Swig CI Repro
swig/swig
Reproduce a GitHub Actions Linux CI failure locally when it does not happen on your machine: a podman/docker image that mirrors the ubuntu-22.04 runner by reusing the real Tools/CI-linux-.sh install…
Complete an explicitly authorized official Claude subscription login on a Linux Devin Docker worker without inference or credential logging.
Install Claude Subscription Login
$ npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tamaratran/jev-pruner claude-subscription-login --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tamaratran/jev-pruner.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/claude-subscription-login .claude/skills/claude-subscription-login && rm -rf skills-srcUse ~/.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/
Install the "claude-subscription-login" agent skill from https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-login into .claude/skills/claude-subscription-login/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-subscription-login", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-loginType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tamaratran/jev-pruner claude-subscription-login --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamaratran/jev-pruner.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/claude-subscription-login .agents/skills/claude-subscription-login && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "claude-subscription-login" agent skill from https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-login into .agents/skills/claude-subscription-login/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-subscription-login", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tamaratran/jev-pruner claude-subscription-login --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamaratran/jev-pruner.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/claude-subscription-login .cursor/skills/claude-subscription-login && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "claude-subscription-login" agent skill from https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-login into .cursor/skills/claude-subscription-login/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-subscription-login", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tamaratran/jev-pruner.git --path .agents/skills/claude-subscription-login--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tamaratran/jev-pruner claude-subscription-login --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamaratran/jev-pruner.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/claude-subscription-login .gemini/skills/claude-subscription-login && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "claude-subscription-login" agent skill from https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-login into .gemini/skills/claude-subscription-login/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-subscription-login", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tamaratran/jev-pruner claude-subscription-loginInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tamaratran/jev-pruner.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/claude-subscription-login .github/skills/claude-subscription-login && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "claude-subscription-login" agent skill from https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-login into .github/skills/claude-subscription-login/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-subscription-login", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tamaratran/jev-pruner claude-subscription-login --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamaratran/jev-pruner.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/claude-subscription-login .opencode/skills/claude-subscription-login && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "claude-subscription-login" agent skill from https://github.com/tamaratran/jev-pruner/tree/main/.agents/skills/claude-subscription-login into .opencode/skills/claude-subscription-login/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-subscription-login", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
claude-subscription-login- GitHub stars
- 160
- Token cost
- ~629 tokens
- SKILL.md length
- 309 words
- Files
- 2
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Complete an explicitly authorized official Claude subscription login on a Linux Devin Docker worker without inference or credential logging.
- Works in 7 steps: Use the existing Chrome browser and its… → Create a dedicated mode-700 auth home… → Run the helper with explicit parameters → …
- Tasks that involve Containers
- Runs Python scripts from its folder; calls claude and python
What it does
Claude Subscription Login is an agent skill from tamaratran/jev-pruner. Complete an explicitly authorized official Claude subscription login on a Linux Devin Docker worker without inference or credential logging.
Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `login.py`).
It sits in DevOps & Cloud, covering Containers. It works with Docker and Linux. The repository describes itself as: Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it. The licence is MIT.
When your agent uses it
- Tasks that involve Containers
Example prompts
- “/claude-subscription-login”
Requirements
- Python 3
- Docker
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Use the existing Chrome browser and its CDP endpoint at
- Create a dedicated mode-700 auth home outside the repo and evidence. Do not
- Run the helper with explicit parameters
- Continue the official browser flow. Confirm the exact requested account
- Read the helper's output after the user completes verification. It reports
- Verify with claude auth status --json in a fresh container using only the
- Confirm no benchmark containers/processes are running. Keep subsequent
What it can do on your machine
Read from SKILL.md and the folder at commit edbc602. 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
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
claudepython
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Claude Subscription Login loads about 629 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 309 words of instructions outside code blocks.
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
The full file from tamaratran/jev-pruner at commit edbc602, republished under its MIT licence (© tamaratran). 309 words, ~629 tokens.
Download SKILL.mdSave it as
.claude/skills/claude-subscription-login/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- claude-subscription-login
- description
- Complete an explicitly authorized official Claude subscription login on a Linux Devin Docker worker without inference or credential logging.
Use only when the user requests subscription login. Authentication does not authorize a benchmark, smoke, or inference call.
Use the existing Chrome browser and its CDP endpoint at
http://localhost:29229. Docker must already work, and the image must contain Claude Code 2.1.274. The helper needs Pythonplaywrightandpexpect==4.9.0.Create a dedicated mode-700 auth home outside the repo and evidence. Do not read credential file contents or save an OAuth token as a Devin secret without separate permission.
Run the helper with explicit parameters:
sh python login.py --image "$SMOKE_IMAGE" \ --auth-home "$CLAUDE_AUTH_HOME" --email "$LOGIN_EMAIL"It starts
claude auth login --claudeaiin a temporary container, opens the official URL, and privately submits the official one-time callback code to the CLI. It never runsclaude -p. No CLI output containing codes is logged.Continue the official browser flow. Confirm the exact requested account identity in the Google UI before entering an authorized password using secure secret substitution. Pause for user verification or CAPTCHA in this Desktop. Never expose passwords or callback codes in messages/screenshots.
Read the helper's output after the user completes verification. It reports
Login successfulonly when the official CLI does. Do not infer login success from the browser alone. The helper times out after 30 minutes.Verify with
claude auth status --jsonin a fresh container using only the private auth mount. Do not pass API keys, auth tokens, cloud-provider flags, custom headers, or an OAuth token override. Use--setting-sources ''and--settings '{"forceLoginMethod":"claudeai"}'. Report only selected status fields, not the entire config or credential contents.Confirm no benchmark containers/processes are running. Keep subsequent evaluations paused unless separately authorized. See
evals/README.mdfor read-only mounting, private per-trial auth storage, and reporting caveats.
Verified on Linux with the official Google login, user-completed 2FA/CAPTCHA, Claude Code 2.1.274, and Max subscription status. Status is local authentication selection, not a test of model availability or remaining subscription allowance.
© tamaratran, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/claude-subscription-login of tamaratran/jev-pruner.
- SKILL.md
- login.py
Open the folder on GitHubat commit edbc602
Compare with similar skills
Claude Subscription Login 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Claude Subscription Login this skilltamaratran/jev-pruner | 160 | — | ~629 | Automated safety check: Pass | MIT | |
| Swig CI Reproswig/swig | 6.3k | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| .NET Crash Dump Collectiondotnet/skills | 5.6k | 2 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Docker Jfr Benchmark Loopeclipse-rdf4j/rdf4j | 420 | — | ~945 | Automated safety check: Pass | BSD-3-Clause | |
| Minimegasandia-minimega/minimega | 160 | — | ~3.2k | Automated safety check: Pass | GPL-3.0-only | |
| Oneclickvirtoneclickvirt/oneclickvirt | 373 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 |
Similar skills
- Official
.NET Crash Dump Collection
dotnet/skills
Configures automatic crash dumps or captures dumps from running processes for modern .NET apps on Linux, macOS and Windows, including Docker and Kubernetes.
Docker Jfr Benchmark Loop
eclipse-rdf4j/rdf4j
Run a repeatable RDF4J performance loop against one JMH benchmark in Docker with Linux Java 26 and JFR CPU-time profiling.
Minimega
sandia-minimega/minimega
This skill should be used when the user asks how to configure, run, automate, integrate, or troubleshoot minimega (VMs, namespaces, VLANs, clusters, miniccc, miniweb, command socket or Python API…
Oneclickvirt
oneclickvirt/oneclickvirt
OneClickVirt operations skill for managing containers, virtual machines, provider nodes, health checks, and metrics through MCP.
Devsy
devsy-org/devsy
Operate Devsy workspaces and providers for end users. An agent skill from devsy-org/devsy.
More from tamaratran/jev-pruner
Jev Pruner
tamaratran/jev-pruner
Use Jev to prune lengthy output from non-interactive build, test, install, and search commands in Codex.
Modal Login
tamaratran/jev-pruner
Authenticate an explicitly authorized Modal CLI through existing Chrome without logging token values.
Related
Categories
Questions about Claude Subscription Login
What does Claude Subscription Login do?
Complete an explicitly authorized official Claude subscription login on a Linux Devin Docker worker without inference or credential logging. Claude Subscription Login is an agent skill from tamaratran/jev-pruner. Complete an explicitly authorized official Claude subscription login on a Linux Devin Docker worker without inference or credential logging.
When should I use Claude Subscription Login?
Claude Subscription Login fits situations like: tasks that involve Containers.
How do I install Claude Subscription Login in Claude Code?
Run `npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a claude-code`. Or copy the skill folder (.agents/skills/claude-subscription-login in tamaratran/jev-pruner) into .claude/skills/claude-subscription-login in your project. Claude Code loads it when a task matches its description.
How do I install Claude Subscription Login in Codex?
Run `npx skills add tamaratran/jev-pruner --skill claude-subscription-login -a codex`. Or copy the skill folder (.agents/skills/claude-subscription-login in tamaratran/jev-pruner) into .agents/skills/claude-subscription-login in your project. Codex loads it when a task matches its description.
Can I use Claude Subscription Login 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 tamaratran/jev-pruner --skill claude-subscription-login -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-subscription-login, .gemini/skills/claude-subscription-login, .github/skills/claude-subscription-login and .opencode/skills/claude-subscription-login in your project.
What does Claude Subscription Login need to run?
Going by SKILL.md and its folder, Claude Subscription Login needs Python for the scripts in its folder and the command-line tools its instructions call (claude and python). Our summary lists: Python 3; Docker.
Does Claude Subscription Login access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Claude Subscription Login 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 Claude Subscription Login use?
Claude Subscription Login is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Claude Subscription Login use?
About 629 tokens (SKILL.md is roughly 2.5k 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 Claude Subscription Login?
Skills that share tags, products or a category with Claude Subscription Login: Swig CI Repro (swig/swig, 6.3k stars), .NET Crash Dump Collection (dotnet/skills, 5.6k stars), Docker Jfr Benchmark Loop (eclipse-rdf4j/rdf4j, 420 stars) and Minimega (sandia-minimega/minimega, 160 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Claude Subscription Login?
tamaratran (a GitHub user) maintains it in tamaratran/jev-pruner, which has 160 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 30, 2026.
Source: tamaratran/jev-pruner on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.