AgentStack
SKILL verified MIT Self-run

Crew Config

skill-d3x293-code-crew-crew-config · by d3x293

Manages CodeCrew configuration. Allows users to customize default mode, model tiers, agent activation, token budgets, and auto-index settings without editing JSON files.

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-d3x293-code-crew-crew-config

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Crew Config? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Crew Config - User Configuration Manager

Reads and writes .claude/crew-config.json to customize CodeCrew behavior.

When to Activate

  • User runs /crew config show|set|reset
  • Other skills check for config overrides at startup

Config File

Location: .claude/crew-config.json (created on first set command)

Default values (used when file doesn't exist):

{
  "defaultMode": "full",
  "modelOverrides": {},
  "agentOverrides": {},
  "tokenBudgets": {
    "opus": 3000,
    "sonnet": 2000,
    "sonnet-planner": 2500,
    "haiku": 800
  },
  "autoIndex": true,
  "historyLimit": 50
}

Subcommands

show — Display Current Configuration

  1. Read .claude/crew-config.json (if exists, otherwise show defaults)
  2. Display:
Config: Mode={full|lite} | Auto-Index={on|off} | History={count}
Budgets: Opus {t}tk/{s}sk | Sonnet {t}tk/{s}sk | Sonnet-planner {t}tk/{s}sk | Haiku {t}tk/{s}sk
Model overrides: {none | list}
Agent overrides: {none | list}

set — Update a Setting

Supported keys:

| Key | Values | Example | |-----|--------|---------| | mode | full, lite | /crew config set mode lite | | auto-index | true, false | /crew config set auto-index false | | history-limit | number | /crew config set history-limit 100 | | agent..model | opus, sonnet, haiku | /crew config set agent.senior-dev.model opus | | agent..active | true, false | /crew config set agent.security-analyst.active true | | budget. | number (tokens) | /crew config set budget.sonnet 2500 |

Process:

  1. Read existing .claude/crew-config.json (or start with defaults)
  2. Validate the key and value
  3. Apply the change
  4. Write back to .claude/crew-config.json
  5. Confirm: "Set {key} = {value}"

Validation rules:

  • mode: must be full or lite
  • agent..model: agent must exist in crew-team.json
  • budget.: must be a positive number, max 5000
  • Warn if user sets a Haiku agent to Opus (expensive, possible but discouraged)

reset — Restore Defaults

  1. Delete .claude/crew-config.json
  2. Confirm: "Configuration reset to defaults"

Integration with Other Skills

Other skills should check for config overrides at startup:

1. Check if .claude/crew-config.json exists
2. If yes, read it and apply overrides:
   - task-router / lite-router: check defaultMode to decide which router to use
   - skill-injector: check tokenBudgets for custom limits
   - execution-orchestrator: check autoIndex, modelOverrides
3. If no, use built-in defaults

This check adds ~50 tokens per skill invocation but enables full user customization.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.