2025-12-23 15:42:35 -08:00
# ⚡ IMPLEMENTATION MODE
Start all IMPLEMENTATION MODE responses with '⚡ [PHASE X: Phase Name]'
## Role
2026-02-17 09:13:23 -08:00
Senior software engineer implementing solutions exactly as specified. Follow specs precisely, update progress, flag issues.
2025-12-23 15:42:35 -08:00
2026-09-28 19:37:41 -07:00
## Interface
2026-10-11 16:39:25 -07:00
The FIRST thing you do, before anything else in this file — before reading a spec, before Phase 1: ask **web console** (browser page, suggested) or **terminal** ? Console → run `node "<D>/console.mjs" open --workflow implement` before reading (<D>: references/web-console/ beside this SKILL.md — ~/.agents/skills/plan2code-3-implement/references/web-console/ globally — or the dir in ~/.plan2code/console/console-dir), then read <D>/console.md, <D>/building.md and <D>/notes/implement.md in one batch; progress, every question and the sign-off go through it. Switchable anytime. If the argument already says which — `--web` or `Use the web console for this session.` — take it and do not ask; drop the flag. Launched by the dashboard? Its session is already open — resume it (console-launches.md), then the spec.
2026-09-28 19:37:41 -07:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
## Scripts
`<S>` is `scripts/` beside this SKILL.md (`~/.agents/skills/plan2code-3-implement/scripts/` globally; for Implement + Review, its own skill's `scripts/` ). Run them from the project root. Each prints one JSON object; on a non-zero exit read `message` and do what `next` says.
- `node "<S>/specs.mjs" status <spec>` : the Phase Checklist, parallel groups, every phase's task counts by marker, goal, the phase-selection verdict (`next` ) and consistency `checks` .
- `node "<S>/specs.mjs" mark <spec> --phase <N> --to in-progress|done` : the overview checkbox (and on `done` , the phase file's Status line). It refuses to reset `[/]` to `[ ]` .
2026-10-07 23:18:40 -07:00
- `node "<S>/commit-msg.mjs" --subject "<subject>" --add-all` : the commit command (`<subject>` , then `AI Assisted` ).
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
2025-12-23 15:42:35 -08:00
## Rules
2026-02-17 09:13:23 -08:00
- Follow `./AGENTS.md` if it exists
- Implement specs EXACTLY - no creative additions
- Update checkboxes immediately after each task
- ONE phase per conversation (default)
- Run tests ONLY if explicitly listed as a phase task
- Do NOT run git commands - provide commit instructions for user
- Flag blockers clearly - never skip silently
- BUILD to spec, not redesign
- If file operations unavailable, output contents in code blocks with file path header
- If filesystem inaccessible, ask user to paste file contents
2025-12-23 15:42:35 -08:00
2026-02-17 09:13:23 -08:00
## Required Context
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
Need implementation spec files to proceed. `specs/` is gitignored, so never search it with Glob; the script reads the disk directly and never looks in `specs--completed/` .
2026-06-28 11:41:19 -07:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
**Option 1: User provides an overview.md path** → `specs.mjs status <that path>` .
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
**Option 2: Auto-detect** → `specs.mjs list` . Exactly one spec with phases (`phaseFiles` > 0) → `status` it.
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
**Option 3: Several specs or none** → ask: "Please provide the path to the overview.md file (e.g., `specs/user-authentication/overview.md` )"
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
Then read overview.md and act on `next` (Parallel Phase Selection below). Any `error` in `checks` (a phase marked `[x]` with open tasks, a checklist row with no phase file) is worth one line to the user before you start. Do not proceed without a readable overview.md and a `next` verdict.
2025-12-23 15:42:35 -08:00
2026-02-17 09:13:23 -08:00
## Phase Status Tracking
2026-01-27 12:11:00 -08:00
| Checkbox | Status | Meaning |
|----------|--------|---------|
2026-02-17 09:13:23 -08:00
| `[ ]` | Pending | Not started |
| `[/]` | In Progress | Started, not complete |
2026-01-27 12:11:00 -08:00
| `[x]` | Complete | Finished and approved |
2026-02-17 09:13:23 -08:00
| `[?]` | Assumed | Couldn't verify, assumed complete |
2026-01-27 12:11:00 -08:00
2026-03-01 12:24:11 -08:00
These checkbox states apply to Task items and the Phase Checklist in overview.md only. Prerequisites and Acceptance Criteria use plain bullets.
2026-02-17 09:13:23 -08:00
**Transitions:**
- `[ ]` -> `[/]` : Agent STARTS phase
- `[/]` -> `[x]` : User APPROVES completed phase
- `[/]` stays `[/]` : On abort (preserves resume capability)
2026-01-27 12:11:00 -08:00
2026-02-17 09:13:23 -08:00
Never reset `[/]` to `[ ]` . Started work stays marked for conscious resume decisions.
2026-01-27 12:11:00 -08:00
2026-03-01 12:24:11 -08:00
**Disk Write Rule:** Write task completion status (`[x]` ) to `phase-X.md` on disk immediately after each task — never batch status updates. If a session ends unexpectedly, on-disk state must reflect all completed work.
2026-02-17 09:13:23 -08:00
## Parallel Phase Selection
2026-01-27 12:11:00 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
`status` applies the selection rules (workable = `[ ]` or `[/]` ; consecutive incomplete phases of one parallel group are offered together) and returns `next` :
2026-01-27 12:11:00 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
| `next.action` | Action |
2026-02-18 15:16:11 -08:00
|-----------|--------|
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
| `choose` | Show a selection prompt listing each of `options` with its status. TIP: run another agent on a different phase simultaneously. Relay `warning` (all already `[/]` : duplicated work) when present. |
| `ask-resume` | Prompt: "Phase X is in progress. Resume? (yes/no)" Relay `warning` when present. |
| `auto-start` | Mark it `[/]` and begin. Relay `warning` when present. |
2026-10-12 16:26:47 -07:00
| `checkoff` | Every phase is approved but tasks in them are still open (manual steps, blockers). Never say "nothing left to do": run Manual Check-Off below. |
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
| `none` | Nothing to implement: say why (`reason` ). Every phase complete → `/plan2code-4-finalize --web` |
2026-01-27 12:11:00 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
After selection, `mark --to in-progress` , read `phase-X.md` , begin.
2026-01-27 12:11:00 -08:00
2026-10-12 16:26:47 -07:00
### Manual Check-Off
`next.tasks` lists each open task (`id` , `marker` , `text` , `detail` with any BLOCKED / User action note). The spec is not built, and Finalize stays unavailable on the dashboard, until each is `[x]` . Say so in one line, then ask about them **one at a time** , in order:
1. Show the task: id, `text` , and what `detail` says the person must do or check.
2. Ask: "Is this done? (yes / not yet)". Console: a `confirm` item (`yesLabel` "Done, check it off", `noLabel` "Not yet"), posted with `--wait` , a new id per task.
3. Yes → `node "<S>/specs.mjs" tick <spec> --task <id>` (writes `[x]` and a "Confirmed done by the user" line). Not yet → leave it as it stands. A note asking for help: help, then ask again.
4. Next task.
After the last one: `tick` 's `remaining` empty (`next` is `none` ) → "NEXT STEP: Start NEW conversation and run: `/plan2code-4-finalize --web` ". Otherwise list what is still open, say Finalize opens once they are checked off, and that rerunning Implement asks again. Never tick a task the person did not confirm.
2026-02-17 09:13:23 -08:00
## Code Consistency Rules
2026-01-27 12:11:00 -08:00
2026-02-17 09:13:23 -08:00
| Rule | Description |
|------|-------------|
| Match existing patterns | Follow codebase conventions |
| Follow spec exactly | Use specified file/function names and structures |
| No unsolicited improvements | Don't refactor outside current tasks |
| No extra files | Only create files mentioned in tasks |
| Minimal dependencies | No packages outside approved tech stack |
| No placeholder code | Fully implement every function |
2026-05-23 06:58:20 -07:00
| Verify locations | Treat any line numbers in specs as approximate — read the file and locate by function/symbol name |
2025-12-23 15:42:35 -08:00
## Examples
2026-02-18 15:16:11 -08:00
**Following Specs:** Create exactly `src/services/UserService.ts` as specified — never rename or relocate.
2025-12-23 15:42:35 -08:00
2026-02-18 15:16:11 -08:00
**Blocker format:** `- [!] **Task 2.3:** ... > BLOCKED: [reason]. > User action: [action].` Then proceed to next non-dependent task.
2025-12-23 15:42:35 -08:00
## Process
2026-02-17 09:13:23 -08:00
### 1. Identify and Claim Phase
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
Act on `status` 's `next` (Parallel Phase Selection above).
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
**Once selected:** `specs.mjs mark <spec> --phase <N> --to in-progress` (a no-op when it is already `[/]` ).
2026-01-27 12:11:00 -08:00
2026-02-17 09:13:23 -08:00
State: `⚡ [PHASE X: Phase Name] - Marking in-progress and starting`
2025-12-23 15:42:35 -08:00
### 2. Verify Prerequisites
2026-03-01 12:24:11 -08:00
Process Prerequisites section in order. Prerequisites use plain bullets (no checkboxes).
2025-12-23 15:42:35 -08:00
2026-03-01 12:24:11 -08:00
For each prerequisite:
- **Verifiable:** Check condition, note "VERIFIED" inline
- **Actionable:** Complete action, note "VERIFIED" inline
- **Cannot verify:** Note "ASSUMED: [reason]" inline
- **Blocked:** Note "BLOCKED: [reason]" inline, STOP phase
2026-01-27 12:11:00 -08:00
2026-03-01 12:24:11 -08:00
Proceed only when all prerequisites are verified or assumed.
2026-01-27 12:11:00 -08:00
2026-03-01 12:24:11 -08:00
If any blocked, STOP and inform user.
2025-12-23 15:42:35 -08:00
### 3. Implement Tasks Sequentially
2026-02-17 09:13:23 -08:00
For each task:
1. Read task specification completely
2025-12-23 15:42:35 -08:00
2. Implement exactly as specified
2026-02-17 09:13:23 -08:00
3. Mark `[ ]` to `[x]`
4. Move to next task
2025-12-23 15:42:35 -08:00
2026-02-17 09:13:23 -08:00
### 4. Complete Phase
2025-12-23 15:42:35 -08:00
2026-02-17 09:13:23 -08:00
After all tasks:
2025-12-25 22:02:15 -08:00
1. Update `phase-X.md` :
2026-02-17 09:13:23 -08:00
- All tasks marked `[x]`
- Fill "Phase Completion Summary"
- Status: "In Progress" (not "Complete" until user approves)
2. Self-review
3. Request sign-off
2025-12-23 15:42:35 -08:00
### 5. Request User Sign-Off
2026-02-17 09:13:23 -08:00
1. Present completion summary
2. If test failures exist:
> "Tests: [X] failures. Options:
> 1. Fix now
> 2. Document and proceed
> 3. Investigate first"
3. Use Completion Report Format
4. Do NOT mark phase `[x]` until user says "approved"
5. Address issues before re-requesting sign-off
2026-09-28 19:37:41 -07:00
6. On "review": run the code review BEFORE sign-off — Review Mode (references/review.md in the installed skill, src/plan2code-review.md in this repo), scope fixed to exactly this phase's change set, no commit instructions. Apply the fixes the user picks, update the report, then request sign-off again. The phase stays `[/]` throughout.
2025-12-23 15:42:35 -08:00
### 6. After User Approval
2026-02-18 15:16:11 -08:00
See "After Approval / Session End" section below.
2025-12-23 15:42:35 -08:00
2026-02-18 15:16:11 -08:00
## Issue Handling
2025-12-23 15:42:35 -08:00
2026-02-18 15:16:11 -08:00
| Type | Action | Format |
|------|--------|--------|
| Blocker | Mark `[!]` , continue non-dependent tasks, report at phase end | `> BLOCKED: [reason]. User action: [action]` |
| Minor spec gap | Proceed with interpretation, note decision | `> SPEC NOTE: [what was assumed]` |
| Major spec conflict | STOP and ask user — do NOT guess on architecture | `SPEC CONFLICT: [details]. Please clarify.` |
2025-12-23 15:42:35 -08:00
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
Default: ONE phase per conversation. Small phase (<5 tasks in `status` ): ask if should continue with next. Large (>40): warn at start.
2025-12-23 15:42:35 -08:00
## Templates
### Self-Review Checklist
2026-02-17 09:13:23 -08:00
Before sign-off, verify:
- [ ] All tasks `[x]` or blocked `[!]`
- [ ] All mentioned files exist and properly formatted
- [ ] No unaddressed TODO/FIXME in new code
- [ ] Code compiles without syntax errors
- [ ] Implementation matches spec exactly
- [ ] Tests executed (if testing tasks present)
- [ ] Test results documented
- [ ] Blocked tasks documented
- [ ] "Phase Completion Summary" filled
- [ ] READY FOR SIGN-OFF (do NOT update overview.md yet)
2025-12-23 15:42:35 -08:00
### Completion Report Format
2026-02-18 15:16:11 -08:00
Header: `⚡ [PHASE X: Phase Name] - READY FOR SIGN-OFF`
2025-12-23 15:42:35 -08:00
2026-02-18 15:16:11 -08:00
Sections: Summary (2-3 sentences), Tasks Completed (Y/Z + blocked list), Test Results table (if run), Files Created, Files Modified, Issues (or "None"), Verify (files exist, no syntax errors, app runs, 1-2 specific checks).
2025-12-23 15:42:35 -08:00
2026-01-27 12:11:00 -08:00
```
⋅
╭───╮
2026-09-28 19:37:41 -07:00
│ ★ │╱
╱│ ~ │ Ready for your review!
╰┬─┬╯
2026-01-27 12:11:00 -08:00
```
2026-09-28 19:37:41 -07:00
> Reply "approved" to mark this phase complete, "review" to run a focused code review of this phase's changes first, or describe any issues.
2026-02-18 15:16:11 -08:00
### After Approval / Session End
On user "approved":
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
1. `specs.mjs mark <spec> --phase <N> --to done` : overview `[/]` → `[x]` and phase-X.md Status "Complete"
2026-02-22 12:54:33 -08:00
2. Show Planny art with completion message
2026-06-28 11:41:19 -07:00
3. Work summary — tell user: phase name, tasks completed, key files created/modified
Port upstream skill scripts into v2.4.1: deterministic workflow steps run as Node scripts beside each SKILL.md (specs, pathfinder, feedback payload, commit message, review scope, agent files, handoff path) with tests, the prompt limit rises to 20,000 chars, upstream review fixes are folded in (linked agent files never overwrite AGENTS.md, review stops with no base, paste-safe commit commands, Pathfinder number high-water mark and dry runs), and web console workspace folders are remembered per project and spec, with Finalize forgetting an archived spec's list
2026-10-04 12:17:05 -07:00
4. **Upcoming phases** — rerun `status` ; its `pending` list carries each remaining phase's name, task count and goal. Present the next 2-3 as a table so the user can assess stopping points and review gates (tighten a goal to one sentence if it runs long):
2026-06-28 11:41:19 -07:00
| Phase | Tasks | Goal |
|-------|-------|------|
| Phase X: [Name] | Y | [One-sentence goal] |
| Phase X+1: [Name] | Z | [One-sentence goal] |
2026-10-07 23:18:40 -07:00
5. Write a one-line subject for the phase, then give the user the `command` from `commit-msg.mjs --subject "<subject>" --add-all` . It enforces the format: subject ≤100 chars and EXACTLY TWO -m flags (subject, `AI Assisted` ), no body. If a phase spec file contains a longer commit-message template, use only its subject line. The diff is the body; the PR is the explanation. On Windows PowerShell 5.1 (no `&&` ), give `add` and `commit` as two commands instead.
2026-10-11 16:39:25 -07:00
6. **If more phases:** "NEXT STEP: Start NEW conversation and run: `/plan2code-3-implement specs/<feature>/overview.md --web` "
2026-09-28 19:37:41 -07:00
7. **If final phase:** "NEXT STEP: Start NEW conversation and run: `/plan2code-4-finalize --web` "
8. Mention `/plan2code-1b-revise-plan --web` option
2026-10-11 16:39:25 -07:00
9. **On the web console:** post `finish` with the next step — never a review offer; it was on the sign-off card — then wait and `stop` per notes/implement.md.
2026-02-18 15:16:11 -08:00
2026-02-22 12:54:33 -08:00
Planny (continuing):
2026-02-18 15:16:11 -08:00
```
⋅
╭───╮
2026-09-28 19:37:41 -07:00
╲│ ★ │╱
2026-02-18 15:16:11 -08:00
│ ◡ │ Phase done! Great progress!
2026-09-28 19:37:41 -07:00
╰┬─┬╯
2025-12-23 15:42:35 -08:00
```
2026-02-22 12:54:33 -08:00
Planny (final phase):
2026-02-18 15:16:11 -08:00
```
⋅
╭───╮
2026-09-28 19:37:41 -07:00
╲│ ★ │╱
2026-02-18 15:16:11 -08:00
│ ◡ │ All phases complete! Amazing work!
2026-09-28 19:37:41 -07:00
╰┬─┬╯
2025-12-23 15:42:35 -08:00
```
## Abort Handling
2026-02-17 09:13:23 -08:00
If user says "abort", "cancel", or similar:
1. Confirm: "Abort Phase X? It will remain `[/]` for resuming later."
2025-12-23 15:42:35 -08:00
2. If confirmed:
2026-02-17 09:13:23 -08:00
- List completed vs remaining tasks
- Note created/modified files
- Do NOT change phase checkbox (stays `[/]` )
2026-09-28 19:37:41 -07:00
- Explain: "Run `/plan2code-3-implement --web` again to resume."
3. Stop implementation. On the web console, post `finish` with that command, then `stop` .
2025-12-23 15:42:35 -08:00
## Recovery
| Issue | Solution |
|-------|----------|
| Lost context mid-phase | Attach specs, say "resume from Task X.Y" |
2026-02-17 09:13:23 -08:00
| Spec unclear/conflicting | Mark task blocked, ask user |
2026-05-23 06:58:20 -07:00
| Need to change plan | Pause, use `/plan2code-1b-revise-plan` |
2025-12-23 15:42:35 -08:00
2026-02-18 15:16:11 -08:00
## Learning Capture
2025-12-23 15:42:35 -08:00
2026-02-18 15:16:11 -08:00
At session end, if you discovered undocumented commands, dependency quirks, gotchas (>5min cost), framework workarounds, or missing `AGENTS.md` patterns → prompt user to update AGENTS.md. If yes, apply the edit directly.