agentleFS
kentcdoddskentcdodds/kcd-skills/skills/use-kody/SKILL.md

use-kody

Skill64 starsChanged 25 days agoMITView on GitHub

Default to Kody (MCP search/execute/api and the @kodycodes/cli) for every task when Kody is connected. Use at the start of any task where the Kody MCP is available, or whenever you are about to reach for an ad-hoc alternative (raw scripts, other APIs, browser) for something Kody might cover.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not ask a human for a token.

    line 18
  2. Very specific:

    Run the returned cli_command (it already includes lifetime flags), which is equivalent to:

    line 21
  3. Very specific:

    Never paste a kody_at_… into chat.

    line 29
  4. Very specific:

    Run through execute or the local CLI.

    line 38

≈ “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

Use Kody for everything

Load this whenever the Kody MCP tools (search, execute, api) are available, or right before you reach for a one-off script, another API, or the browser for work Kody might already cover.

CLI bootstrap (agents on MCP)

Do not ask a human for a token. Call MCP api with operationId: "cliCredentialBootstrap" and params: { "lifetime": "short" } (or MCP execute with kody.cliCredentialBootstrap({ lifetime: "short" })). Run the returned cli_command (it already includes lifetime flags), which is equivalent to:

npx @kodycodes/cli auth bootstrap --code 'kody_bc_…' --lifetime short
npx @kodycodes/cli whoami

Never paste a kody_at_… into chat. Prefer npx @kodycodes/cli execute --local when Node ≥22 (prefer-local-kody-execute, Local CLI execute). If a step is unclear, search({ entity: "guide:local_execute" }) for current setup.

Default path

  1. search first (packages, integrations, capabilities, docs).
  2. Run through execute or the local CLI. Prefer existing packages over rewriting helpers.
  3. Persist reusable work as a Kody package (search({ entity: "guide:package_lifecycle" })), not a one-off script.
  4. Fall back to other tools only when Kody genuinely has nothing for the job.

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.