2026-07-20 22:07:21 -07:00
# plan2code-handoff
Turn everything useful in the current conversation into a single, self-contained
handoff document that lets a *different* agent — a new session, a teammate's
session, or a subagent — resume the work without re-reading this transcript.
The reader of this document starts with **zero context** . They can see the repo
and can open files, but they cannot see this conversation. Write for them.
2026-09-28 19:37:41 -07:00
## Interface
2026-11-02 12:00:11 -08:00
The FIRST thing you do, before anything else in this file — before inferring the next task: ask **web console** (browser page, suggested) or **terminal** ? Console → run `node "<D>/console.mjs" open --workflow handoff` before reading (<D>: references/web-console/ beside this SKILL.md — ~/.agents/skills/plan2code-handoff/references/web-console/ globally — or the dir in ~/.plan2code/console/console-dir), then read <D>/console.md and <D>/notes/handoff.md. The next-task confirmation and any clarifying questions go through it, and the finished handoff lands on the page as a doc with the download the page offers. 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 one hard rule.
2026-09-28 19:37:41 -07:00
2026-07-20 22:07:21 -07:00
## The one hard rule: capture the next task, and confirm it with the user
Every handoff MUST end with a **Next task** that the incoming agent should start
on. This is the single most important part of the document — a handoff with a
vague or missing next step forces the reader to re-derive intent, which is
exactly what this skill exists to prevent.
Determine it like this:
1. **Try to infer it** from the conversation — the open TODO, the failing test,
the plan step you were mid-way through, the thing the user just asked for
next. Look at what's actually unfinished, not just the last message.
2. **Present it to the user for confirmation before writing the file.** If you
inferred a candidate, show it and ask them to confirm or correct it. If you
genuinely can't infer one, ask them to tell you what the next agent should do.
2026-11-08 13:48:28 -08:00
Use the question tool (offer your inferred task as the recommended option) or
2026-07-20 22:07:21 -07:00
a plain question — either is fine.
3. **Do not write the document until the user has confirmed or supplied the next
task.** This gate is mandatory even when your inference feels obviously
correct. The user's answer is the source of truth; your inference is only a
draft of it.
If the user passed a focus area as an argument, treat it as a strong signal for
the next task (and shape the whole document around it), but still confirm.
## Where to write it
2026-10-17 12:35:29 -07:00
No question to ask: every handoff lives in `~/.plan2code/handoffs/` , outside every repo. From the project root, let the console name the file:
2026-07-20 22:07:21 -07:00
```
2026-10-17 12:35:29 -07:00
node "<D>/console.mjs" handoff new --workflow handoff --skill plan2code-handoff --spec specs/<feature> --title "<short title>"
2026-07-20 22:07:21 -07:00
```
2026-10-17 12:35:29 -07:00
`<D>` is `references/web-console/` beside this SKILL.md, as in Interface. Pass `--spec` only when the work was inside a spec; the title is a few words naming the work. It prints one JSON object: write the document to exactly its `path` , and tell the person that path. Exit 3 means it could not write there: say so and stop.
2026-07-20 22:07:21 -07:00
2026-10-17 12:35:29 -07:00
The dashboard lists the handoff for this checkout until it is picked up, and old ones go after 30 days.
2026-07-20 22:07:21 -07:00
2026-08-08 12:39:13 -07:00
## If this touched a plan2code spec
2026-11-08 13:48:28 -08:00
`specs/` is gitignored — file search and text search silently skip it. If the
2026-08-08 12:39:13 -07:00
conversation worked inside `specs/<feature>/` , confirm the exact state before
2026-11-05 11:39:04 -08:00
writing with `node "<S>/specs.mjs" status specs/<feature>` (`<S>` is `scripts/` beside this SKILL.md: `~/.agents/skills/plan2code-handoff/scripts/` globally), which reads the disk:
2026-08-08 12:39:13 -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
- Which `phase-X.md` is in progress, and which of its tasks are still open
(each phase's `tasks` and `openTasks` : checkboxes are ground truth, not the
overview's Phase Checklist; a disagreement shows up in `checks` ).
2026-08-08 12:39:13 -07:00
- Cite that file and its checkbox state directly in **Current state** and
**Key files & pointers** , instead of relying on conversation memory alone.
- Let **Suggested skills** name the specific next pipeline command
2026-09-28 19:37:41 -07:00
(`/plan2code-3-implement --web` to keep implementing the phase,
`/plan2code-4-finalize --web` once all phases are checked) — but only as a
2026-08-08 12:39:13 -07:00
suggestion; the confirmed **Next task** above still governs what the reader
does first.
No `specs/` activity this session? Skip this section entirely.
2026-07-20 22:07:21 -07:00
## What to include
Keep it tight and high-signal. Prefer pointers over prose: this repo already
2026-11-02 13:22:59 -08:00
records a lot (plan specs, the loop's reports, git history, diffs), so
2026-07-20 22:07:21 -07:00
**reference those by path or URL instead of copying them in** . The reader can
open a file; they can't open your memory.
Use this structure:
```markdown
# Handoff — <short title of the work>
<!-- written <timestamp> -->
## Next task
<the confirmed next task — concrete and actionable, e.g.
"Implement Step 3 of specs/<name>.md: wire the aggregator into cli.ts, then
run `npm run build` in plan2code-metrics/ and fix the two failing tests.">
## Goal / why
<1– 3 sentences: what the user is ultimately trying to achieve, so the reader
can make good judgment calls the instructions don't cover.>
## Current state
<Where things stand right now. What's done, what's in progress, what's broken.
Name the branch. Point at the plan/spec file(s) by path rather than restating
them. Note anything half-applied or left uncommitted.>
## Key files & pointers
<Bulleted paths the reader will need, each with a one-line "why". Include plan
2026-11-02 13:22:59 -08:00
specs, the files you were editing, relevant logs (e.g. `specs/<feature>/LOOP-SUMMARY-<date>.md` , `~/.plan2code/console/loop-reports.json` ),
2026-07-20 22:07:21 -07:00
and any PR/issue URLs.>
## Gotchas & decisions
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
<Non-obvious things learned this session: a constraint (e.g. the 20,000-char limit
2026-07-20 22:07:21 -07:00
on src/plan2code-*.md), a decision made and why, a dead end already ruled out,
a command that must be run a specific way. Save the reader from re-discovering
these the hard way.>
## Suggested skills
2026-09-28 19:37:41 -07:00
<Which skills the next agent should use, and when — e.g. /plan2code-3-implement --web
to continue a phase, /plan2code-review before finishing, /plan2code-4-finalize --web
2026-08-08 12:39:13 -07:00
to wrap up. Skip if none apply.>
2026-07-20 22:07:21 -07:00
## Verification
<How the reader confirms their work: exact test/build commands, what "done"
looks like.>
```
Adapt the sections to the work — drop any that would be empty rather than
padding them. **Next task** is the only section that is never optional.
## Strip sensitive data
Before writing, remove credentials, API tokens, passwords, and personal
identifiers. If a secret is load-bearing for the next step, reference *where* it
lives (env var name, secret manager entry) rather than its value.
## After writing
Tell the user the path you wrote to and give a one-line summary of the confirmed
next task, so they know what the incoming agent will start on. Mention that a
fresh session can be pointed at the file to resume the work.