docs(sprint): wire epics to AI-augmented trio + reconcile engine counts#115
Open
abdout wants to merge 2 commits into
Open
docs(sprint): wire epics to AI-augmented trio + reconcile engine counts#115abdout wants to merge 2 commits into
abdout wants to merge 2 commits into
Conversation
Make the CLAUDE/README/ISSUE.md trio (already used by the report agent at issue.mdx:103) a first-class schema so the sprint page can wire each epic to it without parsing prose. Add YAML frontmatter spec + section schemas to issue.mdx; the onboarding block's trio is the seed. Fix epics.mdx "Already shipped — the engine" table where counts had drifted from filesystem truth: 40→22 agents, 18→25 MCPs (+19 user), "Skills" → 41 Commands (the naming evolved; one legacy skill dir remains). Archive docs/EPICS.md v3 (kun-engine Phase 1/2/3 roadmap, dated 2026-03-30, superseded by the Q3 hogwarts-execution framing). The new v4 is a 24-line pointer to the live surfaces (sprint.mdx, epics.mdx, kun#76) so other repos that look up docs/EPICS.md still get a useful landing page. Refs #76 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Each of the 14 Q3 2026 epics now carries a four-link header:
[docs] · [README] · [ISSUE] · [Epic #N]
Where README/ISSUE point at the AI-augmented trio at
hogwarts/src/components/<feature>/{README,ISSUE}.md. Multi-folder epics
(Finance, Admission, LMS, Messaging, Sales, Marketing) get a "Trios:"
secondary line listing every relevant component folder.
The "Epics at a glance" table is also updated — rows 03/04/05/06/07/08/14
that previously had no GitHub tracker now point at the newly-created
hogwarts#321–327. Row 13 (Fundraising, non-tech, org-level) anchors on
the existing master tracker kun#76.
This closes the loop: anyone (human or agent) landing on the sprint page
can now trace from epic → tracker → code-side trio in two clicks. The
trio frontmatter (epic, sprint, owner, maturity, completion, tracker,
docs, last_audited) means the report agent reads epic metadata
structurally instead of regexing prose.
Trackers referenced:
Existing: hogwarts#313, #314, #315, #316; swift-app#3; kun#76
Created this PR: hogwarts#321, #322, #323, #324, #325, #326, #327
Refs #76
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 tasks
abdout
changed the title
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
1 participant
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.
Summary
Cross-repo docs audit that closes the gap between Sprint Plan epics and code-side truth. Each of the 14 Q3 2026 epics now carries
[docs] · [README] · [ISSUE] · [Epic #N]references; the AI-augmented trio schema lets the/reportagent and orchestration consume epic metadata structurally instead of regexing prose.Companion PR: databayt/hogwarts#328 — adds frontmatter + missing CLAUDE/ISSUE files across 51 trio files in hogwarts.
What's in this PR (kun-side)
content/docs/issue.mdx— new "Component Trio" section defining the YAML frontmatter spec + README/ISSUE/CLAUDE section schemas, with the canonical seed atonboarding/{README,ISSUE,CLAUDE}.mdcontent/docs/sprint.mdx— every epic block gets a four-link header[docs] · [README] · [ISSUE] · [Epic #N]; multi-folder epics (Finance, Admission, LMS, Messaging, Sales, Marketing) get aTrios:secondary line. The "Epics at a glance" table fills in the seven newly-created hogwarts trackers (#321–327) and anchors Epic 13 (Fundraising) on the existing master tracker kun#76content/docs/epics.mdx— "Already shipped — the engine" counts corrected from filesystem truth: 40→22 agents, 18→25 project MCPs (+19 user), "Skills" renamed to 41 Commands (+ legacy-naming note)docs/EPICS.md— v3 (kun-engine roadmap, dated 2026-03-30, superseded) archived todocs/archive/EPICS-v3-2026-03-30.md; replaced with a 24-line v4 pointer to the livesprint.mdx/epics.mdx/kun#76surfacesWhy
The
/reportagent already readsCLAUDE.md · README.md · ISSUE.mdper component dir (issue.mdx:103), but the Sprint Plan couldn't reliably link to that trio — only ~34% of feature folders had a complete trio, none carried frontmatter, and the engine counts had drifted from.claude/filesystem truth. This PR + #328 close that loop: every epic now traces to a tracker + a code-side trio in two clicks, and the YAML frontmatter (epic,sprint,owner,maturity,completion,tracker,docs,last_audited) is agent-readable.GitHub trackers created during this audit
(Existing trackers retained: hogwarts#313 #314 #315 #316; swift-app#3; kun#76)
Test plan
/en/docs/sprintrenders the new[docs · README · ISSUE · Epic]lines for all 14 epics/en/docs/issue#component-trio-claudemd--readmemd--issuemdrenders the new section/en/docs/epicsshows corrected engine countsdocs/EPICS.mdanddocs/archive/EPICS-v3-2026-03-30.mdboth resolve on GitHubOut of scope
kotlin-apprepo doesn't exist yet — separate prerequisite)Refs #76
🤖 Generated with Claude Code