feat(test-automation): universalize bundle, add efficiency-audit skill, harden onboarding docs - #47
Merged
arozumenko merged 1 commit intoJul 13, 2026
Conversation
bermudas
added a commit
to bermudas/sdlc-skills
that referenced
this pull request
Jul 9, 2026
…oks, efficiency-audit, and bundle docs - marketplace: fix efficiency-audit source path in hand-curated Claude manifest (pointed at nonexistent ./skills/); regen generated manifests - usage-rollup: pathToFileURL entrypoint guard (paths with spaces), --help + strict flag parsing, tool_result error dedup (no negative success counts), local-time day bucketing to match ccusage, CLAUDE_CONFIG_DIR + XDG projects-root fallback, unknown-day bucket reconciliation, deterministic fork tiebreak, per-file read guards, skip redundant ccusage fallback, dedupUsage on the production path, drop dead readSubagents; tests 25 -> 35 incl. fs-level fixtures - hooks: revert README Kiro claims to match hooks-kiro.json; guard is_claude_code() against leaked CLAUDE_PROJECT_DIR under SDLC_HOOK_RAW - installer: drop dead installBriefings update param, neutral briefing skip message, note Windows-unserved Cursor hook command - content: TMS back-write is orchestrator-owned post-merge in TAE RULES and onboarding pilot; lead SOUL defers to the Phase 1 gate table; qa-engineer briefing aligned to spec-format (6 statuses, lcovered_/ lextend_, return-only statuses); un-automatable emits no AFS file; seeding steps 6.5/6.6 reordered; scout probes fixed (find over globstar, k6 grep tightened); external-skill links de-linked; greenfield bootstrap prompt is surface-first Claude-Session: https://claude.ai/code/session_01Byba65VsKBGgJ5sftyo2Jc
bermudas
force-pushed
the
feat/test-automation-improvements
branch
2 times, most recently
from
July 9, 2026 14:40
16cd151 to
f21b7e5
Compare
…l, harden onboarding docs Generalizes the test-automation pipeline beyond Jira/Playwright/Claude Code: role naming, tracker/TMS routing (adapter declared by the seed, orchestrator-owned post-merge back-write), surface-first framework choice, multi-host hooks + install. Adds the efficiency-audit skill (ccusage-metered per-project/session/role/day and per-sub-agent cost, snapshots + before/after diffs) to the bundle. Hardens onboarding docs and seeding (way-of-work capture, free-form seeding notes, human-language seeding-prompt examples). Also includes the follow-up hardening applied on this branch: - installer: protect scout-seeded project_briefing.md from --update; Kiro session-start hook restored - review fixes across installer, hooks, efficiency-audit, and bundle docs (marketplace source path, usage-rollup correctness — local-time day bucketing, tool_result dedup, CLAUDE_CONFIG_DIR lookup, strict flag parsing — status-enum/back-write drift, link and probe fixes) - pristine-repro gate: defects first observed via synthetic input must reproduce in a fresh isolated context before filing (defect-filing, reproducing-issues, test-case-analysis, playwright-testing) - hooks: inject role memory for top-level `claude --agent <role>` sessions via CLAUDE_CODE_AGENT (SubagentStart only covers dispatched workers); guarded against env leaks into other hosts
bermudas
force-pushed
the
feat/test-automation-improvements
branch
from
July 9, 2026 14:47
f21b7e5 to
a4caa1e
Compare
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
2 participants
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
efficiency-auditskill to the bundle