
plannotator-tui
Open a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
- Installs
- 303
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/plannotator/herdr-annotate --skill plannotator-tui- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads plannotator-tui automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
plannotator-tui: hand a document to the human for review
Only when HERDR_ENV=1 (you are running inside Herdr). Otherwise tell the human where the
file is and ask them to review it.
-
Write the document to a file. Do not paste it into chat as well.
-
Open it for review, from your own pane:
plannotator-tui herdr open docs/plans/auth.mdplannotator-tui opens beside you (or wherever the user configured it), already knowing that feedback comes back to this pane.
-
End your turn. Do not wait, poll, or read the pane. The review arrives as the next user message, as numbered feedback:
## 1. (line 12) Feedback on: "Rotate the token on every…" > Rotation on every privilege change will log people out…Address every item, then continue.
When you list files you want the human to open, you may print them as file:// hyperlinks
(OSC 8):
printf '\e]8;;file://%s\e\\%s\e]8;;\e\\\n' "$PWD/docs/plans/auth.md" "docs/plans/auth.md"
Do not promise that Ctrl-click opens them in plannotator-tui. That happens only when the human
installed the opt-in annotate-links add-on. To ask for a review, use step 2.
If plannotator-tui is not on PATH, the raw Herdr command is:
herdr plugin pane open --plugin annotate --entrypoint doc --placement split \
--direction right --target-pane "$HERDR_PANE_ID" --focus --cwd "$PWD" \
--env PLANNOTATOR_TUI_FILE="$PWD/docs/plans/auth.md" --env PLANNOTATOR_TUI_DELIVER_TO="$HERDR_PANE_ID"
FAQ
What does the plannotator-tui skill do?
Open a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
How do I install plannotator-tui?
Run npx skills add https://github.com/plannotator/herdr-annotate --skill plannotator-tui in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/plannotator-tui/ (personal) or .claude/skills/plannotator-tui/ (project).
Which AI agents can use plannotator-tui?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is plannotator-tui safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains plannotator-tui?
It is published by plannotator in plannotator/herdr-annotate. It has 303 recorded installs.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.