- name
SKILL.md
Файл навыка остаётся в репозитории издателя.
Вставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add phuryn/product-engineering --skill grok-agents -a cursor -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add phuryn/product-engineering --skill grok-agents -a claude-code -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add phuryn/product-engineering --skill grok-agents -a codex -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add phuryn/product-engineering --skill grok-agents -a grok -yОтправьте скопированное сообщение в чат Grok Bot. Бот загрузит этот SKILL.md с GitHub и добавит его к навыкам, общим для всех ваших ботов.
Install this skill: https://github.com/phuryn/product-engineering/tree/HEAD/agent-teams/skills/grok-agentsОт издателя
Run headless Grok as a peer, builder or fresh reviewer. Any agent can get a full Grok session: tools, repository instructions where Grok reads them, and a conversation that can continue. It is a partner from another model family, with the same standing as its caller. A peer argues a decision through, a builder takes a stage, and a reviewer has never seen the build. This skill covers briefs, modes and commands.
Everything here was read from grok --help and run on Grok CLI 1.0.70, 2026-11-02, unless stated otherwise. The CLI changes often; check grok --help before relying on a flag.
Apply delegation for the full discipline of working with a partner. These rules must hold even when this folder is copied alone.
test-harness § The gate and independent-review § When.delegation.Every mode shares four rules, each from a run that went wrong:
--prompt-file <brief>. Never use inline -p "…". A long inline prompt trips the calling agent's permission classifier and the call is refused.--cwd <repo> and close stdin on every call. This selects the repository you mean. Use < /dev/null, because open stdin waits for input forever. Bare grok without a prompt flag opens the interactive screen and hangs without output.--output-format json returns one object with text, stopReason, sessionId, num_turns and usage, which suits a calling agent. plain returns text alone.--reasoning-effort xhigh for anything needing judgement; the CLI's default is lower. grok models lists models and the default, grok-4.7 on 2026-11-02; -m <id> pins one.Name the peer session and repeat its flags when resuming.
SID=$(python -c "import uuid; print(uuid.uuid4())") # name the session yourself
grok --prompt-file "$S/turn-1.md" --cwd <repo> --session-id "$SID" \
--tools read_file,grep,list_dir --disallowed-tools search_tool,use_tool \
--deny MCPTool --deny Bash --deny Edit --deny Write --disable-web-search \
--always-approve --reasoning-effort xhigh --output-format json < /dev/null > "$S/turn-1.json"
# the next turn continues it: every flag again, --resume in place of --session-id
grok --resume "$SID" --prompt-file "$S/turn-2.md" --cwd <repo> \
--tools read_file,grep,list_dir --disallowed-tools search_tool,use_tool \
--deny MCPTool --deny Bash --deny Edit --deny Write --disable-web-search \
--always-approve --reasoning-effort xhigh --output-format json < /dev/null > "$S/turn-2.json"
--session-id <uuid> and continue with --resume <uuid>. Resume keeps its context: a word given in the first turn came back from the second (observed 2026-11-02). Save the id in a file beside the brief. Don't rely on -c: it continues whichever session ran most recently in the directory.--always-approve is what lets it read at all. Without it, Grok can't approve its own reads and exits 0 after a sentence of preamble that reads like an answer. With the read-only allowlist above, approving everything approves only reading.grok inspect lists them. This suits a peer and is why the reviewer turns it off.Give a builder its own worktree and exclude operational changes. Permit development suites within the delegation boundaries; keep production credentials with the session agent.
grok --prompt-file "$S/stage-brief.md" --cwd <worktree> --session-id "$SID" \
--always-approve --deny MCPTool --disable-web-search \
--reasoning-effort xhigh --output-format json < /dev/null > "$S/build-1.json"
--always-approve approves every tool call, the shell included. Use a git worktree of its own, never the tree you edit. The brief excludes operational changes: no pushes, deploys, applied migrations, provider-setting or secret changes, or production-credential reads (§ The partner discipline, 6). Development suites run within the brief's boundaries. --deny MCPTool blocks the machine's connected MCP servers, including a database's.git status and the named files. A run unable to write returns a reasoned report that reads exactly like one that did.--sandbox <profile> as a write boundary. It enforces only on supporting platforms; on Windows a sandboxed run still created a file (observed 2026-10-10).grok --help 1.0.70. It had not been run end to end when written on 2026-11-02, because the calling agent's classifier refused a fully approved Grok session.Apply independent-review for scope, brief, triage and the stopping rule. Its wrapper runs Grok this way by default. The bare call below explains the flags. The wrapper also sets the turn cap and writes the subject, range's log and diffs to a file. The reviewer has no shell and reads that file.
GROK_MEMORY=0 GROK_MANAGED_MCPS_ENABLED=false GROK_MANAGED_MCP_GATEWAY_TOOLS_ENABLED=false \
GROK_CODEX_SESSIONS_ENABLED=false <and GROK_{CLAUDE,CURSOR}_{AGENTS,RULES,SKILLS,HOOKS,MCPS,SESSIONS}_ENABLED=false> \
grok --prompt-file "$S/review-NNN-brief.md" --cwd <repo> \
--reasoning-effort xhigh \
--tools read_file,grep,list_dir --disallowed-tools search_tool,use_tool \
--deny MCPTool --deny Bash --deny Edit --deny Write --disable-web-search \
--always-approve \
--output-format plain < /dev/null > "$S/review-NNN.md" 2>&1
Every part is load-bearing:
grok inspect --json, 1.0.70, 2026-10-30: all 13 cells off).grok inspect --json with the same variables to list them. In a trusted folder, this includes the project's instruction files and even a gitignored CLAUDE.local.md.--always-approve and reject rounds with short output. Without approval, the round exits 0 after a sentence of preamble that reads as "found nothing". Length is the only tell; a genuinely empty round still argues its way there over paragraphs.--tools read_file,grep,list_dir as the review's write boundary. This allowlist prevents editing the tree being scored. Not --sandbox read-only, and not a denylist such as --disallowed-tools edit,write, which leaves shell and edit access. Observed on Windows, 2026-10-10: those two flags together still allowed file creation; the allowlist did not. Without a shell the reviewer cannot run git, so write the subject to disk first.--disallowed-tools search_tool,use_tool, the --deny rules and --disable-web-search. --tools covers built-ins only; MCP meta-tools and every connected server otherwise remain available. --disallowed-tools wins over --tools; a deny rule wins over --always-approve. Asked to write, call MCP tools and run a shell, a round with these flags did none of them (observed 2026-10-10).--resume or --fork-session the thread that built the code.grok login --device-auth to sign in without a local browser. The CLI prints a link and code; the account owner approves on any device. An agent can start it and relay the link and code to an owner away from the machine. Never paste the resulting credentials anywhere.402 usage balance exhausted and stops (observed 2026-10-31). In a review round, the independent-review wrapper exits 3 and prints the same round for the fallback reviewer. In peer or builder mode, wait for reset or do the work yourself, and say so.grok usage prints a session's persisted token and cost usage; grok sessions list lists recent sessions and ids.Each rule's origin, the case that taught it, is in receipts.md beside this file; read it when a rule's edge is unclear.
The session started with only your brief and used its mode's flags; you read its exit code and output from the run itself. A resumed turn named its session, and anything built was on disk and reviewed before it was trusted.
Apply independent-review for the review loop and its wrapper. Use claude-agents and codex-agents to drive those CLIs the same way. Apply delegation to brief and verify any delegate.
'Ask Grok', 'have Grok build or review this': drive the Grok CLI headless from another agent as a peer, builder or fresh reviewer.
---name: grok-agentsdescription: 'Ask Grok', 'have Grok build or review this': drive the Grok CLI headless from another agent as a peer…---# agent-teams/skills/grok-agents/SKILL.mdFAQ
Скачайте agent-teams/skills/grok-agents/SKILL.md у издателя или скопируйте путь и откройте репозиторий. PlugMCP только показывает навык в каталоге и не хранит файл.
Издатель хранит его в https://github.com/phuryn/product-engineering.
Claude, Cursor, Codex и Grok Build могут читать SKILL.md, который вы добавляете из репозитория издателя. Grok Bot устанавливает его, когда вы отправляете в чат ссылку на папку навыка на GitHub.