plannotator
718 posts
plannotator
@plannotator
Annotate agent plans, html, and review code visually. Iterate with your agent. Share with your team • https://t.co/3Gg5SohuqE
Katılım Ocak 2026
48 Takip Edilen2K Takipçiler
@KolbeYang @linear Hey yeah, we were actually kind of the first to do that...
/plannotator-review [empty for local | PR-link]
x.com/plannotator/st…
plannotator@plannotator
Plannotator v0.21.3 is out Ask AI (plan, review & annotate) - Codex now runs on more reliable app-server Code Review - File-scoped comments + unified comment UX - useful if you create your own guided reviews, ty for the idea @Nartc1410 - Per-file Ask AI chats now open by default - Fixed dead sidebar clicks after switching PRs VS Code extension - Clipboard + keyboard fixes CLI - Subcommand --help fixes
English
Plannotator 0.22.0 is out.
Code Review (is not dead yet):
- Guided reviews give you a list of changes with semantic overviews, ordered by importance & where you need to spend your time reviewing. Inspired by @linear, this works for local and PR changes . You don't need the best models or high reasoning levels to use this!
- Pi and Copilot are added as agent review providers.
- A new default `git status` view is added.
- A new `commits` view is added to easily navigate all commits and view their descriptions+changes.
English
How come no one but @plannotator figure out that it’s important to let users annotate messages and be able to reference them into a new prompt? Like none of the GUI apps supports it. I’d love if you guys from @opencode add this feature in your desktop app.
English
@tadejstanic I will review, you might also like not using plan mode, just chatting with the agent/plan
create documents and then either:
`/plannotator-annotate plan.md`
or
`/plannotator-last` to annotate messages
English
@plannotator how can i get rid of that todo list after a plane is approved? im using pi and have a different flow of plan execution via subagents and that todo list is just messing up my terminal for no reason
English
English
Would be cool to have an annotate feature too. Currently we can select some text and quote a reply for that but I want to select multiple parts of response and annotate each one individually. This is really helpful when planning features. You should check out @plannotator and borrow some ideas from them.
English
Okay this is really cool. Codex app has a new feature that is really useful.
Highlight any text, and you'll notice a new popup.
"More Details" uses GPT 5.5 Instant to explain in more detail about the highlighted portion of your text, allowing you to understand the reasoning/concept/statement/etc in greater detail.
What's interesting about this versus a side chat is that it's instantaneous, and still retains context from the thread.
With /side chat, you'd have to type out a prompt "what are the details on this?"
With "more details" the prompt is implicit and the response is instantenous
Very nice feature, as I'm always making side chats/branches to expand/learn/understand agent outputs better.
English
difit github.com/yoshiko-pg/dif…
vs
crit crit.md
vs
hunk github.com/modem-dev/hunk
自分の中でこの3つのツールが似たようなIssueを解いていて、ずっとCritを愛用していたけど、CLIでこれをやってくるHunkすごーいってなってる
日本語
plannotator@plannotator
Plannotator 0.22.0 is out. Code Review (is not dead yet): - Guided reviews give you a list of changes with semantic overviews, ordered by importance & where you need to spend your time reviewing. Inspired by @linear, this works for local and PR changes . You don't need the best models or high reasoning levels to use this! - Pi and Copilot are added as agent review providers. - A new default `git status` view is added. - A new `commits` view is added to easily navigate all commits and view their descriptions+changes.
English
@plannotator Awesome. One question, do you support or have plans to have an agent guided review? IE rather than viewing the files alphabetically a la GitHub, we can pass the review over to an agent to reorganize the files and help understand the flow. Linear offers something similar...
English
Wait Plannotator has PR reviews? #code-review" target="_blank" rel="nofollow noopener">github.com/backnotprop/pl…
Was thinking of vibecoding a personal version (💀) of this but I'm sold on integrating Plannotator into my workflow now
plannotator@plannotator
Plannotator 0.21.4 is out We are shipping from AIE World's Fair! Code Review (is not dead yet): - PRs: Refined overview dashboard - PRs: Annotate PR descriptions and comments - PRs: Search and filter comments by user, hide bots - PRs: Live sync with GitHub - Agent Instructions: pass agent instructions to your own agents/review skills and have it send annotations to the review app (demo in 🧵) - Refined feedback instructions so agents verify and review your annotations against the code. Plan/Annotate: - latex math support (demo in 🧵)
English
appreciate it... today you can generate what you want on the fly via html with most agents & we don't wan't to get opinionated over creative thinking/generative process & have decided not to platform a route like that.
but you can always annotate the html with us or share it via git backed artifacts with tot.page
English
@plannotator Dope. What do you think about a plannotator feature that takes @dillon_mulroy style tech spec and gives me a variant style selector UI where I can plan and get 2+ interface/architectural options to visualize and pick. Wouldn’t doubt if this is already supported though lol
English
Plannotator 0.21.4 is out
We are shipping from AIE World's Fair!
Code Review (is not dead yet):
- PRs: Refined overview dashboard
- PRs: Annotate PR descriptions and comments
- PRs: Search and filter comments by user, hide bots
- PRs: Live sync with GitHub
- Agent Instructions: pass agent instructions to your own agents/review skills and have it send annotations to the review app (demo in 🧵)
- Refined feedback instructions so agents verify and review your annotations against the code.
Plan/Annotate:
- latex math support (demo in 🧵)
English
plannotator retweetledi
/plannotator-last
Annotating agent messages is still a productive step for me when working on understanding/alignment or shaping something new with an agent.
I'm surprised most desktop harnesses still haven't nailed this UX. It's low friction and requires 0-process adoption (in terms of agents generating specs and other artifacts you otherwise treat as formal instruction).
English
@plannotator i wonder if we are annotating a markdown file we should also be able to edit it inline on the browser
English
@pyrons_ @Steve8708 We will continue to enhance diff review and simple guided experience. But no intent to ship platformed skills like builder or notion.
English
How I've changed the way I do code reviews by using the /visual-recap skill:
English
@ericclemmons that does it
I know you want the persistence! That's going to come this summer when MCP updates.
Otherwise the push/pull ergonomics with agents is janky right now. I tried all sorts of methods and I don't wanna push something that I thought was awkward for myself to others.
English
@plannotator Oops – x hid answer to #1 behind a "More..." link
/plannotator-annotate checklist.md
English
Late night random tip. An og use case: keep a checklist open while an agent works. Plannotator listens for live updates so you can monitor progress in real time.
No html tokens spent. The agent updates the markdown naturally. It looks nice in the UI. You stay in the loop when you need to.
/plannotator-annotate checklist.md
English
there is a code tour feature but it's not the best (there is a review tab where you can kick off agent reviews or your own skill reviews and they show in the diffs, or launch a code tour).
But we can whip a better guided tour out - the key caveat is that it must be user invoked, since it uses your models/providers (this all just runs locally), but maybe can have a setting to always run.
English