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 real-time-guardrailsgit 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/real-time-guardrails)<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/real-time-guardrails"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/real-time-guardrails/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/real-time-guardrails"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/real-time-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00131 | $0.04786 |
| Opus 5.5 | $0.00052 | $0.01914 |
| Sonnet 5.5 | $0.00026 | $0.00957 |
| Haiku 4.5 | $0.00013 | $0.00479 |
Grade B, and why
real-time-guardrails scanned grade B 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 24d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**RULE 1 — Never paste live credentials into chat.** Guide the user to set `WATSONX_APIKEY` and `WXG_SERVICE_INSTANCE_ID` in a `.env` file (`chmod 600`). Use `read -s` to enter the key without leaving it in shell history How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real-Time Guardrails
This skill helps developers wire production-grade safety and quality guardrails into AI agents using IBM's real-time-guardrails package (backed by watsonx.governance). The package ships 28 metrics across safety, RAG-generation, RAG-retrieval, quality, topic, pattern, and tool-call categories, with a 3-state Pass/Flag/Block action model, threshold policy as code, and audit logging.
Mandatory Rules
Read every time. Violating any of these causes silent or costly failures in production.
RULE 1 — Never paste live credentials into chat. Guide the user to set WATSONX_APIKEY and WXG_SERVICE_INSTANCE_ID in a .env file (chmod 600). Use read -s to enter the key without leaving it in shell history. If a user pastes a key into chat, interrupt and tell them to rotate it at IBM Cloud → Manage → Access (IAM) → API keys.
RULE 2 — WXG_PROJECT_ID is optional. The package runs 25 metrics with just WATSONX_APIKEY + WXG_SERVICE_INSTANCE_ID. WXG_PROJECT_ID unlocks 3 LLM-as-judge metrics (Answer Completeness, Conciseness, Tool Call Relevance). Don't force watsonx.ai on partners who don't want LLM-judge cost.
RULE 3 — Python 3.11–3.13 only. The IBM SDK chain doesn't support 3.14 yet. If the user is on 3.14, rebuild their venv with 3.11/3.12/3.13.
RULE 4 — Install from source with the [all] extra; use a dedicated venv. The package is not on PyPI today — partners install from a building-blocks repo clone via pip install -e "<repo>/ai/govern/guardrails/assets/sdk[all]". The quotes are required on zsh (macOS default) — without them, the shell parses [all] as an array subscript, silently produces an empty path, and pip errors with is not a valid editable requirement. The bundled setup.sh quotes correctly. Without [metrics,llmaj] (always part of base install), registry build fails with ModuleNotFoundError: No module named 'unitxt'. If the user reports ResolutionImpossible during install, their existing venv has stricter pins than the SDK can accept (typically on pydantic or httpx) — load reference/setup-and-credentials.md for the conflict matrix + dry-run recipe.
What ships with it
32 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/env.example 1.1 KB
- assets/thresholds.example.yaml 737 B
- examples/audit_log_sample.jsonl 3.6 KB
- examples/backend_guardrails_proxy.py 5.7 KB runs code
- examples/custom_metric_example.py 5.8 KB runs code
- examples/dashboard_skeleton.jsx 10 KB
- examples/decorator_example.py 7.2 KB runs code
- examples/frontend_chat_integration.jsx 5.2 KB
- examples/full_pipeline.py 7.9 KB runs code
- examples/input_safety.json 269 B
- examples/langchain_callback.py 5.5 KB runs code
- examples/middleware_fastapi.py 4.4 KB runs code
- examples/middleware_flask.py 3.1 KB runs code
- examples/pattern_keywords.json 434 B
- examples/rag_generation.json 416 B
- examples/rag_retrieval.json 605 B
- examples/sample_payloads.json 2.6 KB
- examples/tool_call.json 984 B
- examples/wxo_service_middleware.py 11 KB runs code
- examples/wxo_tool_wrapper.py 8.2 KB runs code
- README.md 5.4 KB
- reference/audit-and-observability.md 8.0 KB
- reference/auto-trigger-patterns.md 9.9 KB
- reference/custom-metric-authoring.md 8.9 KB
- reference/deployment.md 5.8 KB
- reference/frontend-integration.md 5.4 KB
- reference/integration-patterns.md 9.5 KB
- reference/metrics-catalog.md 12 KB
- reference/setup-and-credentials.md 7.3 KB
- reference/watsonx-orchestrate-integration.md 11 KB
- setup.sh 5.4 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.
- 24d ago Changed d069743708dc
- 1mo ago Changed 2d1bc88398dc
- 1mo ago Changed 262e92965894
- 2mo ago First seen · 245 lines · 131 tokens per session scan B 0b3eadf7c797
real-time-guardrails 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 131 tokens to every session and 4,786 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
real-time-guardrails compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| real-time-guardrailsibm-self-serve-assets/building-blocks | Skill | 28 | yesterday | Apache-2.0 | B | 131 | Claude Code, Codex |
| embeddingsruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 62 | Claude Code |
| agent-platform-rag-engine-managementgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 54 | Claude Code, Codex |
| 9router-embeddingsdecolua/9router | Skill | 32k | 9d ago | MIT | A | 66 | Claude Code, Codex |
| embedding-strategiesforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | 3d ago | Apache-2.0 | A | 37 | Claude Code, Codex |
| similarity-search-patternsforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | 3d ago | Apache-2.0 | A | 30 | Claude Code, Codex |