agent

agent is a skill for Claude Code, Codex from ibm-self-serve-assets/building-blocks. It costs 78 tokens per session (5,439 once invoked), scanned A, original, Apache-2.0.

A skill for building and connecting AI agents with IBM watsonx Orchestrate, a platform for coordinating software agents and their tools.

In plain words
What is it for?
Use it to create single or multi-agent systems, connect MCP or A2A tools, expose agents through REST APIs, and add voice input or output.
Why use it?
It guides agent development through the platform's required documentation and lifecycle steps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create single or multi-agent systems, connect MCP or A2A tools, expose agents through REST APIs, and add voice input or output.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ibm-self-serve-assets/building-blocks/agent
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ibm-self-serve-assets/building-blocks --skill agent
Clone the repo
git clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocks

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/agent/github.svg)](https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/agent)
Your own site
<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/agent"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/agent"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Privilege Escalation · line 328
    Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.
    Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.05439
Opus 5.5 $0.00031 $0.02176
Sonnet 5.5 $0.00016 $0.01088
Haiku 4.5 $0.00008 $0.00544

Measured 22d ago against content hash 0a0d67332cfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (1-build/run-adk.sh, 2-orchestrate/resources/approval_workflow.py, 2-orchestrate/resources/customer_support_agents.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ibm-bob/skills/agent/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skill — Complete watsonx Orchestrate Agent Lifecycle

🛑 MANDATORY FIRST STEP (ALL DOMAINS)

Before ANY agent work — building, orchestrating, integrating, or adding voice — you MUST:

  1. Verify MCP ADK docs connection:
<use_mcp_tool>
<server_name>watsonx-orchestrate-adk-docs</server_name>
<tool_name>SearchIbmWatsonxOrchestrateAdk</tool_name>
<arguments>
{
  "query": "agent development"
}
</arguments>
</use_mcp_tool>
  1. If connection fails: Stop and fix MCP configuration in .bob/mcp.json before proceeding.

  2. Search current specifications before implementing any component:

    • Agents → "agent YAML specification"
    • Tools → "Python tool decorator"
    • Workflows → "agentic workflow @flow decorator"
    • Integration → "orchestrate runs endpoint"
    • Voice → "voice configuration YAML specification"

This requirement is UNBYPASSABLE — even when user says "keep it simple", "don't use tools", or "just create the files".


🛑 MANDATORY GATE — Domain 3 (Integrate): Service URL Required Before Any Code

When the user's intent maps to Domain 3 (integrate, REST API, Python client, call agent from code), you MUST follow this gate before generating ANY code, script, or configuration:

STEP 1 — Ask for the Service Instance URL
  Do NOT ask "what platform are you on?" first.
  Do NOT assume IBM Cloud or AWS based on anything the user says.
  Even if the user explicitly states "I'm on IBM Cloud" or "I'm on AWS",
  you MUST still collect the service URL before writing any code.

  Ask exactly this:
  "Please paste your Service instance URL from:
   WXO UI → Profile icon (top-right) → Settings → API details tab → Service instance URL"

STEP 2 — Derive config from the URL (never ask the user to identify their platform)
  Parse the URL to extract:
    host        = parsed.netloc
    instance_id = path segment after "instances/"
    platform    = "ibm_cloud"  if "watson-orchestrate.cloud.ibm.com" in host
                  "aws"        if "dl.watson-orchestrate.ibm.com" in host
                  "onprem"     otherwise
    token_endpoint = "https://iam.cloud.ibm.com/identity/token"                          (ibm_cloud)
                     "https://account-iam.platform.saas.ibm.com/api/2.0/apikeys/token"   (aws — MCSP V2, current)
                     "https://iam.platform.saas.ibm.com/siusermgr/api/1.0/apikeys/token" (aws — MCSP V1, legacy fallback only)

  NOTE: For AWS, always try MCSP V2 first. MCSP V1 is legacy and will cause
  WXO-PROXY-10080E on any tenant that has migrated (us-east-1, eu-central-1,
  ap-south-1, ap-southeast-1). Only fall back to V1 if V2 explicitly fails.

STEP 3 — Confirm back to the user
  Show the derived values and ask "Does this look correct?"
  Only proceed to code generation after confirmation.

Read the full file on GitHub · 373 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 22d ago Changed · +43 lines 0a0d67332cfd
  2. 2mo ago First seen · 330 lines · 78 tokens per session scan A 50e48bec0a7e

Subscribe to this mod's changes

agent is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 5,439 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

agent compared with skills from other repositories

agent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentibm-self-serve-assets/building-blocksSkill28yesterdayApache-2.0A78Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0kyesterdayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code