Skip to content

Releases: dean0x/devflow

v1.8.3

22 Mar 12:33

Choose a tag to compare

Fixed

  • HUD: version upgrade notice persists after install — cache now stores only npm latest, reads installed version live

v1.8.2

22 Mar 12:19

Choose a tag to compare

Fixed

  • Ambient mode: skills not loading despite correct classification — reordered instructions so Skill tool invocations happen before any text output

v1.8.1

22 Mar 10:22

Choose a tag to compare

Changed

  • Init wizard: individual feature prompts with explanatory notes replace extras multiselect
  • Init wizard: scope-aware .claudeignore batch install across all discovered projects (user scope)
  • Init wizard: project discovery via ~/.claude/history.jsonl to find all Claude-used git repos
  • Init wizard: managed settings sudo confirmation moved to prompt phase (before spinner)
  • Init wizard: safe-delete prompt moved to prompt phase for uninterrupted install

Added

  • --hud flag for devflow init to explicitly enable HUD
  • discoverProjectGitRoots() utility for finding projects from Claude history

Removed

  • Extras multiselect (buildExtrasOptions) — replaced by individual feature prompts

v1.8.0

22 Mar 00:42

Choose a tag to compare

Added

  • Configurable HUD replacing bash statusline — 14 components, on/off model (#155)
  • HUD components: directory, git branch, ahead/behind, diff stats, release info, worktree count, model, context usage, version badge, session duration, session cost, usage quota, todo progress, config counts
  • --hud-only flag for standalone HUD install
  • --no-hud flag to skip HUD during init
  • devflow hud command (--status, --enable, --disable, --detail, --no-detail)
  • Version upgrade notification: ✦ Devflow vX.Y.Z · update: npx devflow-kit init (yellow, always visible even when HUD disabled)
  • Skill shadowing docs and HUD options added to README (#156)
  • Simplifier agent — 8 structured slop detection categories (#120)
  • Scrutinizer agent — stub detection patterns with reference file (#121)
  • Shepherd agent — goal-backward verification, artifact depth checking, stub type, re-verification (#124)

Changed

  • Init flow: HUD preset picker (5 options) → simple yes/no confirm
  • --disable keeps statusLine registered (version badge still renders)
  • Manifest features.hud field: string|falseboolean

Fixed

  • HUD base branch detection matching raw commit hashes from reflog (#156)
  • HUD comparing main vs main (0/0 always) — now compares against origin/main

Removed

  • HUD preset system (minimal/classic/standard/full)
  • --configure, --preset, --hud <preset> flags
  • speed, tool-activity, agent-activity components

v1.7.0

20 Mar 22:37

Choose a tag to compare

Added

  • Version update notification — statusline shows magenta ⬆ X.Y.Z badge when newer devflow-kit is available (24h cached npm check, fully async)

Fixed

  • Skimmer agent — enforce rskim usage via tools: ["Bash", "Read"] platform restriction and strict sequential workflow; prevents fallback to Grep/Glob
  • Init multiselect — remove redundant "(optional)" suffix from plugin hints
  • Init multiselect — hide audit-claude plugin (not production-ready; still installable via --plugin=audit-claude)
  • Statusline portability — replace macOS-only stat -f %m with portable get_mtime() helper (macOS + Linux)

v1.6.1

20 Mar 11:14

Choose a tag to compare

Added

  • --dry-run flag for devflow uninstall — preview removal plan without deleting anything

Fixed

  • Ambient skill loading — removed allowed-tools restriction from ambient-router so skills actually load via the Skill tool
  • Ambient hook preamble — explicit Skill tool instruction ensures models invoke skills rather than responding directly
  • Init wizard — hide devflow-ambient from plugin multiselect (auto-included via ambient prompt)
  • Working memory — replaced broken --resume with transcript-based background updater

v1.6.0

19 Mar 22:39

Choose a tag to compare

Added

  • Ambient agent orchestration: ORCHESTRATED tier spawns agent pipelines for IMPLEMENT, DEBUG, PLAN intents
  • Orchestration skills: implementation-orchestration, debug-orchestration, plan-orchestration for ambient agent pipelines
  • knowledge-persistence skill (#145) — extraction procedure, lock protocol, loading instructions for project knowledge
  • Knowledge loading phase (#145) — /debug, /specify, /self-review now load project knowledge at startup
  • Pitfall recording phase (#145) — /code-review, /resolve record pitfalls to .memory/knowledge/pitfalls.md
  • Knowledge directory (#145) — .memory/knowledge/ with decisions.md (ADR-NNN, append-only) and pitfalls.md (area-specific gotchas)

Changed

  • Ambient mode: Three depth tiers (QUICK/GUIDED/ORCHESTRATED) replacing old QUICK/GUIDED/ELEVATE
  • Ambient mode: GUIDED tier for small-scope IMPLEMENT (≤2 files), simple DEBUG, focused PLAN, and REVIEW — main session with skills + Simplifier
  • Ambient mode: BUILD intent renamed to IMPLEMENT for clarity
  • Coder agent: Added test-driven-development and search-first to permanent skills
  • Command phase numbering (#145) — renumbered fractional phases to sequential integers across 12 command files

Fixed

  • Agent metadata (#146) — fixed subagent_type in debug, added missing YAML frontmatter
  • Plugin count (#146) — corrected to "8 core + 9 optional"
  • Skills catalog (#146) — cataloged 3 missing skills in reference
  • Debug command (#147) — removed non-standard name= parameter
  • Plugin descriptions (#147, #148) — synced across plugin.json, plugins.ts, marketplace.json
  • Simplifier agent (#148) — added Output/Boundaries sections
  • Plugin metadata (#148) — added homepage/repository/license/keywords to 3 plugins

Removed

  • /ambient command: Ambient mode is now hook-only. Use devflow ambient --enable to activate.

Behavioral Changes

  • EXPLORE intent now always classifies as QUICK (was split QUICK/GUIDED)
  • Simple text edits ("Update the README") classify as QUICK (was BUILD/GUIDED)
  • Debug agent budget cap removed — agents scale to investigation needs

v1.5.0

13 Mar 23:15

Choose a tag to compare

Added

  • Search-first skill (#111) — New skill enforcing research before building custom utility code. 4-phase loop: Need Analysis → Search (via Explore subagent) → Evaluate → Decide (Adopt/Extend/Compose/Build)
  • Reviewer confidence thresholds (#113) — Each review finding now includes a visible confidence score (0-100%). Only ≥80% findings appear in main sections; lower-confidence items go to a capped Suggestions section. Adds consolidation rules to group similar issues and skip stylistic preferences
  • Version manifest (#91) — Tracks installed version, plugins, and features in manifest.json. Enables upgrade detection during devflow init and shows install status in devflow list

Fixed

  • Synthesizer review glob — Fixed ${REVIEW_BASE_DIR}/*-report.*.md glob that matched zero reviewer files; now uses ${REVIEW_BASE_DIR}/*.md with self-exclusion

v1.4.0

09 Mar 23:35

Choose a tag to compare

Added

  • Smart branch naming/implement #42 auto-derives branch names from issue labels and title (e.g., feature/42-add-jwt-auth); free-text tasks infer type from keywords (e.g., /implement fix login bugfix/login-bug)

Fixed

  • Code review file detection — Corrected file detection and skill check logic in /code-review

Changed

  • Author standardization — Unified author name to Dean0x across marketplace and plugin manifests

v1.3.3

09 Mar 09:00

Choose a tag to compare

Changed

  • Sudo trust prompt — Managed settings now shows a clear explanation, a copy-pasteable verification prompt, and an explicit fallback option before any password prompt

Added

  • Managed settings test coverage — Unit tests for installManagedSettings two-stage write logic