Agent skill

Cursor Agents Workflow

by langfuse in langfuse/langfuse

Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and…

Custom licenceAuto-check passedDevelopment

Install Cursor Agents Workflow

skills CLI
$ npx skills add langfuse/langfuse --skill cursor-agents-workflow -a claude-code

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

GitHub CLI
$ gh skill install langfuse/langfuse cursor-agents-workflow --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/langfuse/langfuse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cursor-agents-workflow .claude/skills/cursor-agents-workflow && 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
cursor-agents-workflow
GitHub stars
35k
Token cost
~1.7k tokens
SKILL.md length
890 words
Files
2
Skills in repo
33
Repo updated
First seen
Licence
Custom licence

At a glance

Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and…

  • Works in 3 steps: Keep each thread open. Do not reply in… → If the finding is right: apply the fix,… → If you are sure it should be skipped:…
  • Cursor desktop agent implements a Linear issue
  • SKILL.md covers Branch names, Linear connection, Pull requests and Bot review comments, plus 4 more sections
  • Reaches pr-123.preview.langfuse.com; needs LINEAR_API_KEY and LINEAR_TOKEN

What it does

Cursor Agents Workflow is an agent skill from langfuse/langfuse. Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and review-doubt notes for Cursor agents. Use when a Cursor Cloud or Cursor desktop agent implements a Linear issue, opens a GitHub PR, asks a human to test, posts screenshots or videos, or handles Claude, Greptile, or Codex code-review comments.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Verification before completion. It works with GitHub, Linear, Langfuse and Model Context Protocol. The repository describes itself as: 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

When your agent uses it

  • Cursor desktop agent implements a Linear issue
  • Opens a GitHub PR
  • Asks a human to test
  • Posts screenshots

Example prompts

  • “/cursor-agents-workflow”

Requirements

  • A credential in LINEAR_API_KEY
  • A credential in LINEAR_TOKEN

Workflow steps

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

  1. Keep each thread open. Do not reply in the thread.
  2. If the finding is right: apply the fix, then resolve the thread.
  3. If you are sure it should be skipped: tell the human in plain language

What it can do on your machine

Read from SKILL.md and the folder at commit 8b58764. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are html).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • pr-123.preview.langfuse.com

    Also links to:

    • cursor.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • LINEAR_API_KEY
    • LINEAR_TOKEN
    • LINEAR_API_TOKEN

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

Context cost

Cursor Agents Workflow loads about 1.7k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 890 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 890 words (~1,732 tokens).

“Use this when implementing Langfuse work as a Cursor agent. Keep humans in the loop with short, testable asks. Do not write long agent-only reports.”

— opening of SKILL.md by langfuse, Custom licence
name
cursor-agents-workflow

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .agents/skills/cursor-agents-workflow of langfuse/langfuse.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 8b58764

Compare with similar skills

Cursor Agents Workflow 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.

Cursor Agents Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cursor Agents Workflow this skilllangfuse/langfuse35k—~1.7kAutomated safety check: PassCustom licence
Octocode Code Researchbgauryy/octocode946—~1.5kAutomated safety check: PassMIT
Ops Triagedavepoon/buildwithclaude3.6k—~2kAutomated safety check: NotesMIT
GitHub Commentingjuspay/neurolink143—~698Automated safety check: PassMIT
GitHubswarmclawai/swarmclaw687—~820Automated safety check: PassMIT
Superset Integration Toolssuperset-sh/superset15k—~1.6kAutomated safety check: WarnCustom licence

Similar skills

  • Octocode Code Research

    bgauryy/octocode

    Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

    946 GitHub stars~1.5k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Ops Triage

    davepoon/buildwithclaude

    Cross-platform issue triage. An agent skill from davepoon/buildwithclaude.

    3.6k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • GitHub Commenting

    juspay/neurolink

    How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules.

    143 GitHub stars~698 tokensUpdated today
    DevelopmentAuto-check passed
  • GitHub

    swarmclawai/swarmclaw

    GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.

    687 GitHub stars~820 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Superset Integration Tools

    superset-sh/superset

    Lists and calls the tools of connected integrations such as Linear, GitHub, Sentry or Notion through the superset mcp command, without storing a token on the machine.

    15k GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check: warnings
  • Deepseek Automation

    zhu1090093659/deepseek-pp

    A skill your agent uses when implementing, resuming, reviewing, or verifying the DeepSeek++ Codex-style automation feature in this repository.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

More from langfuse/langfuse

All 33 skills in this repo
  • Linear Context Handover

    langfuse/langfuse

    Use Linear as the org's memory: reconstruct a feature's history before touching it, and leave the reasoning behind finished work in the ticket description so the next agent inherits it.

    35k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Add Model Price

    langfuse/langfuse

    A skill your agent uses when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing tiers, tokenizer IDs, or matchPattern regexes for OpenAI…

    35k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Backend Dev Guidelines

    langfuse/langfuse

    Build or review Langfuse backend code. An agent skill from langfuse/langfuse.

    35k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Navigate Langfuse repositories, code areas, and agent skills.

    35k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Refactor React Effects

    langfuse/langfuse

    Refactor avoidable React useEffect usage in Langfuse frontend code.

    35k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Add To Dependabot CSV

    langfuse/langfuse

    Append GitHub Dependabot or Snyk/code-scanning alerts to an existing vulnerability CSV after verifying their API metadata.

    35k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Questions about Cursor Agents Workflow

What does Cursor Agents Workflow do?

Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and…. Cursor Agents Workflow is an agent skill from langfuse/langfuse. Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and review-doubt notes for Cursor agents.

When should I use Cursor Agents Workflow?

Cursor Agents Workflow fits situations like: Cursor desktop agent implements a Linear issue; opens a GitHub PR; asks a human to test; posts screenshots.

How do I install Cursor Agents Workflow in Claude Code?

Run `npx skills add langfuse/langfuse --skill cursor-agents-workflow -a claude-code`. Or copy the skill folder (.agents/skills/cursor-agents-workflow in langfuse/langfuse) into .claude/skills/cursor-agents-workflow in your project. Claude Code loads it when a task matches its description.

How do I install Cursor Agents Workflow in Codex?

Run `npx skills add langfuse/langfuse --skill cursor-agents-workflow -a codex`. Or copy the skill folder (.agents/skills/cursor-agents-workflow in langfuse/langfuse) into .agents/skills/cursor-agents-workflow in your project. Codex loads it when a task matches its description.

Can I use Cursor Agents Workflow 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 langfuse/langfuse --skill cursor-agents-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cursor-agents-workflow, .gemini/skills/cursor-agents-workflow, .github/skills/cursor-agents-workflow and .opencode/skills/cursor-agents-workflow in your project.

What does Cursor Agents Workflow need to run?

Going by SKILL.md and its folder, Cursor Agents Workflow needs credentials named LINEAR_API_KEY, LINEAR_TOKEN and LINEAR_API_TOKEN. Our summary lists: A credential in LINEAR_API_KEY; A credential in LINEAR_TOKEN.

Does Cursor Agents Workflow access the network?

SKILL.md names 2 domains. In commands or code: pr-123.preview.langfuse.com; the agent is likely to contact it when it follows the instructions. As links in the text: cursor.com. This is read from the text; nothing was executed.

Is Cursor Agents Workflow 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 Cursor Agents Workflow use?

Cursor Agents Workflow has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Cursor Agents Workflow use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Cursor Agents Workflow?

Skills that share tags, products or a category with Cursor Agents Workflow: Octocode Code Research (bgauryy/octocode, 946 stars), Ops Triage (davepoon/buildwithclaude, 3.6k stars), GitHub Commenting (juspay/neurolink, 143 stars) and GitHub (swarmclawai/swarmclaw, 687 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cursor Agents Workflow?

langfuse (a GitHub organization) maintains it in langfuse/langfuse, which has 35,460 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 7, 2026.

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