plannotator — Claude Code skill: what it does, how to install
This skill teaches an agent to use Plannotator for plan, diff, and document review in a local browser. Human feedback returns to the agent in structured form.
Apache-2.0 276 installs ★ 14,187 updated 2026-11-22
npx skills add backnotprop/plannotator --skill plannotator -a claude-codeWhat plannotator does
plannotator is a usage reference for choosing between the plannotator tool and the CLI. It covers reviews of current changes and pull requests, annotations for files, URLs, folders, and local apps, plus a view of the latest assistant message. The same reference includes archived plan decisions and Guided Review export or sharing.
Plan review opens through host hooks when the agent leaves plan mode. Other actions are explicit, including plannotator review, plannotator annotate <file>, plannotator last, and plannotator archive. Each session starts a local web server and waits for a human decision, so a long review needs a long-running or background process rather than a short command timeout.
The skill also covers the Plannotator Inbox for messages and questions that can receive an answer later. It is listed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.
What it helps with
- review a plan before implementation
- inspect the current repository changes
- annotate a file or web page
- open a GitHub PR or GitLab MR review
- browse archived plan decisions
Example prompts for the agent
- Ask Plannotator to review my plan and wait for the decision.
- Run
plannotator reviewto open a review of the current changes. - Annotate
README.mdwithplannotator annotate README.md.
How to install plannotator
1Skills CLI (Vercel)
npx skills add backnotprop/plannotator --skill plannotator -a claude-code2Manually: put the files in place
~/.claude/skills/plannotator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/plannotator/
1Skills CLI (Vercel)
npx skills add backnotprop/plannotator --skill plannotator -a codex2Manually: put the files in place
.agents/skills/plannotator/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add backnotprop/plannotator --skill plannotator -a cursor2Manually: put the files in place
.cursor/skills/plannotator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install backnotprop/plannotator apps/skills/core/plannotator2Manually: put the files in place
.github/skills/plannotator/SKILL.md1Skills CLI (Vercel)
npx skills add backnotprop/plannotator --skill plannotator -a gemini-cli2Platform CLI
gemini skills install https://github.com/backnotprop/plannotator --path apps/skills/core/plannotatorManually: put the files in place
.devin/skills/plannotator/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add backnotprop/plannotator --skill plannotator -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about plannotator
How do I install plannotator in Claude Code?
Run npx skills add backnotprop/plannotator --skill plannotator -a claude-code, then open ~/.claude/skills/plannotator/SKILL.md.
What does plannotator do?
The skill guides an agent through plan, code, and document reviews in a local browser. Feedback and the reviewer’s decision return through stdout or an available Plannotator tool.
Which platforms does plannotator support?
The skill is listed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.
Source text
SKILL.md · Apache-2.0
---
name: plannotator
description: "Reference for using Plannotator (its `plannotator` tool when you have one, otherwise the CLI): plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, exporting or sharing Guided Reviews, and the Plannotator Inbox (messages and questions the person answers later, without blocking you). Invoke when asked to use Plannotator for anything not covered by a more specific plannotator-* skill, and before you leave the person a decision, a question or finished work in the Plannotator Inbox (if another agent started you, report to it instead)."
---
# Plannotator CLI Reference
Plannotator is a local, browser-based review layer for agent workflows: it opens plans, diffs, and documents in an annotation UI, the human marks them up, and the structured feedback comes back to you on stdout. It installs as a single `plannotator` binary plus per-host hooks, so plan review fires automatically when you exit plan mode; every other surface is launched explicitly, with the `plannotator` tool when you have one and with the CLI otherwise. A session runs on a random localhost port (fixed port 19432 in remote mode) and blocks until the reviewer submits feedback, approves, or closes the tab.
This skill is the knowledge layer. The `plannotator-review`, `plannotator-annotate`, and `plannotator-last` skills are thin launchers for the three most common actions; use this reference when you need to pick the right command or flags yourself.
## If you have a `plannotator` tool, always use it
Check your tools before you run any command below. If you have a tool named `plannotator` (it can be listed with a prefix, for example `mcp__plannotator__plannotator` in Claude Code, and can need to be loaded through tool search before you call it), always call it instead of running `plannotator annotate`, `plannotator review`, or `plannotator last`. This includes approvals: call it with `{ "action": "annotate", "target": "<file>", "gate": true }`, not `--gate --json`.
The tool returns at once. End your turn after you call it and wait: the reviewer's decision arrives later as a message. Do not also run the CLI, poll, or reopen the session.
Use the CLI only when you have no such tool, or for what the tool does not do: `archive`, `guide`, `sessions`, review flags other than `--base` and `--gate`, annotate flags other than `--gate` and `--markdown`, and strict gates that a script checks by exit code (`--require-approval`, `--result-file`). If your tool offers `tailscale`, pass `tailscale: true` instead of `--tailscale`.
## Choose the command
| The user wants | Run (CLI, when you have no `plannotator` tool) |
| --- | --- |
| Review a plan you produced | Nothing. Plan review opens automatically on plan exit via hooks. Never run bare `plannotator` yourself. |
| Review and explicitly approve a plan/spec saved as a file | `plannotator annotate <file> --gate --json` |
| Review current code changes | `plannotator review` |
| Review a GitHub PR, GitLab MR or Bitbucket Cloud PR | `plannotator review <PR_URL>` |
| Annotate a markdown, text, config, or HTML file | `plannotator annotate <file>` |
| Annotate a web page | `plannotator annotate <https-url>` |
| Annotate a running local app (dev server) | `plannotator annotate <http://localhost:PORT/>` |
| Pick a file to annotate from a folder | `plannotator annotate <folder/>` |
| Annotate your latest assistant message | `plannotator last` |
| Browse past plan decisions | `plannotator archive` |
| Export or share a Guided Review | `plannotator guide export` / `plannotator guide share` |
| Reopen or list live sessions | `plannotator sessions` |
| Make Plannotator use their own colour theme file | `plannotator theme --help` |
| Ask the person something they can answer later, without blocking | The `plannotator_inbox` tool when you have it, else the Inbox's MCP server (`plannotator inbox mcp`) |
| Have work run on its own on a schedule, reporting in the Inbox (a routine) | `plannotator routine --help` |
## Session model
Every review or annotate command starts a local web server, opens the browser, and blocks until the human decides. That can take minutes, or more than an hour for a large pull request. Launch it with a long (or no) command timeout, or in the background, then read stdout when the process exits. In Claude Code, a background command is stopped after 30 minutes unless you pass `run_in_background` with a longer `timeout` (up to `7200000` ms). Do not kill the process to "finish" a review; a session that ends without a decision reads as no feedback. If a session was stopped by a time limit, run the same command again: annotation drafts are restored.
Stdout is the interface, but its contract is command-specific. For `annotate` and its last-message variants:
- Plaintext (default): empty output on close, `The user approved.` on approve (an approval with a note prints an "Approved with Notes" message instead; treat the notes as guidance, not a change request), otherwise the feedback text. Address returned feedback in the same conversation.
- `--json`: one JSON record with `decision` (`approved`, `dismissed`, or `annotated`) and optional raw `feedback`. An approval may still carry notes in `feedback`; treat those as guidance, not a change request.
- `--hook`: hook-native output for real PostToolUse/Stop hook contexts only. Approve/close emits nothing (hook passes); annotations emit `{"decision":"block","reason":"..."}`. `--hook` implies the gate UI. Never use it for a normal interactive invocation.
`plannotator <command> --help` prints usage without launching anything. Bare `plannotator` is the hook entry point and expects hook JSON on stdin.
## plannotator review
```bash
plannotator review [--git | --gitbutler] [--base <ref>] [--diff-type <type>] [--local | --no-local] [--patch-file <path | ->] [--no-git-remote-check] [--tailscale] [--gate] [--json] [DIRECTORY | PR_URL]
```
Reviews local VCS changes, or a pull request when a URL is given. Default stdout stays plaintext: the existing close message, approval prompt, or feedback.
With `--json`, direct review emits one record: `{ decision: 'approved' | 'annotated' | 'dismissed', message: string }`. `message` is the CLI-rendered text exactly as default plaintext would print it, without the final console newline. It includes customized prompts and non-blocking approval-with-notes framing; a denial suffix is included only when `annotations.length > 0`, including in PR mode, not for zero-annotation platform status.
Classify the outcome only by `decision`, never by `message` text. Notes on an `approved` review are guidance, not a blocking change request. This rendered `message` contract is separate from the raw feedback JSON used by `annotate` and the unchanged `opencode-review` integration. `--hook` is annotate-only.
- VCS is auto-detected (JJ, GitButler, Git, and P4 where supported). `--git` forces plain Git; `--gitbutler` forces GitButler (requires the `but` CLI 0.21.0+). Running from a non-VCS parent folder that contains nested repos produces a combined workspace diff.
- The default diff is "everything a PR would show now": merge-base of the trunk vs the working tree plus untracked files. `--base <ref>` opens the session against a different compare target (branch, `origin/<branch>`, tag, or commit) and `--diff-type <type>` opens it in a different mode (`since-base`, `merge-base`, `branch`, `uncommitted`, `staged`, `unstaged`, `last-commit`, `local-vs-remote`, `all`). Both are **session-only**: the reviewer can change either in the UI, and neither writes the user's saved defaults.
- **Reviewing one layer of a stacked branch? Pass `--base <the branch below yours>`** — `plannotator review --base feature/part-1` shows only what this layer adds, instead of everything since `main`.
- Both flags are git-only: they error on jj, GitButler, Perforce, multi-repo workspace reviews, and PR URLs (a PR's base comes from the pull request). A `--base` ref that does not resolve is a startup error naming near-match branches, never a silently wrong diff.
- `--patch-file <path>` reviews a static caller-supplied unified diff with no repository at all (use `-` to read it from stdin): the session serves the patch as-is with no file-system affordances that need a worktree. It cannot be combined with a PR/MR URL, `--base`, `--diff-type`, `--git`/`--gitbutler`, or `--local`/`--no-local`. Every working-tree affordance is off in that session (staging, hunk-context expansion, open-in-editor, code navigation, diff-type/base switching), and the endpoints behind them answer 400.
- Pass a directory to review another repo or worktree: `plannotator review ../feature-worktree` or `plannotator review ./backend --diff-type last-commit`. Paths resolve relative to the invoking directory; quote paths containing spaces. A directory selects the review workspace, not a file filter. Accepts one directory or PR URL; a directory cannot be combined with `--patch-file`. Invalid targets fail instead of falling back to the current repo.
- PR review (`plannotator review https://github.com/owner/repo/pull/123`, GitLab MR and Bitbucket Cloud PR URLs too) needs an authenticated `gh` or `glab` CLI; Bitbucket Cloud (`https://bitbucket.org/<workspace>/<repo>/pull-requests/<id>`) instead needs an Atlassian API token in `PLANNOTATOR_BITBUCKET_TOKEN` (plus `PLANNOTATOR_BITBUCKET_EMAIL`). `--local` (the default) builds a local checkout of the PR head in the background for full file access; `--no-local` skips it and reviews the platform diff only.
- `--no-git-remote-check` stops the session contacting the git remote at all: no `git ls-remote` for the default branch or the "behind GitHub" baseline check. The compare target then comes from local refs only and the staleness banner never shows, which also takes away its one-click Fetch button (the `/api/fetch-base` endpoint stays available); fetching from a terminal is unaffected. Use it when a remote probe is expensive or intrusive — most sharply when SSH authentication is backed by a hardware token, where each probe is a physical touch prompt. The same opt-out is available session-wide as `PLANNOTATOR_GIT_REMOTE_CHECK=0` or `{ "gitRemoteCheck": false }` in `config.json` in the data directory (`plannotator data-dir` prints it) (the flag beats the env var, which beats the config key). Without it the remote is queried when the review opens, on diff load, on a diff-type/base switch, and on Fetch — never on a timer.
- `--tailscale` publishes the loopback session over the user's tailnet via `tailscale serve` (HTTPS, never public) and prints the URL with a QR code. A publish failure exits nonzero instead of leaving the server hanging. Use it only when the user asks to open the review on another device (a phone, a tablet) or over Tailscale. With a `plannotator` tool that offers it, pass `tailscale: true` (annotate, review, last) instead: "Ask this session" then keeps working on the tailnet for the Tailscale login that owns this computer.
- `--gate` says you are waiting for the reviewer's sign-off before going on (committing, opening the PR): a bare Approve then reaches you too. With a `plannotator` tool, pass `gate: true` on the `review` action instead.
## plannotator annotate
```bash
plannotator annotate <target> [--markdown] [--no-jina] [--app | --static] [--render-html] [--tailscale] [--gate] [--json] [--hook]
```
Opens one document, page, or app in the annotation UI and returns the human's annotations on stdout.
Plain `annotate` is feedback-only: it shows **Close** but no **Approve** button. When the user asks to review, approve, accept, or gate a generated plan/spec/document saved as a file, call the `plannotator` tool with `"gate": true` if you have it; otherwise always add `--gate --json`. Do not tell the user they can approve a plain `annotate` session. If the plan is being handed off through the host agent's native plan flow, do not launch `annotate`; let the plan-exit hook open the approval UI automatically.
Targets:
- Markdown and text files: `.md`, `.mdx`, `.txt`.
- Plain-text config and data files, rendered as text: `.yaml`, `.yml`, `.json`, `.jsonc`, `.json5`, `.toml`, `.ini`, `.cfg`, `.conf`, `.properties`, `.csv`, `.tsv`, `.log`, `.xml`, `.env.example`. A `.env` file opens only on its own, by its explicit path, and nothing of it is kept in Plannotator's data folder; open one only when the person asks for that file. Source-code files belong to `plannotator review`, not annotate.
- Diagram sources, opened in the full diagram viewer (zoom, pan, popout, click a node/edge/cluster to comment): `.mmd`, `.mermaid` (Mermaid) and `.dot`, `.gv` (Graphviz). The file is the whole diagram — no fence needed — and comments carry the part's id plus its real file line.
- AsciiDoc files: `.adoc`, `.asciidoc`.
- HTML files (`.html`, `.htm`): rendered as the raw page by default; `--markdown` converts to markdown instead. `--render-html` is accepted for compatibility; raw rendering is already the default.
- URLs (`https://...`): fetched and converted via Jina Reader by default; `--no-jina` uses plain fetch plus Turndown instead.
- Running local apps: a loopback `http://localhost:PORT/` URL whose probe returns HTML opens in live-app mode (annotate the real running page). `--app` forces live mode and fails loudly when it cannot apply; `--static` forces the classic conversion pipeline. Non-loopback URLs always use the conversion pipeline.
- Folders: `plannotator annotate docs/` opens a file browser over the folder's supported files.
- Several files: `plannotator annotate spec.md mock.html notes.md` opens them as one review, in the order given, with one decision. Every argument must be an existing file named by its path (no prose, URLs or folders among them). With the `plannotator` tool, pass the list as `target`.
Single files are capped at 2MB. Files are read from disk at stable project paths; keep the reviewed source where it lives.
Argument tolerance: extra words are fine (`plannotator annotate look at notes.md please` opens `notes.md`), but two resolvable targets mixed with prose, a URL or a folder is an error naming them, and an unrecognized dashed token disables the tolerance so flag typos fail loudly. When nothing resolves in a plain multi-word invocation, the CLI prints an agent-addressed handoff on stdout and exits 0: read it, work out the concrete target, and re-run with that exact path or URL.
### Strict gates and exit codes
For a machine-checkable approval gate, add `--gate --json` plus one or both strict flags:
```bash
plannotator annotate report.md --gate --json --require-approval --result-file /tmp/decision.json
```
- `--require-approval`: exit code reports the human outcome.
- `--result-file <path>`: the stdout decision JSON is also published atomically to `<path>`. The parent directory must exist and the file must not; results resolve from the invocation cwd.
Exit codes under a strict flag (grep convention):
| Exit | Meaning |
| --- | --- |
| 0 | Approved. The only success. |
| 1 | The reviewer did not approve (annotated or dismissed); the decision record was still published. |
| 2 | The gate itself failed: bad flag combination, startup failure (missing file, unreachable URL, oversized file), or the result file could not be published. Never treat as a reviewer outcome. |
| 128+n | Killed by signal n. |
Without strict flags, startup failures exit 1 and the exit code carries no decision; parse the output instead. Both strict flags require `--gate --json` and reject `--hook`.
## plannotator annotate-last
```bash
plannotator annotate-last [--stdin] [--tailscale] [--gate] [--json] [--hook]
plannotator last
```
Opens the latest rendered assistant message from the current agent session in the annotation UI (`last` is an alias). The session log is discovered per host automatically; `--stdin` reads the content from stdin instead.
Do not print a commentary or status message immediately before running it: the command targets the latest rendered assistant message, so a preamble becomes the thing being annotated.
## plannotator copilot-last
```bash
plannotator copilot-last [--gate] [--json] [--hook]
```
The annotate-last variant for live GitHub Copilot CLI sessions (reads Copilot's session-state events). Normally invoked by the Copilot plugin's /plannotator-last command; use it only inside a Copilot CLI session.
## plannotator archive
```bash
plannotator archive
```
Opens a read-only browser over saved plan decisions (approved/denied badges) from the Plannotator data directory. No feedback comes back; the session ends when the user clicks Done.
## plannotator guide
```bash
plannotator guide list
plannotator guide export --id <savedGuideId> [--out <file.html>]
plannotator guide export --guide <guide.json> --patch <diff.patch> [--out <file.html>]
plannotator guide export --snapshot <snapshot.json> [--out <file.html>]
plannotator guide share --id <savedGuideId> [--public] [--ttl <7d|24h|30m|3600>] [--json]
plannotator guide unshare <id> --token <deleteToken>
plannotator guide import --guide <guide.json> --patch <diff.patch> [--pr <url>]
```
Guided Reviews are AI-generated walkthroughs of a diff, produced inside the code review UI. The CLI works with saved ones:
- `list` shows guides Plannotator has persisted for the current repo.
- `export` writes one portable, self-contained HTML file (the viewer loads from guides.show). `--guide` + `--patch` exports a guide you authored yourself against a unified diff (`--patch -` reads stdin; validation is strict and names any file the guide references that the patch lacks). `--out -` writes to stdout. `--viewer-url` overrides the pinned viewer base.
- `share` uploads the guide and prints a link. Encrypted by default: the key lives only in the URL fragment and the host stores ciphertext. `--public` stores it unencrypted so chat apps can unfurl a preview. `--ttl` sets an expiry; otherwise the link stays until `unshare`. A saved guide records its link, and a second `share --id` refuses rather than orphaning the first link's delete token.
- `unshare <id> --token <t>` removes a link using the delete token printed at share time.
- `import` saves a guide you authored (`--guide` + `--patch`, checked as for `export`, or `--snapshot`) so the next `plannotator review` of this repository lists it under Guides. `--pr <url>` saves it with that PR's repository and labels it with the PR. Prints the new id; it never replaces a saved guide.
## plannotator sessions
```bash
plannotator sessions [--open [N]] [--clean] [--json]
```
Lists active Plannotator server sessions, each with its full target (absolute path, URL, PR URL or reviewed directory) and, for a review a host opened, its `pn-` id. `--open` reopens session N (default 1) in the browser, useful when a tab was closed mid-review. `--clean` drops stale entries. `--json` prints the list as a JSON array on stdout.
## plannotator inbox
```bash
plannotator inbox [--background | --no-open | --open] [--tailscale]
plannotator inbox mcp
plannotator inbox call [--session <id>] <action> [<json> | -]
plannotator inbox status [--json] | stop | restart
```
The Plannotator Inbox is one local window per machine where you leave the person messages, `:::question` blocks they answer with a click, files to annotate and guided reviews. Nothing blocks: you send, then keep working or end your turn.
- Use it for a decision only they can make (a `:::question` block, then go on with work that does not depend on it), long work you finished (one short summary with its pictures in place, `` in the body where you write about each, and the files to look at in `attachments`), or when they ask. One thread per work stream, unless the person says otherwise. A decision you sent to the Inbox stays there: when the person writes in the chat, say there what waits (a short summary and the thread's link), but never also ask it in the chat with a blocking question tool (AskUserQuestion or similar). Ask in the chat only about something new they raised there that needs no pictures or files, or when they ask. Be proactive about Inbox updates and about replying to the person through the Inbox when you think they would want you to. Don't withhold important updates or decisions, and don't batch updates to send later: proactivity is better than procrastination. Use a review (plan review, `annotate`, `review`) when you need a decision on this document or diff before you go on.
- When the person picks between looks (designs, variants, today's screen against a redesign), write about the options inside the question, not above it: each option is a picture choice, `- [ ] A · Label —  what it means`, its own picture inside it and what you would say about it as its description; a choice with nothing to show (both, none yet) stays plain text. When another agent designs the options for you, ask it for, per option: a label, one screenshot, one HTML file that shows only that option, what it means, pros and cons; when it returns a report, send its options as one question as above, not the report.
- A question that proposes a change (words, a screen, code, a setting) shows it: `Where: <what it is and where the person sees it>`, then `Before:` and `After:`, each the whole sentence, paragraph or screenshot it sits in (the card marks the change; `Before: none` when nothing is there). Several places: repeat the three lines per place. A choice that is its own version or change gets its own `After:` (and `Before:`) under it. A new feature or a prototype skips these (send pictures), and so does a choice the person never sees, such as a library. More forms (several places, pictures, a version per choice): `plannotator inbox --help before-after`.
- If you have a `plannotator_inbox` tool, use it; otherwise use the stdio MCP server `plannotator inbox mcp`. When send_message says the person's reply arrives in this session by itself, end your turn instead of waiting; otherwise go on with your work and read the thread later with read_thread.
- For many Inbox calls in a row (a tidy above all), `plannotator inbox call` runs any action from a script and prints its result as JSON; `plannotator inbox --help` says how.
- To put a thread's decisions on its pull request, run `plannotator inbox export-decisions --thread <id> --pr <ref>`: updated in place when run again.
- Run `plannotator inbox --help` once and read it before your first use: it is the full guide (tools and arguments, threads, where replies go, question syntax, replacing questions, connecting other agents).
- Never run `plannotator inbox` just to send: once the person has turned the Inbox on here (their own `plannotator inbox`), calls start a stopped Inbox in the background, and bare `plannotator inbox` opens the window for the person. Until they have, a call answers that the Inbox is off: ask them in the chat instead. `--tailscale` is the person's choice; never add it. `plannotator inbox status` only reads; never run `plannotator inbox stop` or `restart` unless the person asks.
- When the person asks where their Inbox is, or to open it (a closed tab), run `plannotator inbox --open`: it opens the window in their browser (starting the Inbox in the background if needed), prints its address on stdout and returns at once. The first time, it also turns the Inbox on and connects the agents it finds, within half a minute. Tell them the address.
## plannotator t3
```bash
plannotator t3 login --url <T3 MCP URL>
plannotator t3 logout --url <T3 MCP URL>
```
If the person uses T3 Code, set it up once so their Inbox replies reach Claude threads in T3 as new turns: run `plannotator t3 --help` and follow its two steps. The person approves T3's sign-in page themselves.
## plannotator card
```bash
plannotator card <create|move|say|link|ship|drop|list|initiative_delete> ...
```
Only while the person has turned the Inbox's Board on (Settings → Capabilities); it is off by default, and then every call answers `board_off` and writes nothing, so use it only when your inbox tool lists `card` or the person asks. The Board holds one card per piece of work that outlasts a reply, in the column of where the work stands (todo, in_progress, in_review, done; backlog for what nobody asked for yet). Use the `card` action of a `plannotator_inbox` tool when you have one; this CLI is the same call from a shell. `plannotator card --help` gives the arguments, and `plannotator inbox --help` its card section while the Board is on. A card the person put in backlog is theirs to move. A title is 2–5 words naming the work ("Pi update fix"), never a sentence; where it stands goes in `say`. Move a card to in_review yourself when you hand your part over, with `you` and the Inbox thread where the person makes the call (`thread_id`), so "You: …" opens it. Ship a card when you see its PR merge (the Board may also move it to done once every PR linked with `--pr` merged). `--initiative <name>` (the card action's `initiative`) puts a card in an initiative. Not all cards need an initiative: put a card in one only when it is part of an extensive effort that spans several cards or PRs, and reuse an initiative that fits (list shows them) instead of making a near-duplicate. Use good judgement; don't overthink it.
## Other subcommands
```bash
plannotator setup-goal <interview|facts> <bundle.json | -> [--json]
plannotator data-dir
plannotator feedback --stdin [--category <bug|idea|other>] [--contact '<text>'] <<'PLANNOTATOR_FEEDBACK_END'
<the message, exactly as the person approved it>
PLANNOTATOR_FEEDBACK_END
plannotator theme add <file> | use <id> [--light | --dark] | list [--json] | remove <id>
plannotator update [--check]
plannotator uninstall [--purge] [--yes] [--dry-run]
plannotator improve-context
```
- `setup-goal` opens the interview or facts-acceptance UI for /goal workflows; it is driven by the `plannotator-setup-goal` skill and takes a bundle JSON (`-` reads stdin). Do not hand-build bundles.
- `data-dir` prints the absolute path of Plannotator's data directory (plans, history, drafts, `config.json`, `hooks/`) and creates nothing. Run it whenever you need a file in that folder, and use the path it prints. Never write a path such as `~/.plannotator/...` from memory: an install can keep its data under `$XDG_DATA_HOME/plannotator`, and a new `~/.plannotator` can hide that data from Plannotator. If it prints nothing or fails (an older Plannotator, before 0.28.41), use `$PLANNOTATOR_DATA_DIR` when it is set; otherwise the home folder's `.plannotator` if it exists, else `$XDG_DATA_HOME/plannotator` when `XDG_DATA_HOME` is set, else the home folder's `.plannotator`.
- `feedback` sends the person's feedback about Plannotator to its maintainers and prints `Sent` (the message, the category and contact if given, the version, the OS name and that it came from the CLI; nothing else). Only when the person asks you to send feedback: show them the exact text first and run it only after they say yes. Pass the message on stdin with a quoted heredoc (`<<'PLANNOTATOR_FEEDBACK_END'`, quotes included; pick another end word if a line of the message is exactly that), never inside double quotes in any shell, where `$VAR`, backticks and `$(...)` are expanded and change the approved text. Fill in or leave out the bracketed options (`--category idea`), and put a contact in single quotes. In PowerShell, set `$OutputEncoding = [Text.UTF8Encoding]::new($false)` and pipe a single-quoted here-string (`@'` … `'@ | plannotator feedback --stdin`). Exit 0 sent, 1 not sent, 2 usage.
- `plannotator theme` gives Plannotator the person's own colour theme (a VS Code theme, a base16 scheme, or Plannotator's own format): run `plannotator theme --help` for the commands and the format.
- `update` installs the newest release now (the install script, with the choices from the last install); `--check` only reports whether one exists. Run it only when the person asks you to update Plannotator: it replaces the binary. Exit 0 up to date or updated, 1 failed, 2 usage, 130 interrupted.
- `uninstall` removes Plannotator-installed components (`--purge` also deletes local data; `--yes` is required without a TTY; `--dry-run` previews).
- `improve-context` and `install-runtime` are internal integration commands (hook plumbing and managed runtime install). Never run `improve-context` directly; `plannotator install-runtime agent-terminal` exists for reinstalling the optional annotate-terminal runtime and is normally run by the installer.
- Additional host-internal subcommands (the `opencode-*` family, `copilot-plan` and `dsh-plan`) are invoked by their plugins, not by you.
## Environment variables that change behavior
| Variable | Use |
| --- | --- |
| `PLANNOTATOR_REMOTE=1` | Force remote mode (fixed port 19432, wide bind) for SSH/devcontainer sessions; `0` forces local. Unset means SSH auto-detection. |
| `PLANNOTATOR_PORT` | Fix the port instead of a random one. |
| `PLANNOTATOR_ORIGIN` | Override agent-origin detection (`claude-code`, `codex`, `opencode`, `pi`, `oh-my-pi`, `amp`, `droid`, `copilot-cli`, `gemini-cli`, `kiro-cli`, `mistral-vibe`, `qwen-code`, `dsh`). Set it when launching Plannotator from a wrapper the detection cannot see through. |
| `PLANNOTATOR_AI=disabled` | Disable Ask AI and agent-launched review surfaces in the UI. |
| `PLANNOTATOR_SHARE=disabled` | Disable URL sharing, including guide share links. |
| `PLANNOTATOR_DATA_DIR` | Move the data directory: plans, history, drafts, config. Unset, the default is `~/.plannotator` or `$XDG_DATA_HOME/plannotator`; `plannotator data-dir` prints which one this install uses. |
| `PLANNOTATOR_BROWSER` | Open sessions in a specific browser; `none` opens no browser at all (the session URL is always printed on stderr). |
| `PLANNOTATOR_UPDATE_CHECK=0` | No automatic check for a newer relea...
© backnotprop · Apache-2.0 · backnotprop/plannotator