agentleFS
p10ns11yp10ns11y/skills/grok-host-prep/SKILL.md

grok-host-prep

Skill2 starsChanged 40 days agoMITView on GitHub

One-time (re-runnable) host prep for Grok Build: check binaries, lsp.json, [features] lsp_tools, MCP command existence, and efficiency knobs. Use when setting up a machine, enabling LSP, or a Feed harness_gap is mcp / permissions / 8192. Triggers: grok-host-prep, /grok-host-prep, prepare machine, setup LSP, tweak grok host, host prep.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the script (check first):

    line 31
  2. Distinctive:

    If the report is what you want on disk:

    line 37
  3. Very specific:

    Do not treat permission_mode = always-approve as a prep win (EVA forbids it).

    line 73
  4. Very specific:

    No secrets printed; no grok nested

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

grok-host-prep

Load rule: This skill owns host checks + safe apply. Prompt routing stays in control-feeder. Do not paste MCP env/secrets. Do not nest grok.

Check  : default — report OK / WARN / MISS
Apply  : write missing lsp.json servers; append [features] lsp_tools if absent
Install: optional LSPs only with --install

When to use

UseSkip
New host, missing lsp tool, Feed harness_gapMid-turn code edit
Want rust-analyzer / clangd / tsserver wiredChanging models or permission_mode
MCP command might be missing from PATHDumping or editing MCP secrets

Steps

  1. Run the script (check first):
bash ~/.grok/skills/grok-host-prep/scripts/prepare.sh --check
  1. If the report is what you want on disk:
bash ~/.grok/skills/grok-host-prep/scripts/prepare.sh --apply
  1. Optional LSPs (only if you want them globally):
bash ~/.grok/skills/grok-host-prep/scripts/prepare.sh --apply --install
  1. New Grok session (or restart) so lsp.json + lsp_tools load.
  2. Session flags the script will not write into your shell rc — set if you want the extra tools:
FlagEffect
GROK_LSP_TOOLS=1same as [features] lsp_tools = true
GROK_WEB_FETCH=1enable web_fetch (off by default)
GROK_SUBAGENTS=1enable task / subagents
GROK_MEMORY=1expose memory_search / memory_get (config [memory] enabled is separate)

What actually makes this host faster

Owned by the harness, not a second graph:

KnobWhy
~/.grok/lsp.json + lsp_toolsgoToDefinition / references / hover instead of fat read_file
codebase_indexing (default true)code-graph context; leave on
output_byte_limit ≥ 8192do not lower (repo AGENTS.md)
rg + rust-analyzer + clangd on PATHthis tree is Rust + some C
MCP command existsdead [mcp_servers.*] wastes startup; project .grok/config.toml replaces a name entirely
Official grok = ~/.grok/bin/grokleftover ~/.local/bin/grok can steal PATH

Do not treat permission_mode = always-approve as a prep win (EVA forbids it).

Done when

  • Script printed a full check table
  • --apply (if requested) wrote only missing LSP servers and lsp_tools = true
  • No secrets printed; no grok nested

Do not

  • Rewrite config.toml wholesale or print [mcp_servers.*.env]
  • Lower output_byte_limit
  • --install without the user asking for extra LSPs
  • Invent a second agent OS / extra graph crate

Related

Skills: control-feeder (Feed harness_gap) · eva-emptiness (always-approve is not a prep win)
Plugin: eva-emptiness (auth tether). Official grok binary + bundled/ after login — not this script.

Notes in grok-build intelli-arch-designs/:

NoteUse from this skill
harness-feed-filter.mdharness knobs (perms, 8192, AGENTS.md, MCP) ≠ graph
harness-economy-model.mdtools dominate $; do not lower bash below 8192 or polish skill-list
harness-learning-cost-roadmap.mdofficial grok; measure with tool-mix-observe; no second OS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.