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.
git clone --depth 1 https://github.com/Owl-Listener/ai-design-skillsWrote 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/commands/owl-listener/ai-design-skills/design-guardrails)<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/design-guardrails"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/design-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/commands/owl-listener/ai-design-skills/design-guardrails"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/design-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 | $0.00011 | $0.00484 |
| Opus 5 | $0.00005 | $0.00242 |
| Sonnet 5 | $0.00002 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
design-guardrails 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 12d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are designing guardrails for an AI feature. Use only skills from the ai-alignment-reasoning plugin. Follow this process:
Step 1: Map the Risk Landscape
Using harm-anticipation:
- Identify all potential harms this feature could cause (direct, facilitated, emergent, omission, erosion)
- For each harm, assess likelihood and severity
- Identify the most vulnerable users and misuse scenarios
- Create a risk-severity matrix
Step 2: Define Values
Using value-specification:
- What values should this feature embody?
- Establish a value hierarchy for this feature
- Identify where values conflict and how to resolve conflicts
- Translate each value into at least one concrete rule
Step 3: Design Guardrails
Using guardrail-design:
- For each identified risk, design a guardrail
- Specify: content, action, tone, scope, and confidence guardrails
- For each guardrail, define what the user sees when it activates
- Define severity tiers (hard block, soft warning, nudge)
- Identify edge cases for each guardrail
Step 4: Design Communication
Using transparency-patterns and guardrail-design:
- Write refusal messages for each hard-block guardrail
- Design redirect suggestions for each soft warning
- Specify when the AI should explain its boundaries vs. silently steer
Step 5: Design Escalation
Using escalation-design:
- Define when guardrails should trigger escalation to humans
- Design the escalation flow for high-stakes guardrail activations
- Specify context transfer for escalated cases
Step 6: Design User Controls
Using consent-and-agency:
- Which guardrails can users adjust?
- What override mechanisms exist?
- How does the user understand and control the boundaries?
Output
Deliver a complete guardrail specification:
- Risk landscape matrix
- Value hierarchy and conflict resolution rules
- Guardrail specification table: Guardrail | Type | Severity | Trigger | User Experience | Edge Cases
- Refusal and redirect message templates
- Escalation protocols for guardrail activations
- User control specifications
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.
- 12d ago First seen · 49 lines · 11 tokens per session scan A f019de1f15d2
design-guardrails is a command published in the GitHub repository Owl-Listener/ai-design-skills (173 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 484 once invoked, about $0.0001 per session on Opus 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.