Shipped and released
Now
Outcomes that have shipped in a released version. Each one links to the changelog entry that released it, so you can check it rather than take it on trust.
Released highlights
- The finding-adjudication commands
classify,raw-classify,inspect, andrecordnow live inreview-artifact.py. They print exactly what theloop-cohort.py reviewverbs print, and those verbs keep working. - Without cohort state,
review-artifact.py record --run-id <uuid>keeps onerecordfile per review round under.context/reviews/<run-id>/and counts the review budget from those files. Lifting the cap needs anownerauthority reference. - The reviewer roster, each role's boundary and fallback, and the high-risk definition now also live in
review-rules.json. A check fails if they drift from the work-loop skill text. - The supervisor, still dark-launched, now picks reviewers from that rules file and a recorded selection. It closes review only when structured review readiness says so, and it records repair,
fixed-by, andaccept-riskdecisions. - Policy families can now be selected by supervisor stage, or by the new
PRE-APPROVALconstant. Each key selects what its engine states select today.
- The finding-adjudication commands
- The offline intent view can now show what is ready to work on: pipe the workspace-status status output into the export with --readiness - and the view lists active, ready and blocked items, marks the one work-loop would pick, and shows each blocked item's findings in What is broken. If the check fails, the page says why and the export still succeeds.
- The work-loop traceability check now reads an intent's
Kind:,Level:andSlug:only from its header block above the first##heading, and ignores commented-out lines. It places each intent on the outcome, opportunity and capability ladder exactly as the intent navigator shows it. - A retired (tombstoned) intent no longer appears as a node on the ladder.
- An intent whose
Kind:sits only in its body, in a comment, or under a lowercasekind:label no longer counts as a ladder rung. Move theKind:line into the header block to keep it on the ladder.
- The work-loop traceability check now reads an intent's
- A spec's
Discovery:line, which names the intent or research the spec came from, can now name its intent asoutcome:<slug>,opportunity:<slug>,capability:<slug>, orintent:<slug>. Close-out still finds the same parent intent. - A spec you add or change is refused before the work loop completes the change when its
Discovery:points at an intent by file path or link, or names no existing intent of that kind. Research and notes paths stay plain paths and are not checked. - Older specs you do not touch keep working with their legacy paths.
- A spec's
- The longer shaping route now continues from the capability map into intent decompose, and align-value-stream proposes a hard-limits README section.
- The render-proof skill's locked markdown-it moves to 14.3.3, which fixes two high-severity quadratic-time rendering advisories.
- Architect-design can write a solution repo's shared system reference and offers a physical architecture with a bill of materials after a design.
- When the architect pack is installed, intent de-risk and intent decompose now offer architect-design before the work is cut, and you can decline once; teams without it see no change.
- Authors and agents get a check that catches untyped or broken
Parent intent:andBrief:pointers in the artifacts a change adds or modifies, so a bad link to an intent or brief is fixed before it merges. - Artifacts a change leaves untouched are never checked, so older documents with legacy pointers do not block new work.
- Skills now write typed pointers by default, so new specs and briefs start out well formed.
- The work-loop finish step and the repository gate both run the check, and an incomplete check counts as a failure, not a pass.
- Authors and agents get a check that catches untyped or broken
- Picking an item in the offline intent view now shows a ready-to-paste prompt that starts the named skill on that file, copied with one click or selected for you to copy by hand.
- Runs on Wicked Estate 0.30.0 — re-run the install command to upgrade. The documented capabilities are unchanged; this release tracks the new upstream release and raises the floor and pin to 0.30 / 0.30.0.
- The offline intent view now answers "How far along is each capability?": every capability under its product strategy, with how much of the work beneath it is delivered, being built or not yet started, and a Browse tree you can narrow to open or done work and regroup by capability.
- The offline intent view has a calmer, more polished look: soft panels, tinted state labels that still read as a word and a shape, a clearer detail card, and short fades that stop when your system asks for reduced motion.
- Architect-diagram can export a saved Mermaid diagram to an editable draw.io file on request.
- Pack page rewritten to the catalogue's pack-page template.
- The propose-catalogue-pack shell check now names
agentbundle catalogue verifyinstead of a removed lint script.
- The propose-catalogue-pack shell check now names
- Experience Design now writes the words your screens show:
ux-writingdrafts error, empty-state, button, and label copy keyed to each screen and state.
- Experience Design now writes the words your screens show:
- See what an intent waits for and what waits for it, in the query, its text output and the offline view.
- Pick an intent in the offline view and its Dependencies part lists "A waits for B" lines, with Show and Steps controls; dependency problems also appear in "What is broken?".
- Plans can now declare the external effects a task performs, and stub fences carry the command and exit codes that prove a test fails first.
- The pack's activation-eval comment now names the live
agentbundle pack evals runcommand instead of a removed script.
- The pack's activation-eval comment now names the live