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 mrstev3n/balise-skills --skill balise-trustworthy-flowsgit clone --depth 1 https://github.com/mrstev3n/balise-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/skills/mrstev3n/balise-skills/balise-trustworthy-flows)<a href="https://agentmods.dev/skills/mrstev3n/balise-skills/balise-trustworthy-flows"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-trustworthy-flows/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/mrstev3n/balise-skills/balise-trustworthy-flows"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-trustworthy-flows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.03311 |
| Opus 5 | $0.00032 | $0.01656 |
| Sonnet 5 | $0.00013 | $0.00662 |
| Haiku 4.5 | $0.00006 | $0.00331 |
Grade A, and why
balise-trustworthy-flows 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trustworthy Flows for Figma
Protect a person's ability to understand, choose, refuse, leave, revoke, and recover across consequential product flows. Audit the decision system, not the visual polish of one screen.
Do not call other skills or depend on references, scripts, assets, or files outside this document.
Core rules
- Preserve source frames, components, libraries, prototype links, and annotations unless the user explicitly asks to edit them.
- Work within the selection and the adjacent path needed to understand entry, commitment, outcome, exit, revocation, and recovery.
- Reuse existing components, variants, properties, variables, styles, Auto Layout, tokens, naming, and product language.
- Separate observed, prototype-verified, declared, hypothetical, and proposed evidence.
- Never infer intent from the interface. Describe the visible mechanism and plausible consequence.
- Never invent price, stock, urgency, social proof, consent persistence, deletion, notification, permission, analytics, or backend behavior.
- Do not diagnose a person's cognitive bias. State that the presentation may exploit or amplify a known bias.
- Do not declare an interface legal, compliant, safe, accessible, or free of manipulation from a Figma file.
- Preserve legitimate protective friction. Challenge friction that appears to serve only the product's preferred choice.
- Use synthetic data. Never place real personal, financial, health, authentication, research, or client data in test frames.
- If entry, commitment, or exit is missing, produce a partial finding and open questions. Never invent a branch.
- Route serious legal, privacy, accessibility, financial, child-safety, or coercive-control risks to qualified review.
Infer the mode
- Audit: reconstruct and report without editing.
- Compare: compare selected branches, alternatives, or versions against one contract.
- Repair: create the smallest cooperative correction after explicit edit intent.
- Design: design a new consequential flow with disclosure, choice, exit, and recovery.
- Verify: exercise visible prototype paths and report evidence and unknowns without editing.
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 · 315 lines · 65 tokens per session scan A f02ade38fab9
balise-trustworthy-flows is a skill published in the GitHub repository mrstev3n/balise-skills (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 65 tokens to every session and 3,311 once invoked, about $0.0003 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 skills, from other repositories
ijfw-ui-spec
Use when the user says: 'ui spec', 'design contract', 'ui audit setup', 'lock the design', 'visual contract', 'ui review setup', or '/ijfw-ui-spec'. Produces UI-SPEC.md as the visual design contract before any frontend or visual-artifact build, and dispatches ijfw-ui-auditor as the final 6-pillar gate.
ijfw-design
Use when the user says: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish', 'pretty', 'professional', 'user experience', 'layout', 'visual', 'accessibility', 'colors', 'typography', 'brand'.
Add Claude design-system and accessibility workflows with UX/UI Agent Skills
Use UX/UI Agent Skills when Claude should generate tokens, component specs, accessibility audits, and framework-specific UI code from a repeatable design workflow.
design-maker
name: design-maker description: Used when the Design Brief is complete and the user needs to generate mockups. Reads Product-Spec.md and Design-Brief.md, then generates a complete set of design deliverables through a design tool MCP, including all pages, state variants, component specifications, design tokens…
ui-designer
Designs and builds interface work on top of the design system the repo already has: layout, spacing, hierarchy, interaction states, and accessible defaults, with creativity calibrated to the surface instead of an unrequested redesign. Use when asked for a new screen, a redesign, empty, loading, and error states, or to…
design-brief-builder
name: design-brief-builder description: Used when the user wants to define a design style or visual direction, or says something vague like 'I want a premium/sleek/modern look'. Guides the user through a design interview to clarify visual preferences and outputs Design-Brief.md. After Brief is saved, MUST run Next…