agentclash-cli-setup
Use when configuring the AgentClash CLI, authenticating with device login or tokens, selecting a workspace, saving default config with link, creating project…
Skill by agentclash
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/agentclash-agentclash-cli-setup
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.
About
Use cases: backend
Reviews
Write a reviewNo 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 and code. 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/agentclash-cli-setup
What's inside
- Skill name
agentclash-cli-setup- Description
- Use when configuring the AgentClash CLI, authenticating with device login or tokens, selecting a workspace, saving default config with link, creating project config with init, resolving API URL precedence, or diagnosing CLI access against production, local, or self-hosted backends.
- License
- MIT
- Metadata
- agentclash.role: setup · agentclash.version: 1 · agentclash.requires_cli: true
- Instructions
- 212 lines in SKILL.md · view on GitHub
Before installing
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (1)
- SKILL.md
SKILL.md (first lines)
# AgentClash CLI Setup ## Purpose Configure an AgentClash CLI session that can reach the intended backend, authenticate safely, resolve the right workspace, and pass `agentclash doctor` before a user starts authoring packs or running evals. ## Use When - A user asks to install, authenticate, verify, or repair AgentClash CLI access. - A coding agent needs AgentClash access but does not have the AgentClash source repo. - A user needs to switch workspaces, save a default workspace, or create project-local `.agentclash.yaml` config. - A CLI command fails because API URL, token, organization, workspace, or saved config precedence is unclear. - CI needs a non-interactive setup path with `AGENTCLASH_TOKEN`. ## Do Not Use When - The CLI is already configured and the task is to run an eval or inspect a scorecard. - The user needs to author challenge pack YAML; use `agentclash-challenge-pack-yaml-author` after setup passes. - The user is making a release decision or CI gate from completed runs; use `agentclash-ci-release-gate`. - The task requires changing AgentClash CLI source code rather than using the CLI. ## Inputs Needed - Backend target: hosted production, local development, or self-hosted. - Whether the CLI is installed as `agentclash` or run from source with `go run .` inside `cli/`. - Whether browser/device login is acceptable, or whether `AGENTCLASH_TOKEN` must be used. - Organization ID if `workspace list` cannot infer one from saved config. - Workspace ID, workspace slug/name, or permission to choose one interactively with `agentclash link`. - Whether the command should mutate saved user config under `~/.config/agentclash/config.yaml`. - Whether the current repository should get project-local `.agentclash.yaml` config with `agentclash init`. ## Environment Use hosted production by default: ```bash export AGENTCLASH_API_URL="https://api.agentclash.dev" ``` Use a local backend only when the user is explicitly running the API server locally: ```bash export AGENTCLASH_API_URL="http://localhost:8080" ``` For CI or other non-interactive shells, provide a token through the environment instead of running browser login: ```bash export AGENTCLASH_TOKEN="<token>" export AGENTCLASH_WORKSPACE="<workspace-id>" ``` Do not print token values in chat, logs, docs, or committed files. ## Config And Precedence API URL resolution: ```text --api-url > AGENTCLASH_API_URL > saved user config > default ``` The source-build default is `http://localhost:8080`. Released CLI builds stamp the production default at release time, but skills should still set `AGENTCLASH_API_URL="https://api.agentclash.dev"` explicitly for hosted workflows so copied commands behave the same in source and released builds. Workspace resolution: ```text --workspace / -w > AGENTCLASH_WORKSPACE > project .agentclash.yaml > saved user config ``` Organization resolution for commands that need an org: ```text AGENTCLASH_ORG > project .agentclash.yaml > saved user config ``` Auth token resolution: ```text AGENTCLASH_TOKEN > stored CLI credentials ``` Saved user config lives at: ```text ~/.config/agentclash/config.yaml ``` Project-local config lives in `.agentclash.yaml` and is discovered by walking up from the current directory. It can store `workspace_id` and `org_id`. ## Procedure 1. Choose the backend. For normal hosted work, export `AGENTCLASH_API_URL="https://api.agentclash.dev"` first. 2. Verify the CLI is callable with `agentclash version` or, from the repo `cli/` directory, `go run . version`. 3. Authenticate. Prefer `agentclash auth login --device` for remote shells; use `AGENTCLASH_TOKEN` for CI. 4. Check the authenticated identity with `agentclash auth status`. 5. Select a workspace with `agentclash link` for the guided flow, or `agentclash workspace use <workspace-id>` when the ID is already known. Both commands write saved user config. 6. If this repository should carry its own workspace binding, run `agentclash init --workspace-id <workspace-id> --org-id <organization-id>` from the project root. 7. Run `agentclash doctor` to verify install, auth, workspace, challenge-pack visibility, deployment visibility, and baseline readiness. 8. Report the effective backend, auth state, workspace, doctor result, and the next command the user should run. ## Commands Hosted production, interactive setup: ```bash export AGENTCLASH_API_URL="https://api.agentclash.dev" agentclash version agentclash auth login --device agentclash auth status agentclash link agentclash doctor ``` Hosted production when the workspace ID is already known: ```bash export AGENTCLASH_API_URL="https://api.agentclash.dev" agentclash auth login --device agentclash workspace use <workspace-id> agentclash doctor ``` Workspace discovery when an organization must be explicit: ```bash export AGENTCLASH_API_URL="https://api.agentclash.dev"
From agentclash/agentclash, MIT.
More from agentclash/agentclash
- 0.614score
agentclash-agent-deployment-setup
agentclash
Use when creating, selecting, or diagnosing AgentClash agent deployments for runs, including ready build versions, runtime profiles, provider/model wiring…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-agent-build-author
agentclash
Use when creating, editing, validating, or readying AgentClash agent builds and build versions, including agent identity, spec JSON, prompts, model/runtime…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-challenge-pack-yaml-author
agentclash
Use when writing or editing AgentClash challenge pack YAML, including pack/version metadata, execution mode, challenges, cases, input sets, scoring blocks…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-challenge-pack-artifacts
agentclash
Use when specifying AgentClash challenge pack assets, artifact references, produced file captures, evidence references, artifact upload/download expectations…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-challenge-pack-planner
agentclash
Use when turning a vague AgentClash evaluation idea into a source-backed challenge pack plan with task boundaries, target agents, cases, input sets, scoring…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-dataset-workflows
agentclash
Use when managing AgentClash datasets via CLI — create versions, import/export examples, run evals, CI gates, synthetic generation, trace import, candidate…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-prompt-eval-playground
agentclash
Use when scaffolding, validating, or running prompt eval YAML configs and managing playground experiments, test cases, and prompt variants via the AgentClash…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-quickstart
agentclash
Use when checking whether a workspace is ready to run AgentClash evals, interpreting quickstart readiness checks, or choosing the next CLI command after auth…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-ci-release-gate
agentclash
Use when wiring AgentClash manifest-based CI gates, deciding whether a PR should run AgentClash, resolving baselines, running `agentclash ci run`…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-workspace-admin
agentclash
Use when creating or administering AgentClash organizations and workspaces, inviting members, updating roles, or binding default workspace context beyond…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-compare-and-triage
agentclash
Use when comparing baseline vs candidate AgentClash runs, evaluating release gates, managing workspace baseline bookmarks, or building a replay triage…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-agent-harness-setup
agentclash
Use when creating, running, or ranking Agent Harness coding-agent tasks via the CLI, including harness specs, E2B runner kinds, suite task banks, executions…
SkillBFreshness: B★ 36Claude Code +9
Signals
- Stars
- 36
- Forks
- 3
- Open issues
- 61
- Last commit (this folder)
- Jun 24, 2026 (4 months ago)
- Last release
- Aug 15, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/agentclash/agentclash
- Website
- www.agentclash.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from agentclash
- 0.614score
agentclash-challenge-pack-artifacts
agentclash
Use when specifying AgentClash challenge pack assets, artifact references, produced file captures, evidence references, artifact upload/download expectations…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-challenge-pack-planner
agentclash
Use when turning a vague AgentClash evaluation idea into a source-backed challenge pack plan with task boundaries, target agents, cases, input sets, scoring…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-challenge-pack-yaml-author
agentclash
Use when writing or editing AgentClash challenge pack YAML, including pack/version metadata, execution mode, challenges, cases, input sets, scoring blocks…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-ci-release-gate
agentclash
Use when wiring AgentClash manifest-based CI gates, deciding whether a PR should run AgentClash, resolving baselines, running `agentclash ci run`…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-compare-and-triage
agentclash
Use when comparing baseline vs candidate AgentClash runs, evaluating release gates, managing workspace baseline bookmarks, or building a replay triage…
SkillBFreshness: B★ 36Claude Code +9 - 0.614score
agentclash-agent-deployment-setup
agentclash
Use when creating, selecting, or diagnosing AgentClash agent deployments for runs, including ready build versions, runtime profiles, provider/model wiring…
SkillBFreshness: B★ 36Claude Code +9
Cite this page
agentclash-cli-setup skill. Agent Mart. https://agentmart.dev/skills/agentclash-agentclash-cli-setup (last updated 2026-10-24)