Skip to main content
← back to extensions

@magistr/issue-lifecycle

v2026.04.10.1

Issue lifecycle model with 9 bundled Claude Code skills for DDD, TDD, moldable development, and parallel code review.

Drives issues from filing through triage, prior-art lookup, DDD + TDD planning, parallel review fan-out (5 review skills), autonomous code-review iteration (zero CRITICAL + zero HIGH gate), optional UAT/KB harvest, and completion. State persists across sessions via the state resource; the hydrate method writes a cheap summary resource for long autonomous loops.

State Machine

filed ──[triage]──> triaged
triaged ──[plan]──> planned
planned ──[review_plan]──> reviewing
reviewing ──[approve_plan]──> approved
reviewing ──[reject_plan]──> planned  (feedback loop)
approved ──[implement]──> implementing
implementing ──[review_code]──> code_reviewing
code_reviewing ──[resolve_findings]──> resolved
code_reviewing ──[iterate]──> implementing  (autonomous loop)
resolved ──[iterate]──> implementing
resolved ──[harvest]──> harvested  (optional)
resolved ──[complete]──> complete
harvested ──[complete]──> complete

approve_plan requires full matrix coverage AND zero open CRITICAL AND zero open HIGH findings. close works from any state.

Methods

  • start — file a new issue
  • triage — classify with optional confidence/regression/reproduction
  • record_prior_art — record existing UAT scenarios and KB entries
  • plan — create/revise plan with DDD analysis, TDD strategy, review matrix
  • review_plan — enter plan review phase
  • record_review — record one reviewer's findings
  • approve_plan — approve (gated on coverage + zero blocking findings)
  • reject_plan — reject with auto/human source tracking
  • implement — start coding on a branch
  • review_code — enter code review phase
  • resolve_findings — record resolutions, snapshot round
  • iterate — return to implementation (bumps codeReviewIteration)
  • harvest — record UAT/KB improvement proposals
  • complete — mark done
  • close — abandon from any state
  • hydrate — write compact summary for autonomous loops

Bundled Skills

  • issue-lifecycle — orchestrates the full lifecycle
  • ddd — domain-driven design building block selection
  • tdd — red-green-refactor workflow enforcement
  • moldable-dev — contextual inspectors and live-data queries
  • review-code — general code review
  • review-adversarial — adversarial review (7 dimensions)
  • review-security — OWASP-adapted security audit
  • review-ux — CLI output and error message review
  • review-skill — skill quality review

Repository

https://github.com/umag/swamp-workspace

Platforms

linux-x86_64linux-aarch64darwin-x86_64darwin-aarch64

Labels

issue-trackingtdddddreviewlifecyclesdlc

Contents

modelsskills

Quality score

How well-documented and verifiable this extension is.

Not yet scored.

A score will be generated the next time this extension is published. The owner can also trigger scoring manually.

Install

$ swamp extension pull @magistr/issue-lifecycle

Release Notes

Restructure to monorepo layout. Add repository field, root README as additionalFile, improved manifest description with state machine and method docs.

Security Notice

This extension includes AI agent skills that can modify AI assistant behavior. Review the skill files before installing.

@magistr/issue-lifecyclev2026.04.09.1issue_lifecycle.ts
startFile a new issue — creates initial state
ArgumentTypeDescription
titlestring
descriptionstring
labelsarray
triageTriage the issue — set priority, category, affected areas, and
ArgumentTypeDescription
priorityenum
affectedAreasarray
reasoning?string
isRegression?boolean
clarifyingQuestionsarray
record_prior_artRecord existing UAT scenarios and KB entries found during the
ArgumentTypeDescription
uatScenariosarray
kbEntriesarray
planCreate or revise the implementation plan with DDD analysis and TDD
ArgumentTypeDescription
summarystring
stepsarray
dddAnalysisstringWhich aggregates, entities, value objects, and domain services are affected
testStrategystringWhat tests to write first, red-green-refactor sequence
potentialChallengesarray
review_planEnter the plan review phase — the skill then fans out review skills
record_reviewRecord one reviewer's findings. Call once per active entry in reviewMatrix.
ArgumentTypeDescription
reviewerstringSkill name: review-code, review-adversarial, review-security, review-ux, review-skill
verdictenum
findingsarray
approve_planApprove the plan. Requires (a) all reviewers in the matrix have
reject_planReject the plan — returns to 'planned' state so the next plan call
ArgumentTypeDescription
reasonstring
sourceenum
implementStart implementation — record branch name. Follow TDD: write failing test first.
ArgumentTypeDescription
branchstring
descriptionstring
review_codeEnter the code review phase — the skill then fans out reviewers
resolve_findingsRecord resolution for review findings. Merges into cumulative
ArgumentTypeDescription
resolutionsrecordMap of finding description → resolution action
iterateReturn to implementation — not all findings resolved. Snapshots
ArgumentTypeDescription
reasonstring
sourceenum
harvestRecord UAT and KB improvement proposals from this lifecycle.
ArgumentTypeDescription
uatProposalsarray
kbProposalsarray
completeMark the issue as complete. Accepts either 'resolved' (harvest
ArgumentTypeDescription
summarystring
closeClose/abandon the issue from any state
ArgumentTypeDescription
reasonstring
hydrateReturn a compact summary for the autonomous loop's decision-making:

Resources

state(infinite)— Issue lifecycle state — persists across sessions
summary(infinite)— Compact decision-making summary written by the `hydrate` method.

issue-lifecycle4 files
ddd6 files
tdd5 files
moldable-dev5 files
review-code4 files
review-adversarial4 files
review-security4 files
review-ux4 files
review-skill4 files