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.
npx skills add ibm-self-serve-assets/building-blocks --skill agent-opsgit clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocksWrote 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.
[](https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/agent-ops)<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.
<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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.
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`. 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).
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.
- assets/mcp.json 440 B
- assets/PREREQUISITES.md 12 KB
- examples/minimal_single_tool/README.md 861 B
- examples/minimal_single_tool/scenario_01_lookup_user.json 574 B
- examples/multi_agent_routing/README.md 1.2 KB
- examples/multi_agent_routing/scenario_01_route_to_billing.json 1005 B
- examples/multi_agent_routing/scenario_02_route_to_tech_support.json 1.2 KB
- examples/portfolio_advisor/scenario_01_portfolio_review_and_report.json 1.2 KB
- examples/portfolio_advisor/scenario_02_gold_tier_metrics.json 894 B
- examples/portfolio_advisor/scenario_03_all_holders_metrics.json 1.1 KB
- examples/portfolio_advisor/scenario_04_multi_turn_portfolio_review.json 1.6 KB
- examples/portfolio_advisor/scenario_05_diamond_tier_market_update.json 1.3 KB
- examples/portfolio_advisor/scenario_06_rebalancing_alert_with_text_check.json 1.8 KB
- examples/portfolio_advisor/scenario_07_rag_investment_policy.json 1.2 KB
- examples/portfolio_advisor/scenario_08_rag_compliance_and_action.json 1.2 KB
- examples/rag_only/README.md 1.2 KB
- examples/rag_only/scenario_01_policy_lookup.json 690 B
- examples/rag_only/scenario_02_compliance_question.json 686 B
- examples/stories_sample.csv 299 B
- README.md 6.8 KB
- reference/auth-env-matrix.md 12 KB
- reference/command-emission.md 8.1 KB
- reference/module-analyze.md 7.3 KB
- reference/module-benchmarks.md 8.8 KB
- reference/module-eval.md 10 KB
- reference/module-observability.md 10 KB
- reference/module-red-teaming.md 9.3 KB
- setup.sh 2.2 KB runs code
- USAGE-GUIDE.md 11 KB
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.
- 10d ago First seen · 275 lines · 138 tokens per session scan A cfc363c4c152
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.
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.
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".
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…
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.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.