Gws
kv0906/pm-kit
This skill should be used when the user asks to "set up gws", "install Google Workspace CLI", "connect Gmail to Claude", "manage Google Drive from terminal", "send email from CLI", "check my…
Install/auth CLIs the sandbox lacks - gws (Drive, Gmail, Sheets, Calendar), gcloud, agents-cli, mcp-cli (MCP servers).
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add google/adk-recipes --skill bootstrap-google-tools -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install google/adk-recipes bootstrap-google-tools --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/google/adk-recipes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools .claude/skills/bootstrap-google-tools && 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 "bootstrap-google-tools" agent skill from https://github.com/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools into .claude/skills/bootstrap-google-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bootstrap-google-tools", 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/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-toolsType 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 google/adk-recipes --skill bootstrap-google-tools -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install google/adk-recipes bootstrap-google-tools --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-recipes.git skills-src && mkdir -p .agents/skills && cp -r skills-src/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools .agents/skills/bootstrap-google-tools && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bootstrap-google-tools" agent skill from https://github.com/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools into .agents/skills/bootstrap-google-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bootstrap-google-tools", 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 google/adk-recipes --skill bootstrap-google-tools -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install google/adk-recipes bootstrap-google-tools --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-recipes.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools .cursor/skills/bootstrap-google-tools && 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 "bootstrap-google-tools" agent skill from https://github.com/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools into .cursor/skills/bootstrap-google-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bootstrap-google-tools", 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/google/adk-recipes.git --path core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools--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 google/adk-recipes --skill bootstrap-google-tools -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install google/adk-recipes bootstrap-google-tools --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-recipes.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools .gemini/skills/bootstrap-google-tools && 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 "bootstrap-google-tools" agent skill from https://github.com/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools into .gemini/skills/bootstrap-google-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bootstrap-google-tools", 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 google/adk-recipes bootstrap-google-toolsInstalls 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 google/adk-recipes --skill bootstrap-google-tools -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/google/adk-recipes.git skills-src && mkdir -p .github/skills && cp -r skills-src/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools .github/skills/bootstrap-google-tools && 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 "bootstrap-google-tools" agent skill from https://github.com/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools into .github/skills/bootstrap-google-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bootstrap-google-tools", 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 google/adk-recipes --skill bootstrap-google-tools -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install google/adk-recipes bootstrap-google-tools --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-recipes.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools .opencode/skills/bootstrap-google-tools && 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 "bootstrap-google-tools" agent skill from https://github.com/google/adk-recipes/tree/main/core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools into .opencode/skills/bootstrap-google-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bootstrap-google-tools", 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.
bootstrap-google-toolsInstall/auth CLIs the sandbox lacks - gws (Drive, Gmail, Sheets, Calendar), gcloud, agents-cli, mcp-cli (MCP servers).
Bootstrap Google Tools is an agent skill from google/adk-recipes, published by the product's own GitHub organization. Install/auth CLIs the sandbox lacks - gws (Drive, Gmail, Sheets, Calendar), gcloud, agents-cli, mcp-cli (MCP servers). Use on "command not found" or before GCP/Workspace/MCP work.
Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering MCP servers, Email management and Cloud office suites. It works with Model Context Protocol, Google Cloud, Google Workspace and Gmail. The repository describes itself as: A collection of agent recipes, reference patterns, and vertical plugins built with Agent Development Kit (ADK). The licence is Apache-2.0.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit fa9bdde. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
curlgcloudbashuvnpmnpxbqgsutilFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
nodejs.orgdl.google.comraw.githubusercontent.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
CLOUDSDK_AUTH_ACCESS_TOKENGOOGLE_WORKSPACE_CLI_TOKENGOOGLE_WORKSPACE_CLI_CLIENT_SECRETGOOGLE_APPLICATION_CREDENTIALSUSER_TOKENMCP_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Bootstrap Google Tools loads about 5k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 2,363 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.
The automated check found patterns that need a careful read before installing.
**Don't pipe-to-bash.** `curl … | bash` is blocked by the tool policy (pipingAutomated 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.
The full file from google/adk-recipes at commit fa9bdde, republished under its Apache-2.0 licence (© google). 2,363 words, ~4,988 tokens.
.claude/skills/bootstrap-google-tools/SKILL.md (or your agent's skills folder).The sandbox ships lean — Node, gws, gcloud, agents-cli, and mcp-cli are
not prebaked. This skill is the verified install + auth recipe for each.
The tools are independent: install only the one the task needs. This is a
menu, not a sequence — there's no 1-2-3 to run in order.
~/.local, credentials in /workspaceTwo different durability rules, because the sandbox has two boundaries:
$HOME
included) persists. Install once, reuse next session./workspace is migrated — and that migration is a zip that drops symlinks
and strips executable bits (and is best-effort). So it can't carry installed
CLIs at all; it's only safe for plain data files.That dictates the split:
| What | Where | On upgrade |
|---|---|---|
| CLI binaries | ~/.local (bin dir ~/.local/bin is on PATH) | gone — reinstalled (cheap, automatic via the command -v check) |
| Credentials / config | /workspace/lha/config/ (gws/, gcloud/, mcp_servers.json) | migrated — logins survive |
So: install binaries the normal way, but point each tool's config dir at
/workspace/lha/config (via its own env var, shown per tool) so the expensive
part — the OAuth client + tokens — survives upgrades. Don't put binaries on
/workspace: they can't migrate anyway, and bloating the migration zip risks
the credentials that can. ~/.local/bin is already on PATH (runtime image),
and the bash shell is non-login (no ~/.profile), so that image PATH is
what makes installs resolve.
| Task | Tool | Needs first |
|---|---|---|
| Google Workspace — Drive / Gmail / Sheets / Calendar / Chat | gws | Node |
Raw GCP, or creating a gws OAuth client by hand | gcloud | — |
| Call another agent deployed remotely (A2A / ADK) | agents-cli | — (uv is present) |
| Use tools exposed by an MCP server | mcp-cli | — (standalone binary) |
Each tool's usage lives in its own skill (google-workspace, mcp-cli's
shipped skill, the google-agents-cli-* set). This skill only gets a tool
installed and authed, then hands off.
Within a session (and across sessions without an upgrade) a tool may already be present — check before installing, and install only what's missing:
bash(command="command -v gws") # or gcloud / agents-cli / mcp-cli / nodegws)The sandbox is Debian x86_64 with curl and tar but no xz. So you must
download the .tar.gz build, not the .tar.xz. Pick a current LTS version:
bash(command='mkdir -p ~/.local/bin && cd ~ && V=v22.x.x && \
curl -fsSLo node.tgz "https://nodejs.org/dist/$V/node-$V-linux-x64.tar.gz" && \
tar -xzf node.tgz -C ~/.local && rm node.tgz && \
ln -sf ~/.local/node-$V-linux-x64/bin/node ~/.local/node-$V-linux-x64/bin/npm ~/.local/node-$V-linux-x64/bin/npx ~/.local/bin/')Replace v22.x.x with the real current LTS. The ln -sf … ~/.local/bin/ step
puts node/npm/npx on PATH. Then verify:
bash(command="node --version && npm --version").tar.gz — .tar.xz will fail to extract (xz is absent).gws — Google Workspace CLIInstall the npm global into ~/.local (needs Node on PATH — see above) with
--prefix, so the binary lands at ~/.local/bin/gws:
bash(command='npm install -g --prefix ~/.local @googleworkspace/cli && gws --version')Expect 0.22.x. gws self-identifies as "not an officially supported Google
product."
Keep gws credentials on /workspace. By default gws reads/writes
~/.config/gws — which is not migrated on a runtime upgrade. Point it at
/workspace and use the file keyring (no OS keyring headless) on every gws
command so the OAuth client, token, and encryption key survive:
export GOOGLE_WORKSPACE_CLI_CONFIG_DIR=/workspace/lha/config/gws
export GOOGLE_WORKSPACE_CLI_KEYRING_BACKEND=fileFirst, always: probe the pre-injected token. When the user has used
"Connect Workspace" in the web UI, the GOOGLE_WORKSPACE_CLI_TOKEN secret is
auto-injected into every bash command — gws's highest-priority auth
source. Don't inspect the environment or ask; just run a cheap read against the
surface you need and see if it works:
bash(command="export GOOGLE_WORKSPACE_CLI_CONFIG_DIR=/workspace/lha/config/gws GOOGLE_WORKSPACE_CLI_KEYRING_BACKEND=file && gws gmail messages list --params '{\"maxResults\": 1}'")If it returns data, you're done — no OAuth client, no gws auth login, no
loopback bridge. It's a ~1h token (no refresh); the user re-clicks Connect
when it lapses. The token only carries the surfaces + access level
(read-only by default) the user picked — a gws call outside those scopes fails
(403/scope error), which means "reconnect with more surfaces or read-write,"
not that the token is missing. Don't trust gws auth status — with the
env token it reports auth_method: none / credential_source: token_env_var
even while reads succeed, so a real read is the only reliable check. Only if the
probe 401s (truly no token) do you fall through to the OAuth-client options
below.
Otherwise, point gws at an OAuth client — gws ships none of its own. Pick one:
client_secret.json into /workspace/lha/config/gws/ (must be a
Desktop app OAuth client — see the google-workspace skill).GOOGLE_WORKSPACE_CLI_CLIENT_ID + GOOGLE_WORKSPACE_CLI_CLIENT_SECRET.GOOGLE_APPLICATION_CREDENTIALS=/workspace/lha/config/gws/key.json
— for fully unattended automation (no interactive login).gws auth setup — provisions a project + OAuth client, but is a full-screen
TUI that can't be driven headless; prefer option 1 in the sandbox.gws auth login is loopback-browser only, but does complete headless — you
bridge the OAuth redirect by hand (start it backgrounded, relay the auth URL to
the user, then curl their pasted localhost:<port>/?code=... redirect back to
the waiting listener). The google-workspace skill has the full auth recipe
(Desktop-app client type, Internal audience, the loopback bridge) plus command
shapes (Drive, Docs, Sheets, Gmail, Calendar, Chat). For fully unattended jobs
with no user present to paste the redirect, use the service-account option.
Under a routine, the Google/gcloud token is present only if you declared its
secret name (GOOGLE_WORKSPACE_CLI_TOKEN / CLOUDSDK_AUTH_ACCESS_TOKEN) in the
routine's secrets:.
Once gws is set up, strongly suggest installing Google's official gws
skills. They live in the googleworkspace/cli repo and go deeper than the
builtin google-workspace skill — one per surface. Install the ones the user
needs (gws-shared is the common base the others build on):
bash(command="npx --yes skills add googleworkspace/cli@gws-shared -y")
bash(command="npx --yes skills add googleworkspace/cli@gws-gmail -y")
# also: gws-drive, gws-docs, gws-docs-write, gws-sheets, gws-calendar,
# gws-events, gws-chat-sendThe Skills CLI stages each under .agents/skills/<skill>/, which Horizon
auto-discovers — just load_skill(action="reload"), no move needed (see the
find-skills skill for details). (npx --yes skills find gws lists the
current set with install counts.)
gcloudInstall under ~/.local (slim — don't add extra components) and symlink the
entrypoints onto PATH:
bash(command='mkdir -p ~/.local/bin && cd ~/.local && \
curl -fsSLo gcloud.tgz "https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-cli-linux-x86_64.tar.gz" && \
tar -xzf gcloud.tgz && rm gcloud.tgz && \
./google-cloud-sdk/install.sh --quiet --usage-reporting=false --path-update=false && \
ln -sf ~/.local/google-cloud-sdk/bin/gcloud ~/.local/google-cloud-sdk/bin/gsutil ~/.local/google-cloud-sdk/bin/bq ~/.local/bin/')No durable gcloud credentials are kept in the sandbox. GCP access is via the
short-lived token-as-secret path below, which persists nothing — no refresh
token, no ADC file, no key. (You may set CLOUDSDK_CONFIG=/workspace/lha/config/gcloud
as a scratch config dir, but there is no login state to persist across upgrades.)
Verify:
bash(command="gcloud --version")Logging in deposits credentials the agent can use, in a sandbox with open
outbound internet egress. An injected agent could read the user's GCP data,
bq extract / gsutil cp it to a foreign bucket, mint a service-account key,
or grant external IAM — all over *.googleapis.com. Layer A (exfil_guard) still
gates credential/secret exfil and uploads to non-allowlisted hosts, and still
blocks the GCP metadata server; it has no GCP-action awareness (it can't see
what a gcloud call does). The real control is credential minimization:
cloud-platform
(everything the user's IAM allows) is a broad, high-trust default — not a free one.The lowest-trust, least-friction path, and the only one we use (works for corp / org-restricted accounts too): the user mints a short-lived access token on their own machine (already gcloud-authed there, so the org's device/CAA policy is satisfied) and hands it to the agent as a secret. Nothing durable lands in the sandbox, and the token self-expires in ~1 hour.
gcloud auth print-access-tokenCLOUDSDK_AUTH_ACCESS_TOKEN in the
/lha/secrets UI — never pasted into chat (it's a live credential).bash command, and
gcloud reads CLOUDSDK_AUTH_ACCESS_TOKEN from the environment — so the agent
just runs commands, no login / ADC / OAuth client at all:bash(command="export CLOUDSDK_CONFIG=/workspace/lha/config/gcloud && gcloud projects list")gsutil and bq read the same env token. Don't name the token in a
curl/wget (-H "Authorization: Bearer $CLOUDSDK_AUTH_ACCESS_TOKEN"): the
exfil guard hard-blocks a network command that references a secret env var (by
design — it stops the agent exfiltrating the token). Use the gcloud-family CLIs,
which pick it up from the environment without naming it; a raw REST call that
must carry the token needs a /grant.Why this is the default:
/workspace to reuse.Account restricted, no custom OAuth client, no remote-bootstrap.agents-cli — call a remote agent (A2A / ADK)To hand a task to another agent deployed remotely (Cloud Run, Vertex Agent
Runtime, or any A2A endpoint), shell out to agents-cli — no in-process wiring
needed. This is the outbound counterpart to in-process subagent(): the remote
agent is its own service with its own state; you just send a prompt over HTTP.
Install (one-time; uv is already in the sandbox — it installs to ~/.local/bin):
bash(command="command -v agents-cli || uv tool install google-agents-cli")
bash(command="agents-cli --version")(Install pulls from wherever google-agents-cli is published — if the sandbox
can't reach that index, that's the same egress dependency as the Node/gcloud
downloads.)
Invoke:
bash(command='agents-cli run "summarize this repo" --url https://my-agent-xxxx.run.app --mode a2a')--mode a2a for the A2A protocol; --mode adk for ADK SSE (/run_sse, or
:streamQuery on Agent Runtime). --mode is required with --url.--app-name <name> to target a specific agent at that endpoint.--session-id <id> to continue a conversation; -v for full JSON events.process(action='spawn', command=...)
and poll via the process tool (fire-and-forget).Auth — usually automatic. agents-cli auto-detects Google credentials from
the sandbox identity: an ID token (audience = service URL) for Cloud Run, an
access token for Vertex AI / Agent Runtime. For this to yield a usable token,
the sandbox/Cloud Run service account needs the right IAM on the target
(roles/run.invoker for Cloud Run; Vertex perms for Agent Runtime) — a 401/403
is almost always missing IAM, not a CLI problem.
User-delegated auth (call as the user): pass the token explicitly, which overrides auto-detect:
bash(command='agents-cli run "..." --url https://... --mode a2a -H "Authorization: Bearer $USER_TOKEN"')Source the token from the secrets / headless-auth subsystem (never inline a raw secret into chat).
--url is a thin client — it loads no local skills (the remote agent's skills
are its own concern). If you need agents-cli's broader toolchain (scaffold,
deploy, eval, observability, publish, workflow), install those skills on demand
via the find-skills skill.
mcp-cli — use tools exposed by an MCP serverTo call tools served by an MCP server (GitHub, filesystem, databases,
third-party APIs) from the sandbox. This is the client side — using external
MCP servers via bash, not running one. (Auth is static token only —
inject the server's bearer via ${VAR} headers, below; there is no OAuth/consent
flow. For GCP, use the token-as-secret path in the gcloud section, not MCP.)
Install — install.sh downloads a checksum-verified, self-contained prebuilt
binary (mcp-cli-linux-x64, ~100 MB) to ~/.local/bin/mcp-cli. It's compiled
with Bun but needs no Bun/Node at install or runtime — it's standalone.
Don't pipe-to-bash. curl … | bash is blocked by the tool policy (piping
remote content to a shell). Download the script, then run it from a file:
bash(command="command -v mcp-cli || (curl -fsSLo /tmp/mcp_install.sh https://raw.githubusercontent.com/philschmid/mcp-cli/main/install.sh && bash /tmp/mcp_install.sh)")
bash(command="mcp-cli --version")(Optionally read('/tmp/mcp_install.sh') first — it just fetches the latest
release binary and verifies its SHA256.) It installs to ~/.local/bin.
Configure servers — this is the real onboarding work. mcp-cli is
config-driven: it reads mcp_servers.json. Keep it on /workspace (config is a
data file — it migrates) and point mcp-cli at it with MCP_CONFIG_PATH (its
highest-priority resolver); the default ~/.config/mcp/… is not migrated:
export MCP_CONFIG_PATH=/workspace/lha/config/mcp_servers.jsonWrite that file (Claude-Desktop / Gemini / VS-Code compatible):
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"]
},
"remote-api": {
"url": "https://mcp.example.com",
"headers": { "Authorization": "Bearer ${MCP_TOKEN}" }
}
}
}command + args the sandbox can spawn (install the server
too, e.g. via npx/uvx).url (+ headers).${VAR} in headers is substituted from the environment at config
load (missing var errors unless MCP_STRICT_ENV=false). Source that token from
the secrets subsystem (env-injection) — never inline a raw secret.Use (or install mcp-cli's own usage skill via find-skills for the full
reference):
bash(command="mcp-cli") # list servers + tools
bash(command="mcp-cli info filesystem read_file") # tool schema
bash(command="mcp-cli call filesystem read_file '{\"path\": \"./README.md\"}'")Use call to invoke and info to inspect — mcp-cli <server> <tool> directly
is ambiguous and errors.
| Symptom | Cause / fix |
|---|---|
| any tool "command not found" after a runtime upgrade | binaries live in $HOME and aren't migrated — reinstall per this skill (the command -v check does this) |
node/gcloud: command not found after install | the ln -sf … ~/.local/bin/ symlink step was skipped; re-run it (~/.local/bin is on PATH, the versioned/SDK bin dir isn't) |
tar: ... cannot exec xz | downloaded .tar.xz; use the .tar.gz build instead |
gws asks to log in again after an upgrade | its credentials were written under $HOME (not migrated); set GOOGLE_WORKSPACE_CLI_CONFIG_DIR to the /workspace/lha/config/* path on every call (gcloud keeps no persisted login — re-add the token secret) |
gws login token not saved / no keyring | set GOOGLE_WORKSPACE_CLI_KEYRING_BACKEND=file (alongside the config-dir export) |
gws auth status says auth_method: none but reads work | expected when GOOGLE_WORKSPACE_CLI_TOKEN is the source — auth status doesn't reflect the env token. Confirm with a real read, not auth status; don't start a login dance |
gws auth login hangs on the listener | expected headless — bridge the redirect (see google-workspace skill) or use a service account if no user is present |
403 access_denied "Account restricted" | Context-Aware Access on the OAuth client — don't fight it. Use the token-as-secret path: user runs gcloud auth print-access-token locally and stores it as the secret CLOUDSDK_AUTH_ACCESS_TOKEN |
| network command blocked: "reads a credential path or secret env var" | Don't name $CLOUDSDK_AUTH_ACCESS_TOKEN (or any *_TOKEN/*_KEY) in a curl/wget — the exfil guard hard-blocks it. Let gcloud/gsutil/bq read the token from the env instead; a raw REST call needs a /grant |
| Unattended job has no GCP token | the CLOUDSDK_AUTH_ACCESS_TOKEN secret is missing or expired; surface "needs a fresh token" and stop — don't loop |
agents-cli: command not found | uv tool install google-agents-cli (uv is already in the sandbox) |
remote agents-cli run --url 401/403 | missing IAM on the target (roles/run.invoker / Vertex perms), not a CLI bug |
--mode is required when using --url | add --mode a2a (or --mode adk) to the remote call |
mcp-cli: command not found | download install.sh then bash the file (don't | bash — policy blocks it); installs to ~/.local/bin |
mcp-cli AMBIGUOUS_COMMAND | use mcp-cli call/info <server> <tool>, not mcp-cli <server> <tool> |
mcp-cli ${VAR} missing at config load | export the token (from the secrets subsystem) or set MCP_STRICT_ENV=false |
© google, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools of google/adk-recipes.
Open the folder on GitHubat commit fa9bdde
Bootstrap Google Tools 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 |
|---|---|---|---|---|---|---|
| Bootstrap Google Tools this skillgoogle/adk-recipes | 10k | — | ~5k | Automated safety check: Warn | Apache-2.0 | |
| Gwskv0906/pm-kit | 138 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Google Workspace CLIhoodini/ai-agents-skills | 282 | — | ~10k | Automated safety check: Notes | None | |
| Managing Google Workspacetaylorwilsdon/google_workspace_mcp | 3.3k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Gmail Query Syntaxprovos/ironcurtain | 613 | — | ~971 | Automated safety check: Pass | Apache-2.0 | |
| Gmailsanjay3290/ai-skills | 430 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 |
kv0906/pm-kit
This skill should be used when the user asks to "set up gws", "install Google Workspace CLI", "connect Gmail to Claude", "manage Google Drive from terminal", "send email from CLI", "check my…
hoodini/ai-agents-skills
Interact with all Google Workspace APIs via the gws CLI. An agent skill from hoodini/ai-agents-skills.
taylorwilsdon/google_workspace_mcp
Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search).
provos/ironcurtain
Reference for Gmail's search query syntax — operators like is:sent, newerthan:, from:, has:attachment, label:, and how they compose.
sanjay3290/ai-skills
Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels.
swarmclawai/swarmclaw
Use Google Workspace CLI (gws) for Drive, Docs, Sheets, Gmail, Calendar, Chat, and related Workspace API tasks.
google/adk-recipes
Builds a retail product search agent on Google Cloud, from catalog ingestion into BigQuery and Vector Search to ADK scaffolding, evaluation and Cloud Run deployment.
google/adk-recipes
Brings a Python recipe's pyproject.toml in line with the repo's CI rules, either as a read-only dry run or by rewriting the file while keeping comments.
google/adk-recipes
Generates a minimal tests/test_runnability.py for a Python agent recipe that imports the agent module and checks root_agent, adding only the mocks and env vars it needs.
google/adk-recipes
Sets up a virtual try-on agent on Google Cloud that generates image and catwalk-video try-ons with Gemini, from first setup through local testing.
google/adk-recipes
Creates a new Python recipe for the ADK recipes repository by running a scaffold script that copies template files, after confirming the output directory and recipe name.
google/adk-recipes
Reviews a GitHub pull request and drafts a small set of inline comments in a human reviewing voice, each checkable from the line it points at, then posts them after approval.
Categories
Install/auth CLIs the sandbox lacks - gws (Drive, Gmail, Sheets, Calendar), gcloud, agents-cli, mcp-cli (MCP servers). Bootstrap Google Tools is an agent skill from google/adk-recipes, published by the product's own GitHub organization. Install/auth CLIs the sandbox lacks - gws (Drive, Gmail, Sheets, Calendar), gcloud, agents-cli, mcp-cli (MCP servers).
Bootstrap Google Tools fits situations like: tasks that involve MCP servers; tasks that involve Email management; tasks that involve Cloud office suites.
Run `npx skills add google/adk-recipes --skill bootstrap-google-tools -a claude-code`. Or copy the skill folder (core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools in google/adk-recipes) into .claude/skills/bootstrap-google-tools in your project. Claude Code loads it when a task matches its description.
Run `npx skills add google/adk-recipes --skill bootstrap-google-tools -a codex`. Or copy the skill folder (core/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools in google/adk-recipes) into .agents/skills/bootstrap-google-tools in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add google/adk-recipes --skill bootstrap-google-tools -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bootstrap-google-tools, .gemini/skills/bootstrap-google-tools, .github/skills/bootstrap-google-tools and .opencode/skills/bootstrap-google-tools in your project.
Going by SKILL.md and its folder, Bootstrap Google Tools needs the command-line tools its instructions call (curl, gcloud, bash, uv, npm and npx) and credentials named CLOUDSDK_AUTH_ACCESS_TOKEN, GOOGLE_WORKSPACE_CLI_TOKEN, GOOGLE_WORKSPACE_CLI_CLIENT_SECRET and GOOGLE_APPLICATION_CREDENTIALS. Our summary lists: Node.js; A credential in GOOGLE_WORKSPACE_CLI_TOKEN; A credential in GOOGLE_WORKSPACE_CLI_CLIENT_SECRET.
SKILL.md names 3 domains. In commands or code: nodejs.org, dl.google.com and raw.githubusercontent.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md flagged 1 warning(s): pipes a downloaded script straight into a shell. Read the flagged lines before installing; the check is not a guarantee either way.
Bootstrap Google Tools is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Bootstrap Google Tools: Gws (kv0906/pm-kit, 138 stars), Google Workspace CLI (hoodini/ai-agents-skills, 282 stars), Managing Google Workspace (taylorwilsdon/google_workspace_mcp, 3.3k stars) and Gmail Query Syntax (provos/ironcurtain, 613 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
google (a GitHub organization, an official publisher) maintains it in google/adk-recipes, which has 10,419 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 5, 2026.
Source: google/adk-recipes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.