Validator finding #12 from the publish-debate-vortex hyperultradebate flagged that internal-only skill and command assets could leak into the npm payload once the dot asset roots are included.
Bun 1.3.x ignores a root .npmignore for directories listed in package.json#files, so the exclusion rules live in nested .npmignore files co-located with each published command and skill directory.
RED before nested ignores: bun test script/package-layout-exclusion.test.ts failed with expect(received).toEqual(expected), receiving .opencode/skills/__internal-fake-do-not-ship-test-artifact/SKILL.md, .agents/skills/__internal-fake-do-not-ship-test-artifact/SKILL.md, .opencode/command/__internal-fake-do-not-ship-test-artifact.md, and .agents/command/__internal-fake-do-not-ship-test-artifact.md instead of [].
GREEN after nested ignores: bun test script/package-layout-exclusion.test.ts reported 2 pass, 0 fail, 5 expect() calls.
This is the exclusion companion to script/package-layout.test.ts, the inclusion test arriving through the dev merge.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Split the original Phase 5 (lead-written plan) into Phase 5 (insight
distillation) and Phase 6 (mandatory plan agent handoff via
task(subagent_type="plan")). The lead now produces a structured insight
bundle and dispatches it to the dedicated planner — the planner owns
sequencing, parallelization, and verification gates.
This mirrors the ultrawork plan-agent contract: adversarial distillation
extracts only defensible insights, the planner formalizes them into an
executable plan. Skipping the handoff turns hyperplan back into vanilla
orchestration.
- Update workflow phase count 6 → 7
- Anti-patterns: forbid lead-written plans, forbid skipping the dispatch,
forbid pre-writing tasks before dispatch, forbid using team_send_message
to ship the bundle to the plan agent
- Notes: synchronous dispatch (run_in_background: false), planner has no
team mailbox access (everything must be in the bundle)
Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode).
Adversarial multi-agent planning skill that orchestrates 5 hostile
category members via team-mode for cross-critique debate, then
synthesizes only defensible insights into an executable work plan.
Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode).
When .sisyphus/ is gitignored, task state written during worktree execution
is lost when the worktree is removed. Fix:
- add worktree-sync.ts: syncSisyphusStateFromWorktree() copies .sisyphus/
contents from worktree to main repo directory
- update start-work.ts template: documents the sync step as CRITICAL when
worktree_path is set in boulder.json
- update work-with-pr/SKILL.md: adds explicit sync step before worktree removal
- export from boulder-state index
- test: 5 scenarios covering no-.sisyphus, nested dirs, overwrite stale state
- connected-providers-cache: extract factory pattern (createConnectedProvidersCacheStore) for testable cache dir injection
- port-utils.test: environment-independent tests with real socket probing and contiguous port detection
- resolve-file-uri.test: mock homedir instead of touching real home directory
- github-triage: update SKILL.md
Phase 0 now runs /get-unpublished-changes as single source of truth
instead of manual bash commands. Phase 1 uses its output for grouping.
Layer 2 explicitly references /review-work skill flow.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Replace two separate triage skills with one unified skill using 'free' category
for all subagents. Action-oriented: auto-answer questions, analyze bugs,
merge safe PRs. All items tracked via TaskCreate, [sisyphus-bot] comment prefix.
- Convert github-pr-triage to streaming architecture (process PRs one-by-one with immediate reporting)
- Convert github-issue-triage to streaming architecture (process issues one-by-one with real-time updates)
- Add mandatory initial todo registration for both triage skills
- Add phase-by-phase todo status updates
- Generate final comprehensive report at the end
- Show live progress every 5 items during processing
- Add github-pr-triage skill with conservative auto-close logic
- Update github-issue-triage ratio to 7:2:1 (unspecified-low:quick:writing)
- Add gh_fetch.py script for exhaustive GitHub pagination (issues/PRs)
- Script bundled in both skills + available standalone in uvscripts/
- Add critical warnings about using --limit 500 instead of 100
- Add verification checklist before proceeding to Phase 2
- Add severity levels to anti-patterns (CRITICAL/HIGH/MEDIUM)
- Emphasize counting results and fetching additional pages if needed
YeonGyu-Kim