rbin-task-flow 1.23.1 → 1.24.0

package/.claude/skills/task-flow-think/SKILL.md

@@ -14,4 +14,6 @@ disable-model-invocation: true
 
 Optional: `graphify query` on large repos before suggesting.
 
+For deep verify + auto-add lacunas (no ask): `@task-flow-validate` (`task-flow: validate`).
+
 Reference: `.cursor/rules/task_analysis.mdc` · Sync after confirm: `@task-flow-sync`

package/.claude/skills/task-flow-validate/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: task-flow-validate
+description: Deep-validates RBIN Task Flow tasks against the codebase, reverts false done status, and appends missing gaps to tasks.input.txt then syncs. Use when the user says task-flow validate, validate all, validar tasks, or verificar lacunas.
+disable-model-invocation: true
+---
+
+# Task Flow — Validate
+
+Thorough implementation audit + automatic gap fill (unlike `review` or `think`).
+
+1. Read `tasks.input.txt`, `tasks.json`, `status.json`, `contexts/` — scope `X`, `X,Y`, or `all` (default `all`).
+2. **Verify** each subtask in scope: `done` must match code; `pending` checked for drift.
+3. **Lacunas:** missing work not in `tasks.input.txt` (TODOs, tests, incomplete features).
+4. **Apply:**
+   - False `done` → `pending` in `status.json`
+   - Append new `- Description` lines to `tasks.input.txt` (no duplicates)
+   - Run sync workflow (`@task-flow-sync` / `task-flow-sync.mdc`)
+5. Report verified / reverted / added / next `run`.
+
+Optional: `graphify query` per task area if `graphify-out/graph.json` exists.
+
+Reference: `.cursor/rules/task_validate.mdc`

package/.cursor/rules/graphify-task-flow.mdc

@@ -11,6 +11,7 @@ alwaysApply: false
   - **`task-flow: run` / `run next X`:** Before implementing a subtask in a non-trivial codebase, if `graphify-out/graph.json` exists, use `graphify query "<feature or module from subtask>"` or read `graphify-out/GRAPH_REPORT.md` god nodes — then implement. If no graph exists, proceed with normal search or suggest `graphify extract . --backend claude-cli` (or `rbin-task-flow init --graphify`).
   - **`task-flow: think`:** Optional `graphify query` for gap analysis on large repos.
   - **`task-flow: review X`:** Optional `graphify affected "<symbol>"` to verify impact surface.
+  - **`task-flow: validate`:** Optional `graphify query` per task area before verifying implementation; then append lacunas + sync per `task_validate.mdc`.
   - **`task-flow: audit`:** Graphify is structural only; scoring uses [coding_standards.mdc](mdc:.cursor/rules/coding_standards.mdc) checklist. Deep dive: sections of [coding-standards-full.md](mdc:.task-flow/docs/coding-standards-full.md) only if user asks for depth.
 
 - **When NOT to use Graphify:**

package/.cursor/rules/task-flow-cursor.mdc

@@ -27,6 +27,7 @@ alwaysApply: true
 | `task-flow: audit` | `@task-flow-audit` |
 | `task-flow: improve changes` | `@task-flow-improve-changes` |
 | `task-flow: review X` | `@task-flow-review` |
+| `task-flow: validate` | `@task-flow-validate` |
 | `task-flow: refactor X` | `@task-flow-refactor` |
 | `task-flow: estimate X` | `@task-flow-estimate` |
 | `task-flow: report X` | `@task-flow-report` |

package/.cursor/rules/task_analysis.mdc

@@ -7,6 +7,8 @@ alwaysApply: false
 
 **Not sync.** For `task-flow: sync` use [task-flow-sync.mdc](mdc:.cursor/rules/task-flow-sync.mdc) or `@task-flow-sync`.
 
+**Not validate.** For deep verify + auto-add lacunas use [task_validate.mdc](mdc:.cursor/rules/task_validate.mdc) or `@task-flow-validate`.
+
 **Prefer:** `@task-flow-think` · After user adds lines: `@task-flow-sync`
 
 ## When to run

package/.cursor/rules/task_execution.mdc

@@ -19,6 +19,7 @@ alwaysApply: false
 | `task-flow: audit` | `@task-flow-audit` |
 | `task-flow: improve changes` | `@task-flow-improve-changes` |
 | `task-flow: review X` | `@task-flow-review` |
+| `task-flow: validate` | `@task-flow-validate` |
 | `task-flow: refactor X` | `@task-flow-refactor` |
 | `task-flow: estimate X` | `@task-flow-estimate` |
 | `task-flow: report X` | `@task-flow-report` |

package/.cursor/rules/task_review.mdc

@@ -81,6 +81,7 @@ alwaysApply: false
 
 - **Integration:**
   - Works with [task-flow-cursor.mdc](mdc:.cursor/rules/task-flow-cursor.mdc) / `@task-flow-review`
+  - For verify + auto-add lacunas + sync: [task_validate.mdc](mdc:.cursor/rules/task_validate.mdc) / `@task-flow-validate`
   - Respects [rbin-git-policy.mdc](mdc:.cursor/rules/rbin-git-policy.mdc) — never commit automatically
 
 - **Principle:**

package/.cursor/rules/task_validate.mdc

@@ -0,0 +1,99 @@
+---
+description: Deep-validates task-flow tasks against the codebase, fixes false done status, and appends missing gaps to tasks.input.txt. Use for task-flow validate, validate all, validar tasks, or verificar lacunas.
+alwaysApply: false
+---
+
+# task-flow: validate
+
+**Prefer:** `@task-flow-validate` · After changes: status is updated automatically; new lines trigger sync.
+
+**Not the same as:**
+- `task-flow: review` — only checks `done` subtasks; asks before status revert; does not add tasks.
+- `task-flow: think` — suggests tasks; **asks** before writing `tasks.input.txt`.
+
+## When to run
+
+User says `task-flow: validate`, `task-flow: validate X`, `task-flow: validate all`, `validar tasks`, `verificar lacunas`, `validate implementation gaps`, etc.
+
+Default scope when no ID: **`all`**.
+
+## Depth
+
+Use **thorough** reasoning: read each subtask `instructions`, `.task-flow/contexts/` when cited, verify files/tests/docs in the codebase — not a shallow grep. Optional: `graphify query "<module>"` per task area when `graphify-out/graph.json` exists.
+
+## Process
+
+### 1. Load
+
+- `.task-flow/tasks.input.txt` (lines `- ` only)
+- `.task-flow/.internal/tasks.json`, `status.json`
+- List `.task-flow/contexts/`
+
+### 2. Verify (scope: task X, X,Y, or all)
+
+For each task/subtask in scope:
+
+| Status | Check |
+|--------|--------|
+| `done` | Implementation exists and matches requirements (files, tests, docs per instructions) |
+| `pending` / `in_progress` | Whether code already partially or fully implements the subtask (status drift) |
+
+Record:
+
+- **Verified done** — correctly marked
+- **False done** — marked `done` but missing or incomplete
+- **Drift** — implemented in code but still `pending`
+- **Confirmed pending** — not implemented yet (expected)
+
+### 3. Lacunas (gaps)
+
+Find work not covered by current tasks:
+
+- Requirements from `done`/`pending` subtasks still missing in codebase
+- TODO/FIXME, missing tests, half-finished features, docs, wiring not listed in `tasks.input.txt`
+- Do **not** duplicate lines already in `tasks.input.txt` (match by meaning / `originalRequest`)
+
+### 4. Apply fixes (no ask — user invoked validate)
+
+1. **Status:** set false `done` → `pending` in `status.json`; optional drift `pending` → keep or note in report (do not auto-mark `done` without user run)
+2. **Input:** append new lacunas as `- Description` lines to `tasks.input.txt` (append only; never remove or edit existing lines)
+3. **Sync:** follow [task-flow-sync.mdc](mdc:.cursor/rules/task-flow-sync.mdc) — diff input, regen subtasks for new tasks, rebuild `tasks.status.md` Summary
+4. **Never** edit `.internal/` by hand except through sync-aligned updates to `status.json` for false-done fixes before sync
+
+### 5. Report
+
+```markdown
+## Task Flow Validate
+
+### Verified done
+- 1.2 Title — evidence (file paths)
+
+### False done → reverted to pending
+- 2.1 Title — what is missing
+
+### Lacunas added to tasks.input.txt
+- New line added: "- …"
+- (none)
+
+### Sync
+- N new task(s), M subtasks regenerated
+
+### Next
+- `task-flow: run next X` for pending work
+```
+
+## Natural language
+
+- `task-flow: validate` / `validate all`
+- `task-flow: validate 1` / `validate 2,3`
+- `validar tasks do task-flow`
+- `verificar lacunas e adicionar no task-flow`
+
+## Integration
+
+- Sync: [task-flow-sync.mdc](mdc:.cursor/rules/task-flow-sync.mdc)
+- Review (lighter): [task_review.mdc](mdc:.cursor/rules/task_review.mdc)
+- Think (suggest only): [task_analysis.mdc](mdc:.cursor/rules/task_analysis.mdc)
+- Git: [rbin-git-policy.mdc](mdc:.cursor/rules/rbin-git-policy.mdc)
+
+**Principle:** Validate = truth check + fill gaps. Done means done; missing work becomes new tasks automatically.

package/.task-flow/AI-PLATFORMS.md

@@ -56,7 +56,7 @@ Detalhes dos comandos: [README.md](README.md).
 | `.codex/config.toml` | — | — | ✅ (opcional, preservado no update) |
 | `task-flow-cursor.mdc` | — | ✅ always-on | — |
 | `rbin-git-policy.mdc` | — | ✅ always-on | — |
-| `.claude/skills/` | ✅ (14 skills) | — | — |
+| `.claude/skills/` | ✅ (15 skills) | — | — |
 | `.cursor/skills/` | — | ✅ (espelho) | — |
 
 Por padrão, `.claude/`, `.cursor/`, `.task-flow/`, `CLAUDE.md` e `AGENTS.md` entram no **`.gitignore`** do projeto cliente. Para versionar skills/regras com o time, ajuste o ignore — veja a seção “Versionamento” em cada guia.

package/.task-flow/CODEX.md

@@ -88,6 +88,20 @@ Rule: `.cursor/rules/task_review.mdc`
 
 ---
 
+## task-flow: validate
+
+1. Read `tasks.input.txt`, `tasks.json`, `status.json` — scope `all` or task ID(s).
+2. Thoroughly verify each subtask against codebase (`done` + `pending`).
+3. Revert false `done` → `pending` in `status.json`.
+4. Append lacunas as `- Description` to `tasks.input.txt` (no duplicates).
+5. Run sync workflow (section **Sync** in AGENTS.md).
+
+Rule: `.cursor/rules/task_validate.mdc`
+
+Unlike `think` (asks before add) or `review` (done only, asks before revert).
+
+---
+
 ## task-flow: refactor X
 
 Refactor task-related files: no behavior change, remove explanatory comments, keep section separators.

package/.task-flow/CURSOR.md

@@ -26,6 +26,7 @@ Verify: `rg 'alwaysApply: true' .cursor/rules` → only the two files above.
 | `task-flow: status` | `@task-flow-status` |
 | `task-flow: check` | `@task-flow-check` |
 | `task-flow: improve changes` | `@task-flow-improve-changes` |
+| `task-flow: validate` | `@task-flow-validate` |
 | Implement feature code | `@rbin-coding-standards` (explicit; checklist glob on `src/**`) |
 
 **Avoid:** `@task_work` (short fallback only — prefer `@task-flow-run`).

package/.task-flow/GRAPHIFY.md

@@ -54,7 +54,7 @@ task-flow: check
 |-------------------|----------------|
 | `sync`, `status`, `estimate`, `report`, `generate flow` | Não |
 | `run next X`, `run N` | Sim, se `graphify-out/` existir |
-| `think`, `review` | Opcional |
+| `think`, `review`, `validate` | Opcional |
 | `audit`, `improve changes` | Opcional (estrutura); padrões = checklist `coding_standards.mdc` |
 | `check` | Não |
 

package/.task-flow/README.md

@@ -27,6 +27,7 @@
 | `task-flow: run X,Y` | Executes multiple tasks (e.g., `task-flow: run 10,11`) |
 | `task-flow: run all` | Executes all tasks |
 | `task-flow: review X` | Reviews specific task(s) (e.g., `task-flow: review 1` or `task-flow: review 10,11` or `task-flow: review all`) |
+| `task-flow: validate` | Deep-validates tasks vs codebase, reverts false done, appends gaps to `tasks.input.txt`, syncs (default: all) |
 | `task-flow: refactor X` | Refactors specific task(s) (e.g., `task-flow: refactor 1` or `task-flow: refactor 10,11` or `task-flow: refactor all`) |
 | `task-flow: estimate X` | Estimates time for task X (e.g., `task-flow: estimate 1` or `task-flow: estimate 10,11`) |
 | `task-flow: report X` | Generates implementation report for task X (e.g., `task-flow: report 1` or `task-flow: report 10,11`) |
@@ -101,6 +102,16 @@ Reviews specific task(s) marked as "done" to verify they are actually completed.
 - `task-flow: review 10,11` → Reviews tasks 10 and 11
 - `task-flow: review all` → Reviews all tasks
 
+### `task-flow: validate`
+Deep validation: checks all subtasks (done and pending) against the codebase, reverts falsely marked `done`, discovers lacunas (missing tests, TODOs, incomplete work), **appends** them to `tasks.input.txt`, and runs sync. Unlike `think` (asks before add) or `review` (done only, asks before revert).
+
+**Examples:**
+- `task-flow: validate` → Validates all tasks
+- `task-flow: validate 1` → Validates task 1 only
+- `task-flow: validate 2,3` → Validates tasks 2 and 3
+
+**Invoke:** `@task-flow-validate` (Cursor) · `/task-flow-validate` (Claude)
+
 ### `task-flow: refactor X`
 Refactors code from specific task(s). Removes explanatory comments, improves code without changing functionality.
 

package/.task-flow/platforms/codex.md

@@ -163,6 +163,7 @@ Codex prefere `AGENTS.override.md` sobre `AGENTS.md` **no mesmo nível**.
 | `task-flow: improve changes` | `git diff --name-only HEAD` · checklist `coding_standards.mdc` nos paths alterados |
 | `task-flow: check` | `Rode lint:fix e build do package.json; corrija até passar` |
 | `task-flow: review 1` | `task_review.mdc — verifique se task 1 done está realmente implementada` |
+| `task-flow: validate` | `task_validate.mdc — valide todas as tasks, reverta false done, adicione lacunas em tasks.input.txt e sync` |
 | `task-flow: estimate 1` | `task_estimate.mdc para task 1` |
 | `task-flow: report 1` | `task_report.mdc — task 1 deve estar done` |
 | `task-flow: generate flow` | `task_generate_flow.mdc — preencher tasks.flow.md` |

package/AGENTS.md

@@ -36,6 +36,7 @@ No explanatory comments. Complex topics → `dev-logs/*.md`. Allowed: `// ──
 | `task-flow: improve changes` | `git diff --name-only HEAD` · `.cursor/rules/task_improve_changes.mdc` |
 | `task-flow: audit` | `.cursor/rules/task_audit.mdc` · checklist `coding_standards.mdc` (full: `.task-flow/docs/coding-standards-full.md` if needed) |
 | `task-flow: review X` | `.task-flow/CODEX.md` |
+| `task-flow: validate` | `.cursor/rules/task_validate.mdc` · then sync |
 | `task-flow: refactor X` | `.cursor/rules/task_refactor.mdc` |
 | `task-flow: estimate X` | `.task-flow/CODEX.md` |
 | `task-flow: report X` | `.task-flow/CODEX.md` |

package/CLAUDE.md

@@ -21,6 +21,7 @@
 | Audit repo | `/task-flow-audit` |
 | Audit diff only | `/task-flow-improve-changes` |
 | Verify done | `/task-flow-review` |
+| Validate + fill gaps | `/task-flow-validate` |
 | Refactor task code | `/task-flow-refactor` |
 | Estimate hours | `/task-flow-estimate` |
 | Implementation report | `/task-flow-report` |

package/README.md

@@ -33,7 +33,7 @@
 <a id="português"></a>
 # 🇧🇷 Português
 
-> **v1.23.1** — Graphify `--graphify` usa `claude-cli` por padrão (sem API key extra). De **1.23.0**: `npm install -g rbin-task-flow@1.23.1` e `rbin-task-flow update`. [CHANGELOG](CHANGELOG.md) · [Publicação](RELEASE-1.23.1.md).
+> **v1.24.0** — Novo `task-flow: validate` (auditoria profunda + lacunas automáticas). De **1.23.x**: `npm install -g rbin-task-flow@1.24` e `rbin-task-flow update`. [CHANGELOG](CHANGELOG.md) · [Publicação](RELEASE-1.24.0.md).
 
 ## O Que É Este Projeto?
 
@@ -93,13 +93,13 @@ Após inicializar, use estes comandos na IA (Cursor/Claude/Codex) para gerenciar
 
 **Graphify (opcional):** `rbin-task-flow init --graphify` configura coexistência e roda `graphify extract . --backend claude-cli` (CLI via `rbin-install-dev`; usa assinatura Claude Code).
 
-**Claude Code / Cursor skills (v1.20+):** `init` copia 14 skills para `.claude/skills/` e `.cursor/skills/` — use `/task-flow-sync`, `/task-flow-run`, etc.
+**Claude Code / Cursor skills (v1.20+):** `init` copia 15 skills para `.claude/skills/` e `.cursor/skills/` — use `/task-flow-sync`, `/task-flow-run`, `/task-flow-validate`, etc.
 
 **Codex (v1.21+):** `AGENTS.md` com sync/run embutidos, `.task-flow/CODEX.md` sob demanda, `.codex/config.toml` (64 KiB).
 
 **Cursor (v1.23+):** `task-flow-cursor.mdc` + `rbin-git-policy.mdc` (2 always-on) + skills — ver `.task-flow/CURSOR.md`.
 
-**Perfil minimal:** `init --profile minimal` instala só as 2 regras always-on e as 14 skills; workflows via `@task-flow-*` (sem `task_work`, `coding_standards` glob, etc.). `standard` (padrão) copia todas as regras `.cursor/rules/`.
+**Perfil minimal:** `init --profile minimal` instala só as 2 regras always-on e as 15 skills; workflows via `@task-flow-*` (sem `task_work`, `coding_standards` glob, etc.). `standard` (padrão) copia todas as regras `.cursor/rules/`.
 
 **Compartilhar com o time:** `init --share-ai-config` não ignora `.cursor/skills/` nem `.cursor/rules/` no `.gitignore` (só `.cursor/settings.json` e overrides locais). Padrão: `.cursor/` inteiro ignorado — menos ruído no repo, config local por dev.
 
@@ -116,6 +116,7 @@ Após inicializar, use estes comandos na IA (Cursor/Claude/Codex) para gerenciar
 | `task-flow: run X,Y` | **Completa** múltiplas tarefas | Executa tarefas separadas por vírgula (ex: `task-flow: run 10,11`) |
 | `task-flow: run all` | **Completa** todas as tarefas | Executa todas as tarefas pendentes |
 | `task-flow: review X` | **Garante** qualidade do trabalho | Verifica tarefas específicas (ex: `task-flow: review 1` ou `task-flow: review 10,11` ou `task-flow: review all`) |
+| `task-flow: validate` | **Valida** implementação e **preenche lacunas** | Auditoria profunda: reverifica done/pending, corrige status falso, adiciona lacunas em `tasks.input.txt` e faz sync |
 | `task-flow: refactor X` | **Melhora** código sem quebrar | Refatora tarefas específicas (ex: `task-flow: refactor 1` ou `task-flow: refactor 10,11` ou `task-flow: refactor all`) |
 | `task-flow: estimate X` | **Estima** tempo para gestão | Calcula estimativa de tempo (ex: `task-flow: estimate 1` ou `task-flow: estimate 10,11`) |
 | `task-flow: report X` | **Documenta** implementação | Gera relatório detalhado (ex: `task-flow: report 1` ou `task-flow: report 10,11`) |
@@ -418,7 +419,7 @@ Para problemas ou perguntas:
 <a id="english"></a>
 # 🇬🇧 English
 
-> **v1.23.1** — Graphify `--graphify` defaults to `claude-cli` (no separate API key). From **1.23.0**: `npm install -g rbin-task-flow@1.23.1` then `rbin-task-flow update`. [CHANGELOG](CHANGELOG.md) · [Release guide](RELEASE-1.23.1.md).
+> **v1.24.0** — New `task-flow: validate` (deep audit + auto gap fill). From **1.23.x**: `npm install -g rbin-task-flow@1.24` then `rbin-task-flow update`. [CHANGELOG](CHANGELOG.md) · [Release guide](RELEASE-1.24.0.md).
 
 ## What Is This Project?
 
@@ -478,11 +479,11 @@ After initializing, use these commands in your AI (Cursor/Claude/Codex) to autom
 
 **Graphify (optional):** `rbin-task-flow init --graphify` — cooperative setup + runs `graphify extract . --backend claude-cli` (CLI from `rbin-install-dev`; uses Claude Code subscription).
 
-**Claude / Cursor skills (v1.20+):** installs 14 skills — use `/task-flow-sync`, `/task-flow-run`, etc.
+**Claude / Cursor skills (v1.20+):** installs 15 skills — use `/task-flow-sync`, `/task-flow-run`, `/task-flow-validate`, etc.
 
 **Codex (v1.21+):** optimized `AGENTS.md`, `.task-flow/CODEX.md`, `.codex/config.toml`.
 
-**Cursor (v1.23+):** 2 always-on rules + 14 skills — `@task-flow-sync`, `@task-flow-run`.
+**Cursor (v1.23+):** 2 always-on rules + 15 skills — `@task-flow-sync`, `@task-flow-run`, `@task-flow-validate`.
 
 **Minimal profile:** `init --profile minimal` copies only `task-flow-cursor.mdc` and `rbin-git-policy.mdc` plus skills; use `@task-flow-*` for workflows. `standard` (default) copies all rules under `.cursor/rules/`.
 
@@ -501,6 +502,7 @@ After initializing, use these commands in your AI (Cursor/Claude/Codex) to autom
 | `task-flow: run X,Y` | **Complete** multiple tasks | Executes comma-separated tasks (e.g., `task-flow: run 10,11`) |
 | `task-flow: run all` | **Complete** all tasks | Executes all pending tasks |
 | `task-flow: review X` | **Ensure** work quality | Verifies specific tasks (e.g., `task-flow: review 1` or `task-flow: review 10,11` or `task-flow: review all`) |
+| `task-flow: validate` | **Validate** implementation and **fill gaps** | Deep audit: recheck done/pending, fix false done, append gaps to `tasks.input.txt`, then sync |
 | `task-flow: refactor X` | **Improve** code without breaking | Refactors specific tasks (e.g., `task-flow: refactor 1` or `task-flow: refactor 10,11` or `task-flow: refactor all`) |
 | `task-flow: estimate X` | **Estimate** time for management | Calculates time estimate (e.g., `task-flow: estimate 1` or `task-flow: estimate 10,11`) |
 | `task-flow: report X` | **Document** implementation | Generates detailed report (e.g., `task-flow: report 1` or `task-flow: report 10,11`) |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rbin-task-flow",
-  "version": "1.23.1",
+  "version": "1.24.0",
   "description": "AI-powered task management for Claude and Cursor",
   "main": "index.js",
   "bin": {