Skip to content
Agentmart
Submit a tool

openplanr-unified

Route OpenPlanr planning and complete pipeline workflows across Claude Code, Codex, and Cursor.

Skill by openplanr

IndexedMIT
Write a review

Chalk Labs

Need help deploying openplanr-unified?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/openplanr-openplanr-unified

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Route OpenPlanr planning and complete pipeline workflows across Claude Code, Codex, and Cursor.

Use cases: data, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/openplanr-unified

What's inside

Skill name
openplanr-unified
Description
Route OpenPlanr planning and complete pipeline workflows across Claude Code, Codex, and Cursor.
License
MIT
Instructions
73 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# OpenPlanr unified workflow

OpenPlanr and planr-pipeline are separate products with an intentional planning overlap:

- OpenPlanr is the dedicated planning and project-management CLI. Use it for
  ongoing epics, features, stories, tasks, specs, sprints, backlog, reports,
  integrations, and artifact lifecycle.
- planr-pipeline is the complete PO → Design → Review → DEV → QA → delivery
  workflow. Its PO phase performs feature-local planning directly connected to delivery.
- Both read Protocol v1.0 artifacts. Runtime locks, adapter manifests,
  compatibility manifests, and provenance are additive v1.1 contracts.
- `planr operate` is the evidence-to-decision control plane for recurring
  operating cycles. It proposes and routes reviewed work but never crosses the
  PLAN review gate or invokes SHIP.

## Routing

Use OpenPlanr commands for portfolio/project planning. Use `planr pipeline ...`
for a feature moving through delivery. Do not run both decomposers over an already
populated spec unless the user explicitly asks to reconcile the results.

Before first use run:

```bash
curl -fsSL https://openplanr.dev/install.sh | sh
cd <project>
planr setup
planr doctor
planr init
```

The installer installs only the CLI. Guided setup detects coding agents and asks
which runtimes and scopes to configure; user scope is the safe default. No
global install: `npx openplanr@latest setup`. Planning-only:
`planr setup --minimal`.

For pipeline work, use the dedicated workflow skills or the router:

```bash
planr pipeline prepare-plan <feature> --json
planr pipeline complete-plan <feature> --runtime <active-runtime> --json
planr pipeline design-engine <action> <feature>
# review generated artifacts
planr pipeline prepare-ship <feature> --json
planr pipeline finalize-ship <feature> --runtime <active-runtime> --json
```

PLAN and SHIP are always separate user invocations. Never infer SHIP approval from
PLAN completion. Honor runtime selection precedence, task dependencies, Preserve
paths, the three-correction limit, and frontend/backend ownership boundaries.

For a recurring operating cycle, use the dedicated `planr-operate` skill or the
public `planr operate` surface. Preview provider use and writes first, keep
finding acceptance separate from route application, and follow only the
machine-readable questionnaire, typed action, or recovery command returned by
the CLI. Present CLI-owned questions through the active runtime, submit typed
answers through the returned session, and stop separately before every
non-read-only action. Never infer answers, append `--yes`, execute legacy prose
next steps, trial-edit source configuration, or edit `.planr/operate` state
directly.

For universal HTML review, use `planr artifact <file>`. Sharing is explicit:
`planr artifact share <file>` creates a stable AES-GCM encrypted live room by
default, with a separate private creator manage URL. Use `--snapshot` for a
fragment-only or encrypted short-link snapshot. Import latest room or snapshot
feedback with `planr artifact import <review-url>`.

Codex uses installed user-scope skills and concise project policy. Cursor uses
portable project rules and Composer handoff. Claude Code retains native slash
commands and tool-enforced agents. Runtime-specific model names must not leak into
portable procedures.

From openplanr/skills, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 29, 2026 (3 months ago)
Last release
Aug 2, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from openplanr

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get openplanr-unified running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying openplanr-unified?

CallGet help
Cite this page

openplanr-unified skill. Agent Mart. https://agentmart.dev/skills/openplanr-openplanr-unified (last updated 2026-10-24)