feat(skills): rename sp-writing-plans → sp-planning, add explore-reality phase

.tokeignore

@@ -0,0 +1,3 @@
+internal/ent/**
+!internal/ent/schema/**
+**/*.md

CLAUDE.md

@@ -278,7 +278,7 @@ templates/
     └── ...
   docs/
     skills/            - Skill directories (each has SKILL.md)
-      ├── sp-writing-plans/SKILL.md   - Plan writing methodology
+      ├── sp-planning/SKILL.md        - Full planning process (explore → design → write → validate)
       ├── sp-debugging/SKILL.md       - Bug diagnosis + fix plans
       ├── sp-brainstorming/SKILL.md   - Brainstorming framework
       └── ...

cmd/agent.go

@@ -202,9 +202,6 @@ Example:
 		if ag.Voice != "" {
 			fmt.Printf("Voice:     %s\n", ag.Voice)
 		}
-		if ag.FlicknoteProject != "" {
-			fmt.Printf("Flicknote: %s\n", ag.FlicknoteProject)
-		}
 		return nil
 	},
 }
@@ -244,10 +241,10 @@ Examples:
 				if !voice.IsValidVoice(value) {
 					return fmt.Errorf("unknown voice '%s' — run 'ttal voice list' to see available voices", value)
 				}
-			case "emoji", "description", "role", "flicknote_project":
+			case "emoji", "description", "role":
 				// valid fields
 			default:
-				return fmt.Errorf("unknown field '%s' (available: voice, emoji, description, role, flicknote_project)", field)
+				return fmt.Errorf("unknown field '%s' (available: voice, emoji, description, role)", field)
 			}
 
 			if err := agentfs.SetField(teamPath, name, field, value); err != nil {

docs/docs/agents.md

@@ -42,7 +42,6 @@ All frontmatter fields are optional:
 | `emoji` | Display emoji | `🦅`, `🐱` |
 | `description` | Short role summary | `Task orchestration and planning` |
 | `role` | Role key matching `[role]` in `roles.toml` | `manager`, `designer` |
-| `flicknote_project` | Default flicknote project (injected as `$FLICKNOTE_PROJECT`) | `ttal.plans` |
 
 Agent `.md` frontmatter is the single source of truth for agent identity and per-agent config.
 Operational config (prompts, heartbeat) lives in `~/.config/ttal/roles.toml` per role.
@@ -84,7 +83,6 @@ Update frontmatter fields with `field:value` syntax:
 ```bash
 ttal agent modify kestrel voice:af_heart
 ttal agent modify kestrel emoji:🦅 description:'Worker lifecycle'
-ttal agent modify kestrel flicknote_project:ttal.fixes
 ```
 
 ## One bot per agent

docs/docs/configuration.md

@@ -52,7 +52,7 @@ that contains a `CLAUDE.md` file is treated as an agent.
 ```
 
 Agent configuration lives in two places:
-- **CLAUDE.md frontmatter** — identity (role, emoji, voice, description, flicknote_project)
+- **CLAUDE.md frontmatter** — identity (role, emoji, voice, description)
 - **roles.toml** — operational config per role (prompts, heartbeat_interval)
 
 Bot tokens follow the naming convention `{UPPER_NAME}_BOT_TOKEN` in `~/.config/ttal/.env`.
@@ -90,7 +90,6 @@ description: Task orchestrator — creates and routes work
 emoji: 🐱
 role: manager
 voice: af_heart
-flicknote_project: ttal.plans
 ---
 ```
 
@@ -100,7 +99,6 @@ flicknote_project: ttal.plans
 | `emoji` | string | Display emoji |
 | `role` | string | Role key that maps to `[role]` in roles.toml |
 | `voice` | string | Kokoro TTS voice ID (e.g. `af_heart`) |
-| `flicknote_project` | string | Default flicknote project (injected as `$FLICKNOTE_PROJECT`) |
 
 ## roles.toml fields
 

internal/agentfs/agentfs.go

@@ -42,13 +42,12 @@ func isAgentFile(e fs.DirEntry) (name string, ok bool) {
 
 // AgentInfo holds agent metadata parsed from .md file frontmatter.
 type AgentInfo struct {
-	Name             string // directory name (lowercase)
-	Path             string // absolute path to agent directory
-	Voice            string // Kokoro TTS voice ID
-	Emoji            string // display emoji
-	Description      string // short role summary
-	Role             string // e.g. designer, researcher — matches [prompts] key
-	FlicknoteProject string // default flicknote project for this agent
+	Name        string // directory name (lowercase)
+	Path        string // absolute path to agent directory
+	Voice       string // Kokoro TTS voice ID
+	Emoji       string // display emoji
+	Description string // short role summary
+	Role        string // e.g. designer, researcher — matches [prompts] key
 }
 
 // Discover scans teamPath for agents via flat .md files (e.g., yuki.md).
@@ -79,7 +78,6 @@ func Discover(teamPath string) ([]AgentInfo, error) {
 			info.Emoji = fm["emoji"]
 			info.Description = fm["description"]
 			info.Role = fm["role"]
-			info.FlicknoteProject = fm["flicknote_project"]
 		} else {
 			log.Printf("agentfs: failed to parse frontmatter for %s: %v", name, err)
 		}
@@ -112,7 +110,6 @@ func Get(teamPath, name string) (*AgentInfo, error) {
 		info.Emoji = fm["emoji"]
 		info.Description = fm["description"]
 		info.Role = fm["role"]
-		info.FlicknoteProject = fm["flicknote_project"]
 	} else {
 		log.Printf("agentfs: failed to parse frontmatter for %s: %v", name, err)
 	}

internal/config/config.go

@@ -248,7 +248,6 @@ type AgentConfig struct {
 	Runtime           string `toml:"runtime"          jsonschema:"-"`
 	Model             string `toml:"model"            jsonschema:"-"`
 	HeartbeatInterval string `toml:"heartbeat_interval" jsonschema:"-"`
-	FlicknoteProject  string `toml:"flicknote_project"  jsonschema:"-"`
 }
 
 // AgentBotToken returns the bot token for an agent using the naming convention.

internal/config/config_render_test.go

@@ -21,21 +21,21 @@ func TestRenderSkillPlaceholders(t *testing.T) {
 		},
 		{
 			name:  "CC replaces skill placeholder at start",
-			input: "{{skill:sp-writing-plans}}\nWrite a plan for task {{task-id}}",
+			input: "{{skill:sp-planning}}\nWrite a plan for task {{task-id}}",
 			rt:    runtime.ClaudeCode,
-			want:  "Use sp-writing-plans skill\n\nWrite a plan for task abc123",
+			want:  "Use sp-planning skill\n\nWrite a plan for task abc123",
 		},
 		{
 			name:  "Codex replaces skill placeholder with dollar",
-			input: "{{skill:sp-writing-plans}}\nWrite a plan for task {{task-id}}",
+			input: "{{skill:sp-planning}}\nWrite a plan for task {{task-id}}",
 			rt:    runtime.Codex,
-			want:  "$sp-writing-plans\n\nWrite a plan for task abc123",
+			want:  "$sp-planning\n\nWrite a plan for task abc123",
 		},
 		{
 			name:  "multiple skill placeholders",
-			input: "{{skill:sp-writing-plans}}\n{{skill:flicknote-cli}}\nDo the thing",
+			input: "{{skill:sp-planning}}\n{{skill:flicknote}}\nDo the thing",
 			rt:    runtime.Codex,
-			want:  "$sp-writing-plans\n$flicknote-cli\n\nDo the thing",
+			want:  "$sp-planning\n$flicknote\n\nDo the thing",
 		},
 		{
 			name:  "no placeholders unchanged",

internal/daemon/agents.go

@@ -9,7 +9,6 @@ import (
 	"strings"
 	"sync"
 
-	"github.com/tta-lab/ttal-cli/internal/agentfs"
 	"github.com/tta-lab/ttal-cli/internal/claudeconfig"
 	"github.com/tta-lab/ttal-cli/internal/config"
 	"github.com/tta-lab/ttal-cli/internal/runtime"
@@ -73,14 +72,6 @@ func buildAgentEnv(agentName, teamName string, mcfg *config.DaemonConfig) []stri
 	if team, ok := mcfg.Teams[teamName]; ok && team.TaskRC != "" {
 		env = append(env, fmt.Sprintf("TASKRC=%s", team.TaskRC))
 	}
-	// Read flicknote_project from CLAUDE.md frontmatter
-	if team, ok := mcfg.Teams[teamName]; ok && team.TeamPath != "" {
-		info, err := agentfs.GetFromPath(filepath.Join(team.TeamPath, agentName))
-		if err == nil && info.FlicknoteProject != "" {
-			env = append(env, fmt.Sprintf("FLICKNOTE_PROJECT=%s", info.FlicknoteProject))
-		}
-	}
-
 	// Inject all secrets from .env
 	env = append(env, config.DotEnvParts()...)
 

internal/daemon/routing.go

@@ -9,7 +9,6 @@ import (
 	"strings"
 	"time"
 
-	"github.com/tta-lab/ttal-cli/internal/agentfs"
 	"github.com/tta-lab/ttal-cli/internal/breathe"
 	"github.com/tta-lab/ttal-cli/internal/config"
 	"github.com/tta-lab/ttal-cli/internal/env"
@@ -392,7 +391,7 @@ func handleBreathe(shellCfg *config.Config, req BreatheRequest) SendResponse {
 		log.Printf("[breathe] warning: failed to write status for %s/%s: %v", team, req.Agent, err)
 	}
 
-	// 8. Build restart command with full env (secrets, TASKRC, FLICKNOTE_PROJECT).
+	// 8. Build restart command with full env (secrets, TASKRC).
 	ccCmd := buildCCRestartCmd(newSessionID, am.model, req.Agent, trigger)
 	agentEnv := buildBreatheEnv(req.Agent, team, shellCfg)
 	fullCmd := shellCfg.BuildEnvShellCommand(agentEnv, ccCmd)
@@ -419,7 +418,7 @@ func handleBreathe(shellCfg *config.Config, req BreatheRequest) SendResponse {
 }
 
 // buildBreatheEnv returns the env var list for a breathe restart command.
-// Mirrors buildAgentEnv: agent identity, TASKRC, FLICKNOTE_PROJECT, and .env secrets.
+// Mirrors buildAgentEnv: agent identity, TASKRC, and .env secrets.
 func buildBreatheEnv(agent, team string, cfg *config.Config) []string {
 	vars := []string{
 		fmt.Sprintf("TTAL_AGENT_NAME=%s", agent),
@@ -428,12 +427,6 @@ func buildBreatheEnv(agent, team string, cfg *config.Config) []string {
 	if taskRC := cfg.TaskRC(); taskRC != "" {
 		vars = append(vars, fmt.Sprintf("TASKRC=%s", taskRC))
 	}
-	agentInfo, err := agentfs.Get(cfg.TeamPath(), agent)
-	if err != nil {
-		log.Printf("[breathe] %s: could not read agent config, FLICKNOTE_PROJECT omitted: %v", agent, err)
-	} else if agentInfo.FlicknoteProject != "" {
-		vars = append(vars, fmt.Sprintf("FLICKNOTE_PROJECT=%s", agentInfo.FlicknoteProject))
-	}
 	vars = append(vars, config.DotEnvParts()...)
 	return vars
 }

internal/tui/actions.go

@@ -30,7 +30,7 @@ func advanceTask(uuid string) tea.Cmd {
 		if err != nil {
 			return actionResultMsg{err: fmt.Errorf("advance %s: %s", short, strings.TrimSpace(string(out)))}
 		}
-		return actionResultMsg{message: fmt.Sprintf("Advanced %s", short), refresh: true}
+		return actionResultMsg{message: strings.TrimSpace(string(out)), refresh: true}
 	}
 }
 

templates/basic/README.md

@@ -17,7 +17,7 @@ A minimal ttal setup with two agents: one manages tasks, one designs implementat
 
 ```
 You create a task
-  → manager routes it: ttal task design <uuid>
+  → manager advances it: ttal task go <uuid>
   → designer writes an implementation plan
   → you approve
   → manager spawns a worker: ttal task go <uuid>

templates/basic/designer.md

@@ -26,8 +26,7 @@ You are the design agent. You turn requirements into detailed implementation pla
 4. Write a detailed implementation plan
 5. Save the plan as markdown: `docs/plans/YYYY-MM-DD-<topic>.md`
 6. Annotate the task: `task <uuid> annotate 'Plan: docs/plans/<filename>.md'`
-7. Tag as planned: `task <uuid> modify -brainstorm -design +planned`
-8. Wait for human approval before execution
+7. Wait for human approval before execution
 
 ## Plan Quality
 

templates/basic/manager.md

@@ -13,7 +13,7 @@ You are the task manager for this team. You organize work, route tasks to the ri
 ## Your Role
 
 - Manage tasks via taskwarrior: create, prioritize, tag, schedule
-- Route tasks to agents: `ttal task design` for planning, `ttal task go` for implementation
+- Route tasks to agents: `ttal task go` advances tasks through the pipeline
 - Maintain the daily focus list with `ttal today`
 - Respond to human messages and status requests
 - Monitor worker progress via `ttal worker list`
@@ -23,8 +23,7 @@ You are the task manager for this team. You organize work, route tasks to the ri
 When a new task comes in:
 1. Read it: `ttal task get <uuid>`
 2. Decide what it needs:
-   - Needs a plan? → `ttal task design <uuid>`
-   - Ready to execute? → `ttal task go <uuid>` (only after human approval)
+   - Advance to next stage? → `ttal task go <uuid>` (only after human approval)
 3. Track progress and report status
 
 When the human asks "what's happening?":

templates/basic/roles.toml

@@ -12,5 +12,4 @@ prompt = """Write an implementation plan for this task.
 Read the task first: ttal task get {{task-id}}
 
 Save plan to: docs/plans/YYYY-MM-DD-<topic>.md in the project repo.
-When done: task {{task-id}} annotate 'Plan: docs/plans/<filename>.md'
-Then tag-swap: task {{task-id}} modify -brainstorm -design +planned"""
+When done: task {{task-id}} annotate 'Plan: docs/plans/<filename>.md'"""

templates/docs/README.md

@@ -6,7 +6,7 @@ This directory contains skills, subagents, and commands that `ttal sync` deploys
 
 ```
 docs/
-├── skills/       # Methodology skills (sp-writing-plans, sp-tdd, etc.)
+├── skills/       # Methodology skills (sp-planning, sp-tdd, etc.)
 ├── agents/       # Subagent definitions (pr-reviewers, task-creator, etc.)
 └── commands/     # Slash commands (pr-review, triage, etc.)
 ```
@@ -38,7 +38,7 @@ Create a new directory in `docs/skills/` with a `SKILL.md` file. See existing sk
 ### Skills
 | Skill | Purpose |
 |-------|---------|
-| sp-writing-plans | Write detailed implementation plans |
+| sp-planning | Write detailed implementation plans |
 | sp-executing-plans | Execute plans step by step |
 | sp-research | Structured research methodology |
 | sp-brainstorming | Collaborative idea exploration and design |

templates/docs/skills/sp-debugging/SKILL.md

@@ -184,9 +184,8 @@ task <uuid> annotate 'Fix plan: flicknote <hex-id>'
 1. **Save the plan** — inline annotation or flicknote (see above)
 2. **Create a task** (if needed) via `ttal task add --project <alias> "description"`
 3. **Annotate the task** with plan reference (inline or flicknote hex ID)
-4. **Tag as planned:** `task <uuid> modify -bugfix +planned`
-5. **Review:** Run at least 1 round of `/plan-review <flicknote-id>`. Revise if needed.
-6. **Execute:** When the plan passes review, run `ttal task go <uuid>` to spawn a worker.
+4. **Review:** Run at least 1 round of `/plan-review <flicknote-id>`. Revise if needed.
+5. **Execute:** When the plan passes review, run `ttal task go <uuid>` to spawn a worker.
 
 ## Red Flags — STOP and Return to Phase 1
 

templates/docs/skills/sp-executing-plans/SKILL.md

@@ -137,5 +137,5 @@ Don't guess your way through blockers — alert and wait.
 ## Integration
 
 **Required workflow skills:**
-- **sp-writing-plans** - Creates the plan this skill executes
+- **sp-planning** - Creates the plan this skill executes
 - **knowledge** - Vault conventions (frontmatter, folder structure)