Clean up roadmap: retire solved/speculative items

README.md

@@ -204,7 +204,7 @@ For brainstorming, planning, TDD, verification, and skill authoring — install
 
 ## Hooks
 
-Devkit ships 9 hooks across 4 lifecycle events. All are installed automatically with the plugin — no setup required.
+Devkit ships 10 hooks across 4 lifecycle events. All are installed automatically with the plugin — no setup required.
 
 ### PreToolUse
 
@@ -344,7 +344,7 @@ devkit/
 │   ├── test-writer.md       # Sonnet, worktree isolation
 │   ├── documenter.md        # Haiku, worktree isolation
 │   └── security-auditor.md  # Opus, worktree isolation
-├── hooks/                   # 9 hooks across 4 lifecycle events
+├── hooks/                   # 10 hooks across 4 lifecycle events
 │   ├── hooks.json           # Hook config (auto-loaded)
 │   ├── safety-check.sh      # Dangerous operation blocker
 │   ├── security-patterns.sh # Edit-time vulnerability detection
@@ -530,10 +530,6 @@ See [ROADMAP.md](ROADMAP.md) for full details.
 - [x] Cross-domain dirty-bit enforcement — blocks completion without test evidence per domain
 - [x] Go code quality hooks — error-path access, nil-return, race detection, portability
 - [x] **Language-universal hooks** — consolidated Go-specific hooks into `lang-review.sh` with Go, TypeScript, Rust, Python, and Shell support
-- [x] **Hook consolidation** — merged 14 hooks into 9, reduced per-edit shell processes from 7 to 4. Consolidated stop hooks (dirty-bit + go-vet-stop + old stop-gate) into single `stop-gate.sh`
-- [ ] Stop hook redesign — opt-in or session-end only, not every turn
-- [ ] Cost event hooks — budget threshold events with auto-downgrade actions
-- [ ] Execution registry — centralized step tracking with timing and token usage
-- [ ] Preset library — curated prompt templates for common review/improvement scenarios
-- [ ] Framework-specific review checklists — React, Django, Go, Rust patterns
-- [ ] Conditional hook firing — gitBranch, fileExists, envSet conditions
+- [x] **Hook consolidation** — merged 14 hooks into 10, reduced per-edit shell processes from 7 to 4. Consolidated stop hooks (dirty-bit + go-vet-stop + old stop-gate) into single `stop-gate.sh`
+
+All planned items complete. See [ROADMAP.md](ROADMAP.md) for retired items and rationale.

ROADMAP.md

@@ -3,9 +3,9 @@
 ## Implemented
 
 - **20 slash commands** — Lifecycle workflows, self-improvement loops, multi-agent dispatch, project health audit, post-PR monitoring, AST repo mapping
-- **14 context-activated skills** — 6 auto-trigger workflows (test-gen, doc-gen, changelog, onboard, research, scrape) + 6 coding principles (executing, clean-code, DRY, YAGNI, dont-reinvent, stuck) + 2 tools (gcli, creating-workflows)
+- **15 context-activated skills** — 6 auto-trigger workflows (test-gen, doc-gen, changelog, onboard, research, scrape) + 6 coding principles (executing, clean-code, DRY, YAGNI, dont-reinvent, stuck) + 2 tools (gcli, creating-workflows) + 1 iteration memory (scratchpad)
 - **6 agents** — Scoped tool access, worktree isolation, model assignment
-- **8 hooks** — Safety (destructive command blocking, edit-time security patterns, PR gate), observability (audit trail, slop detection, post-validation, subagent verification), optimization (RTK token compression)
+- **10 hooks** — Safety (destructive command blocking, edit-time security patterns, PR gate), observability (audit trail, slop detection, post-validation, subagent verification, language-aware code review), optimization (RTK token compression)
 - **Graceful degradation** — tri:* commands work with 1-3 agents depending on installed CLIs
 - **Goal decomposition** — Task DAG with dependency ordering and parallel execution
 - **Concurrency limits** — Max 3 parallel agents in multi-agent commands
@@ -18,45 +18,22 @@
 - **Hypothesis-driven perf** — Evidence gathering, ranked hypotheses, one-at-a-time testing replaces blind benchmark loops
 - **Post-PR monitoring** — CI watching + iterative reviewer comment resolution
 - **AST repo mapping** — Symbol index with dependency graph, cached for agent navigation
-
-## Future
-
-### Stop Hook Redesign
-The Stop hook fires on every turn, not just session end. Redesign to fire only on explicit session end or make it opt-in via a command flag.
-
-**When:** Next release. This is a usability blocker.
-
-### Framework-Specific Review Checklists
-React hooks rules, Django ORM patterns, Go concurrency, Rust safety — 20-50 patterns per framework loaded dynamically based on detected tech stack.
-
-**When:** When tri-review needs to produce more actionable, framework-aware findings.
-
-### Conditional Hook Firing
-Hooks that only fire on certain git branches, when files exist, or env vars are set. Similar to skill-bus's condition system but built into devkit's hook stack.
-
-**When:** When users need project-specific hook behavior without modifying global hooks.
-
-### Task DAG Scheduler (Runtime)
-Replace markdown-described DAGs with a runtime scheduler that topologically sorts and auto-parallelizes. Currently decompose describes the pattern; a Go/TS harness would execute it deterministically.
-
-**When:** When workflows regularly exceed 10+ steps with complex interdependencies.
-
-### Shared Context Injection
-Automatically inject upstream agent outputs into downstream agent prompts. Currently done manually in command descriptions; could be automated.
-
-**When:** When tri:* and decompose commands need richer inter-agent communication.
-
-### Cost Event Hooks
-Budget threshold events (warning at 80%, critical at 90%, exceeded at 100%) with auto-downgrade actions. Currently budget is guidance only.
-
-**When:** When users need hard budget enforcement, not just guidance.
-
-### Execution Registry
-Centralized tracking of step state (pending/running/done/failed/skipped) with timing and token usage per step. Currently tracked in temp files during execution.
-
-**When:** When workflow observability needs to improve beyond log files.
-
-### Preset Library
-Curated prompt templates for common review/improvement scenarios (Python security, Go performance, React optimization, etc.).
-
-**When:** When the community identifies common patterns worth standardizing.
+- **Generic YAML workflow engine** — Deterministic step execution, branching, loops, parallel dispatch, budget enforcement in compiled Go
+- **Triage-based phase skipping** — TINY/SMALL/MEDIUM/LARGE classification with fast paths
+- **Iteration scratchpads** — Persistent memory across loop iterations to prevent repeated failures
+- **Cross-domain dirty-bit enforcement** — Blocks completion without test evidence per domain
+- **Language-universal hooks** — Consolidated language-specific hooks into `lang-review.sh` with Go, TypeScript, Rust, Python, and Shell support
+- **Hook consolidation** — Merged 14 hooks into 9, reduced per-edit shell processes from 7 to 4
+
+## Retired
+
+Items below were on the roadmap but determined to be unnecessary — either already solved by existing infrastructure or too speculative to justify the complexity.
+
+| Item | Why removed |
+|------|-------------|
+| Stop hook redesign | Still fires every turn, but exits early with `approve` when no files are changed — near-instant on clean trees, so the performance concern is moot. Revisit only if it causes measurable latency. |
+| Cost event hooks | Budget enforcement already exists in the Go engine via `overBudget()` + `addCost()` callbacks with hard limits |
+| Execution registry | Step tracking already handled by SQLite via `lib.DB` with status, cost, and timing per step |
+| Preset library | The 12 YAML workflows and 15 skills already serve this purpose |
+| Framework-specific review checklists | `lang-review.sh` covers language-level patterns; framework-specific rules are better added per-project via hookify |
+| Conditional hook firing | Hooks already self-filter internally (extension checks, changed-file checks); a generic condition system adds complexity for no current need |