agentleFS
tjg37tjg37/ironclaw/.claude/skills/configure/SKILL.md

configure

Skill1 starsChanged 7 months agoMITView on GitHub

Change IronClaw agent configuration — persona, boundaries, and MCP connections

  • Reads credentials

45 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use calendar, status and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jacobraskSkill

    calendar

    Interact with Apple Calendar via AppleScript. Use when the user asks to check calendar, view events, create events, manage schedule, find free time, or list calendars. Triggers include "my calendar", "my schedule", "calendar events", "create event", "add to calendar", "what's on my calendar", "free time", "available slots", "upcoming events", "today's events". Requires macOS with Calendar.app.

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 45 edited versions we read keep these.

  • 9

    Distinctive

    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:

    If there is more than one agent, use AskUserQuestion to ask which agent to configure.

    line 27
  2. Distinctive:

    If there is only one agent (the default), skip this step and configure it directly.

    line 29
  3. Distinctive:

    Use AskUserQuestion with these options:

    line 48
  4. Distinctive:

    IMPORTANT: Use the AskUserQuestion tool for ALL selections.

    line 57
  5. Distinctive:

    Use AskUserQuestion (single select) with options:

    line 61
  6. Distinctive:

    If they select "Other", show remaining options:

    line 67
  7. Distinctive:

    Use AskUserQuestion (multi-select) with the question "Which capabilities should be ENABLED?":

    line 77
  8. Distinctive:

    Read system files outside project

    line 81
  9. Distinctive:

    Use AskUserQuestion (multi-select) with options:

    line 85
  10. Very specific:

    If the user selects GitHub or Sentry, check .env for the matching token.

    line 92
  11. Very specific:

    If no agents are selected, set allowedAgents to [] (empty array — no delegation allowed).

    line 100

“Common” is measured: kept by at least 6 in 10 of the 45 edited versions of this file we could read. “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

/configure — Reconfigure IronClaw Agent

Change the agent's persona, boundaries, or MCP connections without running full setup. Uses the AskUserQuestion tool for all selections — never ask the user to type numbers or free text (except for custom persona).

Step 1: Select Agent

First, list all agents to see what's available:

cd packages/shared && node --env-file=../../.env --import tsx/esm -e "
import { agentRepo } from './src/index.js';
const tenant = await agentRepo.findOrCreateDefaultTenant();
const allAgents = await agentRepo.listAgents(tenant.id);
for (const a of allAgents) {
  const cfg = a.config ?? {};
  console.log(JSON.stringify({ name: a.name, id: a.id, persona: cfg.persona ?? 'general', model: cfg.model ?? 'default' }));
}
process.exit(0);
"

If there is more than one agent, use AskUserQuestion to ask which agent to configure. Show each agent's name and persona as options.

If there is only one agent (the default), skip this step and configure it directly.

Step 2: Load Current Config

Load the selected agent's config:

cd packages/shared && node --env-file=../../.env --import tsx/esm -e "
import { agentRepo } from './src/index.js';
const config = await agentRepo.getAgentConfig('AGENT_ID');
console.log(JSON.stringify(config, null, 2));
process.exit(0);
"

Show the current config to the user as a summary.

Step 3: Ask What to Change

Use AskUserQuestion with these options:

  • Persona — change the agent's role
  • Boundaries — toggle capabilities on/off
  • MCP connections — manage integrations
  • Allowed agents — configure which agents this agent can delegate to
  • Everything — reconfigure all settings

Step 4: Present Options

IMPORTANT: Use the AskUserQuestion tool for ALL selections.

If changing Persona:

Use AskUserQuestion (single select) with options:

  • General assistant — good at everything
  • Developer assistant — code, debugging, architecture
  • Research assistant — thorough research, citations, analysis
  • Personal organizer — tasks, scheduling, reminders

If they select "Other", show remaining options:

  • Writing assistant — content creation, editing
  • Data analyst — data exploration, SQL, visualizations
  • DevOps / SRE — infrastructure, deployment, monitoring
  • Product manager — requirements, specs, user stories

They can also type a custom persona via "Other".

If changing Boundaries:

Use AskUserQuestion (multi-select) with the question "Which capabilities should be ENABLED?":

  • Run bash commands
  • Write/edit files
  • Web search
  • Read system files outside project

If changing MCP Connections:

Use AskUserQuestion (multi-select) with options:

  • Memory (built-in) — persistent long-term memory
  • GitHub — read/write GitHub issues, PRs, code. Requires GITHUB_TOKEN in .env.
  • Sentry — read Sentry issues/events. Requires SENTRY_AUTH_TOKEN in .env.
  • Slack (coming soon)
  • Google Calendar (coming soon)

If the user selects GitHub or Sentry, check .env for the matching token. If missing, tell the user the token must be added before the connection activates — IronClaw will log a warning and skip the server at runtime if the token isn't set.

If changing Allowed Agents:

First, list all other agents so the user can see what's available. Then use AskUserQuestion (multi-select) with the question "Which agents should this agent be allowed to delegate to via ask_agent/tell_agent?". List all other agents by name as options.

Important security note to show the user: When this agent delegates to another agent, the delegated agent runs with the intersection of both agents' boundaries. This means the delegated agent cannot do anything this agent can't do. For example, if this agent has allowBash: false, no delegated agent can use bash on its behalf — even if the delegated agent's own config allows it. Delegation cannot escalate permissions.

If no agents are selected, set allowedAgents to [] (empty array — no delegation allowed).

Step 5: Save Configuration

Save the updated config using the selected agent's ID:

cd packages/shared && node --env-file=../../.env --import tsx/esm -e "
import { agentRepo } from './src/index.js';
await agentRepo.updateAgentConfig('AGENT_ID', {
  persona: 'CHOSEN_PERSONA',
  customPersona: 'CUSTOM_TEXT_OR_UNDEFINED',
  boundaries: {
    allowBash: BOOL,
    allowFileWrites: BOOL,
    allowWebSearch: BOOL,
    allowSystemFiles: BOOL
  },
  mcpConnections: ['memory'],
  allowedAgents: ['AGENT_NAME_1', 'AGENT_NAME_2']
});
console.log('Config updated!');
process.exit(0);
"

Replace placeholder values with the user's actual choices. For fields that weren't changed, keep the existing values from Step 2.

Step 6: Confirm

Show the updated config summary. Remind the user to restart IronClaw for changes to take effect (config is cached for up to 60 seconds).

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.