agent-ops

agent-ops is a skill for Claude Code, Codex from ibm-self-serve-assets/building-blocks. It costs 138 tokens per session (5,285 once invoked), scanned A, original, Apache-2.0.

A toolkit for evaluating, attacking, and observing watsonx Orchestrate agents, IBM’s platform for building and running AI agents, in its local Developer Edition or hosted SaaS version.

In plain words
What is it for?
Use it to run evaluations, create benchmark workflow files, perform red-team tests, monitor agents, and interpret measures such as task success, tool-use accuracy, routing, and retrieval quality.
Why use it?
It provides a structured way to check whether agents work correctly, find weaknesses before release, and inspect their behavior while running.

Skill for Claude CodeCodex

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

Good fit Use it to run evaluations, create benchmark workflow files, perform red-team tests, monitor agents, and interpret measures such as task success, tool-use accuracy, routing, and retrieval quality.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/agent-ops"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/agent-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

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 →

  • high Privilege Escalation · line 112
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 94
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00138 $0.05285
Opus 5 $0.00069 $0.02642
Sonnet 5 $0.00028 $0.01057
Haiku 4.5 $0.00014 $0.00528

Measured 10d ago against content hash cfc363c4c152, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-ops scanned grade A with 1 finding 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (setup.sh), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Full spec + worked examples (server start, evaluate with explicit token, env activate cloud, traces search with window, curl auth'd endpoint) in `reference/command-emission.md`.
ibm-bob/skills/agent-ops/SKILL.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Ops (watsonx Orchestrate)

This skill drives evaluations, red-teaming, and runtime observability for watsonx Orchestrate agents using the WXO ADK. Targets supported: Developer Edition (local server on :4321) and SaaS cloud (api.<region>.watson-orchestrate.{ibm.com|cloud.ibm.com}). On-prem Cloud Pak for Data is deferred.

Stance: ask-first, command-emit second, execute-rarely. Bob auto-runs only read-only diagnostics. Anything that mutates state, takes minutes, or runs evals is emitted as a bash block for the user to run in their terminal. Bob never runs server start, env activate, evaluations evaluate, red-teaming run, pip install, etc.


First action — prereq notice, then 3-question interview

On the FIRST turn of every conversation, before asking Q1, post this one-line prereq notice verbatim:

👋 Quick note before we start: if this is your first time using this skill on this machine, glance at assets/PREREQUISITES.md — it lists what you need installed (ADK, Docker, venv) and which credentials to have ready (WO_*, WATSONX_*, Langfuse keys). I'll preflight what I can after Q3, but it's friendlier to have these in place up front. If you already know your setup is good, skip straight to Q1 below.

Then proceed immediately with Q1, Q2, Q3 in the same message. Do NOT run any diagnostics (not even lsof or pip show) and do NOT inspect files until Q1 has been answered.

Expert escape hatch (Bob behavior)

Before asking Q1, check if the user's opening message already names a specific action. If they did — for example: "search traces from the last hour for agent X", "just run red-teaming list", "re-evaluate one failing scenario from this output dir", "set up Langfuse env vars" — skip the 3-question interview. Acknowledge in ONE line (e.g., "Going straight to the observability module"), still post the prereq notice, then run the read-only diagnostics for the matching module only.

Also: if the user EXPLICITLY says "skip the interview", "I know what I want", or similar, treat it as escape-hatch consent and ask only the single clarifying question you need to route correctly (typically target env + module, fused into one).

Read the full file on GitHub · 275 lines

Files

What ships with it

29 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. 10d ago First seen · 275 lines · 138 tokens per session scan A cfc363c4c152

Subscribe to this mod's changes

agent-ops is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (24 stars, last pushed today), licensed Apache-2.0. It adds 138 tokens to every session and 5,285 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens