + rec| C + L1 -->|plain-English plan + rec| C L2 -->|/ship receipt, READY at head| C L3 -->|READY| C C -->|train: one gate, up to 5 PRs| T[(Gate)] @@ -91,7 +91,7 @@ his exact reply. **Plan first, with a plain-language yes.** New functionality starts with `/autoplan`: a CEO review, an engineering review, design and DX when the work has them, each with a native and a cross-model voice. The gate goes to Garry as -a short ELI5 with "rec" as the default answer and a "do it" option that takes +a short plain-English summary with "rec" as the default answer and a "do it" option that takes every recommendation at full scope. One "do it" has approved eight plans in a morning, and the lanes built them in parallel. Reviews catch the expensive mistakes before code exists. One plan learned that 12 tasks were too few to @@ -122,11 +122,11 @@ within the hour gstack had a lane on it. Another eval Captain's $5.78 panel foun OpenClaw refused to load a 78 KB gstack skill, and gstack had a fix up the same day ([#3610](https://github.com/garrytan/gstack/pull/3610)). When Garry said "hurry up" to one Captain, another reordered its merge queue for it and -sent back each merge sha. +sent back each merge commit. **Evals with preregistered bars.** A prompt or skill change that claims to help is judged by a before/after with fixed trials and a bar written down -before the first paid call ([/eval-plan](../docs/skills.md#eval-plan)), never by vibes. +before the first paid call ([/eval-plan](../docs/skills.md#eval-plan)), never by gut feel. Good evals here have a no-skill arm and a length-matched placebo, a check that the treatment actually arrived, decoys verified clean, and spend quoted from the meter. They report losses as plainly as wins. One preregistered eval found @@ -147,7 +147,7 @@ did it go on by default. receipt, tests that cap prompt sizes, a ship policy file. A new crew inherits them by installing gstack, not by reading someone's notes. - **It measures itself.** `gstack-factory-scorecard` reports lead time, gate - cost, red-train rate and flaky events every week against DORA-style bars, + cost, red-train rate and flaky events every week against industry benchmarks (DORA), and says `unavailable` instead of 0 when it can't read something. - **It is honest about cost.** Paid gates are cheap relative to a broken main ("it's fine run as many $93 paid gates as you want who cares"), but token @@ -170,7 +170,7 @@ did it go on by default. CHANGELOG conflict and voids the receipt. Merge once, at your slot. 6. **Size review to the diff.** A docs PR doesn't need a red team. Full-depth review on small diffs is how `/ship` once cost about 50M tokens per - gate-class PR. + PR that needed the full test gate. 7. **Keep threads small.** A long-lived parent context reached 1.36B tokens. Hand long steps to fresh children and read the token counter instead of estimating.