AutomationFlowsWeb Scraping › Github Issue → Claude Fix & Pr

Github Issue → Claude Fix & Pr

GitHub Issue → Claude Fix & PR. Uses httpRequest, ssh. Scheduled trigger; 6 nodes.

Cron / scheduled trigger★★★★☆ complexity6 nodesHTTP RequestSsh
Web Scraping Trigger: Cron / scheduled Nodes: 6 Complexity: ★★★★☆ Added:

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "id": "a1b2c3d4-0000-4000-8000-000000000000",
  "name": "GitHub Issue \u2192 Claude Fix & PR",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "minutes",
              "minutesInterval": 5
            }
          ]
        }
      },
      "id": "a1b2c3d4-0001-4000-8000-000000000001",
      "name": "Every 5 Minutes",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "const staticData = $getWorkflowStaticData('global');\nconst lastChecked = staticData.lastChecked || new Date(Date.now() - 5 * 60 * 1000).toISOString();\nreturn { since: lastChecked };"
      },
      "id": "a1b2c3d4-0002-4000-8000-000000000002",
      "name": "Read Last Checked",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        460,
        300
      ]
    },
    {
      "parameters": {
        "method": "GET",
        "url": "https://api.github.com/search/issues",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $env.GITHUB_TOKEN }}"
            },
            {
              "name": "Accept",
              "value": "application/vnd.github+json"
            },
            {
              "name": "X-GitHub-Api-Version",
              "value": "2022-11-28"
            }
          ]
        },
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {
              "name": "q",
              "value": "=is:issue created:>{{ $json.since }} assignee:tupe12334"
            },
            {
              "name": "sort",
              "value": "created"
            },
            {
              "name": "order",
              "value": "asc"
            },
            {
              "name": "per_page",
              "value": "100"
            }
          ]
        },
        "options": {}
      },
      "id": "a1b2c3d4-0003-4000-8000-000000000003",
      "name": "Search New Issues",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        680,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "const staticData = $getWorkflowStaticData('global');\nstaticData.lastChecked = new Date().toISOString();\nconst items = $input.item.json.items || [];\nif (items.length === 0) return [];\nreturn items.map(issue => ({\n  issueNumber: issue.number,\n  issueTitle: issue.title || 'No title',\n  issueBody: issue.body,\n  issueUrl: issue.html_url,\n  repoFullName: issue.repository_url.replace('https://api.github.com/repos/', '')\n}));"
      },
      "id": "a1b2c3d4-0004-4000-8000-000000000004",
      "name": "Extract Issues & Save Cursor",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        900,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "const issueNumber = $input.item.json.issueNumber;\nconst issueTitle = $input.item.json.issueTitle || 'No title';\nconst issueBody = ($input.item.json.issueBody || 'No description provided.').substring(0, 800);\nconst repoFullName = $input.item.json.repoFullName;\nconst issueUrl = $input.item.json.issueUrl;\nconst repoBase = $env.REPO_BASE_PATH;\nconst repoPath = repoBase + '/' + repoFullName;\nconst repoParent = repoPath.split('/').slice(0, -1).join('/');\nconst cloneUrl = `https://${$env.GITHUB_TOKEN}@github.com/${repoFullName}.git`;\nconst safeRepoName = repoFullName.split('/').join('-');\nconst promptFile = `/tmp/claude-${safeRepoName}-${issueNumber}-prompt.txt`;\nconst scriptFile = `/tmp/claude-${safeRepoName}-${issueNumber}.sh`;\nconst sessionName = `claude-${safeRepoName}-${issueNumber}`;\nconst prompt = `Fix GitHub issue #${issueNumber}: ${issueTitle}\\n\\nRepository: ${repoFullName}\\nIssue URL: ${issueUrl}\\n\\nIssue description:\\n${issueBody}\\n\\nRequirements:\\n- Analyze the issue and implement a complete fix\\n- Add or update tests if applicable\\n- Commit your changes with a descriptive message referencing issue #${issueNumber}\\n- Push the branch and open a pull request that closes #${issueNumber}`;\nconst promptB64 = Buffer.from(prompt).toString('base64');\nconst script = [\n  '#!/bin/bash',\n  'export CLAUDE_CODE_OAUTH_TOKEN=$(cat ~/.claude-ssh-token)',\n  `if [ ! -d \"${repoPath}/.git\" ]; then`,\n  `  mkdir -p \"${repoParent}\"`,\n  `  git clone \"${cloneUrl}\" \"${repoPath}\"`,\n  'fi',\n  `cd \"${repoPath}\"`,\n  `PROMPT=$(cat \"${promptFile}\")`,\n  'exec /opt/homebrew/bin/claude --worktree --dangerously-skip-permissions \"$PROMPT\"',\n  ''\n].join('\\n');\nconst scriptB64 = Buffer.from(script).toString('base64');\nconst command = [\n  `printf '%s' '${promptB64}' | base64 -d > ${promptFile}`,\n  `printf '%s' '${scriptB64}' | base64 -d > ${scriptFile}`,\n  `chmod +x ${scriptFile}`,\n  `/opt/homebrew/bin/tmux new-session -d -s \"${sessionName}\" -x 220 -y 50 ${scriptFile}`\n].join(' && ');\nreturn { command, sessionName, issueNumber, issueTitle, repoFullName };"
      },
      "id": "a1b2c3d4-0005-4000-8000-000000000005",
      "name": "Build tmux Command",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1120,
        300
      ]
    },
    {
      "parameters": {
        "authentication": "privateKey",
        "resource": "command",
        "operation": "execute",
        "command": "={{ $json.command }}"
      },
      "id": "a1b2c3d4-0006-4000-8000-000000000006",
      "name": "Run Claude on Host",
      "type": "n8n-nodes-base.ssh",
      "typeVersion": 1,
      "position": [
        1340,
        300
      ],
      "credentials": {
        "sshPrivateKey": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "Every 5 Minutes": {
      "main": [
        [
          {
            "node": "Read Last Checked",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Read Last Checked": {
      "main": [
        [
          {
            "node": "Search New Issues",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Search New Issues": {
      "main": [
        [
          {
            "node": "Extract Issues & Save Cursor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Issues & Save Cursor": {
      "main": [
        [
          {
            "node": "Build tmux Command",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Build tmux Command": {
      "main": [
        [
          {
            "node": "Run Claude on Host",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "meta": {
    "templateCredsSetupCompleted": false
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

GitHub Issue → Claude Fix & PR. Uses httpRequest, ssh. Scheduled trigger; 6 nodes.

Source: https://github.com/tupe12334/n8n-flows/blob/9c8649df8290039810edb70e1b69782c76571cea/flows/github-issue-to-claude.json — original creator credit. Request a take-down →

More Web Scraping workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

Web Scraping

N8N-Self-Updater. Uses ssh, emailSend, httpRequest. Scheduled trigger; 27 nodes.

Ssh, Email Send, HTTP Request
Web Scraping

&gt; An automated n8n workflow originally built for DigitalOcean-based n8n deployments, but fully compatible with any VPS or cloud hosting (e.g., AWS, Google Cloud, Hetzner, Linode, etc.) where n8n ru

Ssh, Email Send, HTTP Request
Web Scraping

This template is designed to automatically clean up old image tags in the Docker registry and perform garbage collection. List all images in the registry Preserve the last 10 tags for each image (late

HTTP Request, Email Send, Ssh
Web Scraping

Hydra Database Backup. Uses ssh, httpRequest. Scheduled trigger; 9 nodes.

Ssh, HTTP Request
Web Scraping

W09 — Backup Verification. Uses ssh, httpRequest. Scheduled trigger; 7 nodes.

Ssh, HTTP Request