Agent skill

Plannotator Annotate

by backnotprop in backnotprop/plannotator

Opens Plannotator's annotation UI on a markdown file, HTML file, URL or folder, then reads the decision and feedback you send back and acts on it.

Apache-2.0Auto-check passedAgent Workflows

Install Plannotator Annotate

skills CLI
$ npx skills add backnotprop/plannotator --skill plannotator-annotate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install backnotprop/plannotator plannotator-annotate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/backnotprop/plannotator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/skills/claude/plannotator-annotate .claude/skills/plannotator-annotate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
plannotator-annotate
GitHub stars
9.2k
Token cost
~413 tokens
SKILL.md length
216 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Opens Plannotator's annotation UI on a markdown file, HTML file, URL or folder, then reads the decision and feedback you send back and acts on it.

  • Works in 4 steps: The exact text The user approved., an… → Empty, OR a JSON object with "decision":… → Plaintext annotation feedback, OR a JSON… → …
  • Reviewing a markdown plan or document visually before the agent acts on it
  • SKILL.md covers Markdown annotations and Your task
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill runs the plannotator annotate command on whatever file, URL or folder you name, which opens a visual annotation page. When you finish, the agent reads what came back and branches on four cases. An approval, with or without notes, means no new work starts, and any notes are kept as non-blocking guidance for later. A dismissed or empty result means the session was closed without changes, so the agent acknowledges it in one sentence and stops.

Plain-text feedback, or an annotated result with a feedback field, is treated as specific comments from you on the file, and the agent addresses them. If the arguments could not be resolved to a file, URL or folder, the agent works out the target from your description, runs the command again with a concrete path and handles that output the same way. The only tool it may call is the plannotator command line.

When your agent uses it

  • Reviewing a markdown plan or document visually before the agent acts on it
  • Annotating an HTML page, URL or whole folder and sending comments back to the agent
  • Approving a plan with notes that should guide later work

Example prompts

  • “Open plan.md in Plannotator so I can annotate it.”
  • “Annotate the docs folder with Plannotator and address my comments.”
  • “Annotate the design spec at docs/spec.html and fix whatever I flag.”

Requirements

  • The plannotator command-line tool
  • Pre-approved tools (allowed-tools): Bash(plannotator:*)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. The exact text The user approved., an "Approved with Notes" message, OR a JSON object with "decision": "approved". The user approved the…
  2. Empty, OR a JSON object with "decision": "dismissed". The user closed the session without requesting changes. Acknowledge with a single…
  3. Plaintext annotation feedback, OR a JSON object with "decision": "annotated" and a "feedback" field. Address the feedback. The user has…
  4. A message that the arguments could not be resolved to a file, URL, or folder. The user described what to annotate in natural language…

What it can do on your machine

Read from SKILL.md and the folder at commit 1d9fe3f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(plannotator:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plannotator Annotate loads about 413 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 216 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~413

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from backnotprop/plannotator at commit 1d9fe3f, republished under its Apache-2.0 licence (© backnotprop). 216 words, ~413 tokens.

Download SKILL.mdSave it as .claude/skills/plannotator-annotate/SKILL.md (or your agent's skills folder).
name
plannotator-annotate
description
Open Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.
allowed-tools
Bash(plannotator:*)
disable-model-invocation
true

Plannotator Annotate

Markdown annotations

!plannotator annotate $ARGUMENTS

Your task

The output above will be one of:

  1. The exact text The user approved., an "Approved with Notes" message, OR a JSON object with "decision": "approved". The user approved the markdown file(s). If it is the Approved with Notes message, or that object also carries a "feedback" field, the user approved with notes: read them and carry them into subsequent work — they are non-blocking guidance, not a request to revise the file. Otherwise acknowledge with a single sentence ("Approved.") and stop. Either way, do not begin any work.
  2. Empty, OR a JSON object with "decision": "dismissed". The user closed the session without requesting changes. Acknowledge with a single sentence ("Annotation session closed.") and stop. Do not begin any work.
  3. Plaintext annotation feedback, OR a JSON object with "decision": "annotated" and a "feedback" field. Address the feedback. The user has reviewed the markdown file(s) and provided specific annotations and comments.
  4. A message that the arguments could not be resolved to a file, URL, or folder. The user described what to annotate in natural language: work out which file, URL, or folder they mean, run plannotator annotate <path-or-url> yourself with that concrete target (keeping any flags the message echoes), then handle its output per cases 1-3.

© backnotprop, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in apps/skills/claude/plannotator-annotate of backnotprop/plannotator.

Open the folder on GitHubat commit 1d9fe3f

Compare with similar skills

Plannotator Annotate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Plannotator Annotate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plannotator Annotate this skillbacknotprop/plannotator9.2k—~413Automated safety check: PassApache-2.0
Planningchampionswimmer/pi-context-prune245—~779Automated safety check: PassNone
Grill With UIjasonku09/grill-with-ui246—~7.9kAutomated safety check: PassMIT
Gstack Autoplan Review Pipelinegarrytan/gstack136k—~16kAutomated safety check: NotesMIT
Plan and Implement Workflowmp-web3/claude-starter-kit109—~913Automated safety check: NotesMIT
Implement Incrementalrsmdt/the-startup536—~1.7kAutomated safety check: PassMIT

Similar skills

  • Planning

    championswimmer/pi-context-prune

    Create and execute phased implementation plans stored in .agents/plans using numbered markdown files with YAML front matter and checklist steps.

    245 GitHub stars~779 tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Grill With UI

    jasonku09/grill-with-ui

    Moves a design-grilling interview from the terminal to a local web page, where each question, recommendation and discussion thread can be handled in any order.

    246 GitHub stars~7.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Runs the gstack CEO, design, engineering and DX review skills on a plan file in sequence and makes borderline taste decisions automatically using six stated decision principles.

    136k GitHub stars~16k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Plan and Implement Workflow

    mp-web3/claude-starter-kit

    Runs new features, scripts and structural changes through explore, design, approval, implementation and verification phases, with a tool search and an explicit plan sign-off.

    109 GitHub stars~913 tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check: notes
  • Implement Incremental

    rsmdt/the-startup

    Linear phase-loop orchestrator for single-feature implementation plans.

    536 GitHub stars~1.7k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Specify Incremental

    rsmdt/the-startup

    Decompose a single-feature specification into a linear, phase-by-phase implementation plan.

    536 GitHub stars~1.4k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

More from backnotprop/plannotator

All 13 skills in this repo
  • Plannotator Visual Explainer

    backnotprop/plannotator

    Builds self-contained HTML explainers for plans, pull requests and technical concepts in Plannotator's theme, then opens them in its annotation view.

    9.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Plannotator Release Preparation

    backnotprop/plannotator

    Drafts Plannotator release notes with full contributor credit, bumps versions in dependency order, builds, and starts the tag-driven release pipeline, in four reviewed phases.

    9.2k GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Plannotator Planning Analysis

    backnotprop/plannotator

    Mines a Plannotator archive of denied plans for feedback patterns and prompt improvements, then writes an HTML dashboard report, with a Claude Code fallback.

    9.2k GitHub stars~6.7k tokensUpdated today
    Auto-check passed
  • Renovate Actions PR Review

    backnotprop/plannotator

    Reviews Renovate pull requests that bump GitHub Actions by checking pinned SHAs against upstream tags, scanning changelogs and confirming workflows stay compatible.

    9.2k GitHub stars~640 tokensUpdated today
    Auto-check passed
  • Plannotator Goal Setup

    backnotprop/plannotator

    Guides the agent from a vague objective to a written goal package under goals/, using a confirmed restatement, a browser interview, a fact sheet and a codebase pass.

    9.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Dependency Update Audit

    backnotprop/plannotator

    Audits outdated npm and Bun packages for supply chain integrity before bumping them, deferring risky ones and logging every decision.

    9.2k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Questions about Plannotator Annotate

What does Plannotator Annotate do?

Opens Plannotator's annotation UI on a markdown file, HTML file, URL or folder, then reads the decision and feedback you send back and acts on it. This skill runs the plannotator annotate command on whatever file, URL or folder you name, which opens a visual annotation page. When you finish, the agent reads what came back and branches on four cases.

When should I use Plannotator Annotate?

Plannotator Annotate fits situations like: reviewing a markdown plan or document visually before the agent acts on it; annotating an HTML page, URL or whole folder and sending comments back to the agent; approving a plan with notes that should guide later work.

How do I install Plannotator Annotate in Claude Code?

Run `npx skills add backnotprop/plannotator --skill plannotator-annotate -a claude-code`. Or copy the skill folder (apps/skills/claude/plannotator-annotate in backnotprop/plannotator) into .claude/skills/plannotator-annotate in your project. Claude Code loads it when a task matches its description.

How do I install Plannotator Annotate in Codex?

Run `npx skills add backnotprop/plannotator --skill plannotator-annotate -a codex`. Or copy the skill folder (apps/skills/claude/plannotator-annotate in backnotprop/plannotator) into .agents/skills/plannotator-annotate in your project. Codex loads it when a task matches its description.

Can I use Plannotator Annotate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add backnotprop/plannotator --skill plannotator-annotate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plannotator-annotate, .gemini/skills/plannotator-annotate, .github/skills/plannotator-annotate and .opencode/skills/plannotator-annotate in your project.

What does Plannotator Annotate need to run?

SKILL.md names no scripts, command-line tools or credentials: Plannotator Annotate is instructions for the agent only. Our summary lists: The plannotator command-line tool. Its frontmatter pre-approves these tools: Bash(plannotator:*).

Does Plannotator Annotate access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plannotator Annotate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Plannotator Annotate use?

Plannotator Annotate is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plannotator Annotate use?

About 413 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Plannotator Annotate?

Skills that share tags, products or a category with Plannotator Annotate: Planning (championswimmer/pi-context-prune, 245 stars), Grill With UI (jasonku09/grill-with-ui, 246 stars), Gstack Autoplan Review Pipeline (garrytan/gstack, 136k stars) and Plan and Implement Workflow (mp-web3/claude-starter-kit, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plannotator Annotate?

backnotprop (a GitHub user) maintains it in backnotprop/plannotator, which has 9,185 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 6, 2026.

Source: backnotprop/plannotator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.