Catalog
BerriAI/update-agent

BerriAI

update-agent

Update an existing AI agent on a live LiteLLM proxy. Ask for the agent_id and what to change (model, description, MCP servers), then call PATCH /v1/agents/{agent_id}.

v1.0LATEST
NewUpdated Oct 12, 2026

Update Agent

Update an existing AI agent on a live LiteLLM proxy.

Setup

LITELLM_BASE_URL  — e.g. https://my-proxy.example.com
LITELLM_API_KEY   — proxy admin key

Ask the user

  1. agent_id — if they don't have it, list first:
    curl -s "$BASE/v1/agents" -H "Authorization: Bearer $KEY"
    
  2. What to change — any combination of:
    • model (swap the underlying model)
    • description
    • tpm_limit / rpm_limit
    • MCP server access

Run

Use PATCH to update only the changed fields:

curl -s -X PATCH "$BASE/v1/agents/<agent_id>" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "litellm_params": {"model": "<new_model>"},
    "agent_card_params": {"description": "<new_description>"}
  }'

Output

Show the updated agent name, model, and description. Confirm the agent ID is unchanged.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

75

Quality

68

Clarity

80

Completeness

62

Summary

This skill updates an existing AI agent on a live LiteLLM proxy by collecting the agent ID and desired changes from the user, then submitting a PATCH request with those modifications. It uses curl with Bearer token authentication to call the proxy's `/v1/agents/{agent_id}` endpoint, allowing updates to model, description, rate limits, and MCP server access.

Detected Capabilities

http requestbash executioncredential usageapi authentication

Trigger Keywords

Phrases that agents use to match this skill to user intent.

update agent modellitellm proxymodify agent configchange agent descriptionagent rate limits

Risk Signals

INFO

Bearer token authentication with API key stored in environment variable

Setup section, curl command
INFO

Outbound HTTP PATCH request to external proxy service

Run section, curl -X PATCH command
WARNING

API key referenced via environment variable (LITELLM_API_KEY)

Setup section and curl headers

Referenced Domains

External domains referenced in skill content, detected by static analysis.

my-proxy.example.com

Use Cases

  • Update an agent's underlying model in a live LiteLLM deployment
  • Change an agent's description or metadata without recreating it
  • Adjust rate limits (TPM/RPM) for an existing agent
  • Modify an agent's MCP server access permissions
  • List available agents to find the correct agent_id for updates

Quality Notes

  • Skill clearly defines setup prerequisites (LITELLM_BASE_URL, LITELLM_API_KEY) with example values
  • Step-by-step workflow (ask user, run command, show output) is well-organized and easy to follow
  • Includes helper command to list agents if user doesn't know agent_id — good UX
  • JSON payload structure is clearly documented with placeholders for dynamic values
  • Output expectations are explicit (show agent name, model, description, confirm unchanged ID)
  • No error handling documented — skill does not describe what to do if agent is not found, PATCH fails, or authentication is denied
  • No validation guidance — skill does not explain how user should verify the update succeeded
  • Missing documentation on required JSON structure for MCP server updates — example only shows model and description
  • No mention of required permissions (does user need specific admin scopes?) or potential failure modes
Model: claude-haiku-4-5-20251001Analyzed: Oct 12, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use BerriAI/update-agent in your dev environment

Command Palette

Search for a command to run...