Repository navigation
Conversation
New skills: ketchup, sharpen, in-your-own-words, correct, create-formal-verification-skill, arena, poteto-help (+ references). Principle rewrites: attack-the-premise, fix-root-causes, make-operations-idempotent, migrate-callers, test-behavior, type-system-discipline. poteto-mode principle index updated. ts-best-practices: brand via type guard. shipping + both autopilot playbooks: verification economy and ketchup replies. opening-a-pr: child retarget after parent merge. Skipped as Cursor-only: per-subagent model/effort knobs, cloud VM handling, /loop, Origin/gt machinery. Version 0.2.0 -> 0.3.0.
Cloeille
left a comment
There was a problem hiding this comment.
Thanks for the careful port. The Scope section is good: dropping the per-subagent effort sentences and make-bot-ui is the right call for Hermes. This can't merge as is, though, because main moved under it.
Blocking
1. main already contains most of this sync, and resolving the conflicts naively would regress it.
While this PR was open, main got f828c1e (sync c49b37a..d457567) and 4f77c7d (bump to 0.3.0). That covers a newer upstream range than this PR (d457567 is past 4382e68). Against current main this branch has 4 conflicts (sharpen, in-your-own-words, principle-migrate-callers-then-delete-legacy-apis, principle-type-system-discipline). Because it branches from fe017f6, the diff against main also:
- deletes
skills/maintain-formal-verification-skill/SKILL.md, - removes step 9 of
setup-pstack(the formal verification offer), - rewrites
create-formal-verification-skillwithout the coverage record and sync commit, whichmaintain-formal-verification-skillreads (its steps 1, 3 and 6 depend on them), and points the hand-off atcreate-verification-skillinstead.
Please rebase onto main and keep only what main lacks: arena, correct, ketchup, poteto-help (+ recipes), the shipping / autopilot-* / opening-a-pr playbook changes, the typescript-best-practices brand rule, the poteto-mode index lines, and the README rows. Keep main's versions of the principles and the formal verification skills unless upstream changed them after d457567.
2. Version check fails. python3 scripts/check_version.py origin/main → 0.3.0 must be greater than 0.3.0. New skills make it a minor bump, 0.4.0. Note that #7 also targets 0.4.0, so whichever lands second takes 0.5.0.
3. arena mutates profile-wide config mid-run. hermes config set delegation.model writes the profile config, which the gateway, cron jobs and any other session on the same profile also read. During an arena, their delegates silently switch model. If the run dies between Phase A and Phase F, the pin is never restored. The "loader invalidates its config cache on file change" claim is also not verified in the PR. Options, simplest first:
- default to one family (same model N times, which the skill already allows) and make cross-family an explicit opt-in that warns about the shared config,
- or keep the mechanism but require the restore to happen even on failure, and state the shared-profile side effect in the skill.
Either way, please show one real delegate_task run picking up a changed pin in the same session, or drop the cache sentence.
Non-blocking
arenauses/tmp/arena-<slug>/. Hermes gives each profile a scratch dir viaTMPDIR;$TMPDIR/arena-<slug>/avoids collisions between profiles.- Good catch fixing the
---name:first line in the files you touched. The same broken first line (---name: xinstead of---thenname: x) is on almost everySKILL.mdonmain. That is a separate fix, not for this PR. - CI shows
action_required(first-time contributor workflow approval), so no checks have run yet. A maintainer needs to approve the run after the rebase.
Checked: check_refs.py passes on the branch (108 files, 55 skills), descriptions are ≤60 chars, no em dashes in added lines, docs/guide/* links in poteto-help resolve.
🤖 AI Agent: Madeleine
|
Follow-up after a second, independent pass. One correction to my first review, then the additions. Correction. The Rebase scope grew. Content to fix after the rebase
Pre-existing on 🤖 AI Agent: Madeleine |
Why
The fork last synced upstream at
c49b37a(Oct 12). poteto has since landed 27 commits oncursor/pluginsthrough4382e68(the /create-formal-verification-skill PR, #709). This ports what carries over to Hermes.What changed
ketchup,sharpen,in-your-own-words,correct,create-formal-verification-skill,arena,poteto-help(withreferences/recipes.md).typescript-best-practices: a brand comes from a verifying type guard, neveras.shippingand both autopilot playbooks: upstream's verification economy is now "a verdict covers one patch, green CI covers one head", so a full swarm runs once at the code-ready head and later heads get a fresh verdict under the patch-id rule. Replies end withpstack:ketchup.opening-a-pr: move a child PR onto trunk as its parent merges.plugin.yamlbumped 0.2.0 to 0.3.0.Scope
Deliberately left out, because they have no Hermes counterpart:
delegate_taskhas no per-task model or effort field; both are config-level (delegation.model,delegation.reasoning_effort). The fork's ownwhyskill already documents this.gt) forge commands,/loop,agent-transcripts/paths, per-worktree candidate dirs.make-bot-ui, which needs Cursor's routine webhook trigger,SendToUsersecret cards, and[routine]wake envelopes.Verification
python3 scripts/check_refs.pypasses: 108 markdown files, 55 skills.python3 scripts/check_version.py mainpasses./pstack:*slash commands.Tradeoffs
arenaimplements model-family diversity by pinningdelegation.modelper batch and callingdelegate_taskonce per family, restoring the pin at the end. The cleaner shape is a per-task model field ondelegate_task; that is a Hermes core change, not a plugin one.