plane
Skill65 starsChanged 7 months agoMITView on GitHub
Plane.so project management interface via direct API scripts. Use when user says 'plane', 'check plane', 'update plane', 'GP-42', 'plane status', 'sync to plane', 'look up task', or any Plane-related project management action.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- clarityreg/plane-claude-skilltheir own version, first seen Jan 24, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- clarityreg/plane-claude-skill★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- buildSkill
- debugSkill
- financial-advisorSkill
- generate-image-openaiSkill
- good-morningSkill
- pdfSkill
- reply-xSkill
- researchSkill
- search-historySkill
- send-emailSkill
- simplify-julesSkill
- skill-creatorSkill
- stop-slopSkill
- thinkSkill
- watch-contactsSkill
- wrap-upSkill
- writeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
All Plane operations use Python scripts calling the REST API via curl.
- Distinctive: line 14
No MCP server dependency — works in interactive and batch contexts.
- Very specific: line 29
All scripts require PLANE_API_KEY.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plane.so Skill
Comprehensive interface to the Plane Cloud workspace ([your-workspace-slug], project Grand Plan).
Architecture: Direct API Scripts
All Plane operations use Python scripts calling the REST API via curl. No MCP server dependency — works in interactive and batch contexts.
| Operation | Script |
| List items, cycles, modules | plane_list.py items, plane_list.py cycles, plane_list.py modules |
| List items in a module | plane_list.py module-items "Pending Review" |
| Filter by state/due date | plane_list.py items --state todo,in_progress --due-within 7 |
| Create item (+ add to module) | plane_create.py "Title" --module "Pending Review" |
| Get item by identifier (GP-42) | plane_lookup.py GP-42 |
| Search items by keyword | plane_search.py "keyword" |
| Pull Plane status → markdown | plane_pull.py [--apply] |
| Compare local vs Plane | plane_compare.py [--diff-only] [--module slug] |
Gap Script Usage
All scripts require PLANE_API_KEY. On Mac, inject at call time:
# Lookup by identifier
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_lookup.py GP-42
# Search
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_search.py "authentication" --state todo
# Push: markdown -> Plane (dry-run by default, --apply for live)
python3 .claude/skills/plane/scripts/plane_sync.py # dry-run
python3 .claude/skills/plane/scripts/plane_sync.py --apply # live changes
# Pull: Plane -> markdown (dry-run by default, --apply writes with backup)
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_pull.py # dry-run
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_pull.py --apply # live (backs up to .plane-pull-backup/)
# Compare: side-by-side diff (read-only)
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_compare.py # full table
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_compare.py --diff-only # only mismatches
PLANE_API_KEY=$(op item get "Plane API" --vault "Dev Secrets" --fields label="API Key" --reveal) \
python3 .claude/skills/plane/scripts/plane_compare.py --module infrastructure # filter by moduleThe sync script auto-injects credentials via op if PLANE_API_KEY is not set.
Workspace Defaults
See references/our-workspace.md for all IDs, states, modules, labels, and conventions.
- Workspace:
[your-workspace-slug] - Project:
Grand Plan(UUID:8238b353-5e87-4b72-b199-fec061be8b98) - Identifier prefix:
GP - [Your Name]'s user ID:
[YOUR_USER_ID]
API Patterns
See references/patterns.md for:
- Why curl (not urllib): Plane returns 403 with Python HTTP clients
- Rate limiting: 1.1s between calls
- Cursor-based pagination
- Issue title convention:
Description [TASK-ID]
Container Scope
MCP server is Mac-only (interactive Claude Code sessions). It launches via start-plane-mcp.sh, which resolves the API key from 1Password using the OP_SERVICE_ACCOUNT_TOKEN (set in ~/.zshrc). Batch jobs use gap scripts with PLANE_API_KEY from macOS Keychain (security find-generic-password -s plane-api-key).
Reference Docs
references/our-workspace.md-- IDs, states, modules, labelsreferences/api-reference.md-- Condensed endpoint referencereferences/mcp-tools.md-- MCP server tool catalog (populate after smoke test)references/patterns.md-- Learned API patterns and gotchas
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

