Repository navigation
Description
Placeholder for a direction, not a spec yet.
spek will eventually be fed by nous (Nous = experiments with different versions of code and config to create a better change PR); we are working on what that looks like with the nous team now. β @clubanderson
Shape
spek-new already starts a spec from existing material (an issue, a tracker epic, a design doc) and records sources[] provenance. The missing input is Nous: the winning experiment β the variant of code + config that measured best β becomes a source for spek-new, so the spek is written from evidence of what worked rather than from a blank page, and then flows out through the publish hand-off (hivecommons/spektacular#109 β RFC + children β Hive picks them up, Hive side #17018).
Open with the Nous team: what a "winning experiment" artifact looks like (diff, config delta, metrics, the hypothesis it confirmed), where it lives, and how spek-new --from nous:<experiment-id> would read it.
Prior art
- β¨ Experiment Lab β Spektacular: feed the winning Nous hypothesis into a spec/planΒ #13579 (closed) β Experiment Lab β Spektacular: the earlier attempt to connect experiment outcomes to Spek.
- π RFC: Spek emits RFC + child issues into a work source (GitHub / Jira / Linear) for Hive pickupΒ spektacular#109 β publish RFC; lists Nous β Spek as explicitly out of scope there ("nothing here depends on it or anticipates it").
No Hive change is proposed yet; this issue exists so the direction has a home and can be linked from the Nous work.
Activity
hivecommons-hive commentedon Nov 7, 2026
π± Good first issue β bring your own coding agent
Hi! This repository is maintained with hive and welcomes contributions made with your own AI coding agent (Claude Code, Codex, Copilot CLI, Bob, β¦). hosted-available-oke-11-placeholder-r05x picked this issue as a good place to start because:
How to land it (no waiting on a human):
git commit -s).Fixes #17020β that closing keyword is how hive's contributor lane links the PR to your claim.Paste this to your agent
Prefer not to drive the loop by hand? Run your own hive (we call them clankers) β a relay on your machine that claims, opens the PR and handles review fixes for you, and earns you a contributor profile and a leaderboard place: see https://hosted-kubestellar-hive-ojv6.hive.hivecommons.dev/contribute.
If nobody claims it, hive may pick it up itself β claiming first prevents that. Docs: contributor relay Β· contributor lane auto-merge Β· trust tiers Β· AGENTS.md.
hivecommons-hive commentedon Nov 7, 2026
π Claim by @Karibhou released (lease revoked).
Claim history
Karibhou(contributor; lease revoked)hivecommons-hive commentedon Nov 7, 2026
PR #17106 covers this issue: #17106
The PR body says this is partial/non-closing work (
Refs/Part ofor leave-open wording), so Hive will not add a closing keyword. GitHub will not show its issue-list PR icon without a closing keyword; the stage comment is the link.π proposal: Nous β Spek β the winning experiment as a spek-new source (β¦
github-actions commentedon Nov 8, 2026
PR #17106 has merged (#17106) and referenced this issue with a non-closing
Refs #17020rather than a closing keyword.This issue remains open because the merged PR did not use
Closes/Fixes/Resolves. If the fix should close it on merge, use a closing keyword in the PR body; use the opt-inhive: needs-confirmationmarker only when the reporter genuinely must verify before closure.clubanderson commentedon Nov 8, 2026
Closing: the work landed in #17106 (#17106), and the body says no Hive change is proposed yet. Reopen with a concrete change when there is one. The stage-derivation gap (proposal issues showing as Actionable after a Refs PR merges) is tracked in #17150.
π fix: unclaimed proposal / kind/design issues derive stage/018-open-β¦
π fix: unclaimed proposal / kind/design issues derive stage/018-open-β¦
π fix: unclaimed proposal / kind/design issues derive stage/018-open-β¦
π fix: unclaimed proposal / kind/design issues derive stage/018-open-β¦