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-handoffgit 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-handoff)<a href="https://agentmods.dev/skills/mrstev3n/balise-skills/balise-handoff"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-handoff/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-handoff"><img src="https://agentmods.dev/badge/skills/mrstev3n/balise-skills/balise-handoff.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 | $0.00087 | $0.03833 |
| Opus 5 | $0.00044 | $0.01917 |
| Sonnet 5 | $0.00017 | $0.00767 |
| Haiku 4.5 | $0.00009 | $0.00383 |
Grade A, and why
balise-handoff 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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Readiness
Determine whether the selected design version can be implemented without unresolved critical ambiguity. Treat readiness as an evidence-based agreement—not as visual polish, layer hygiene, annotation volume, or a promise that future code will be correct.
Core rules
- Audit the user’s selection and its necessary context. Do not review the entire file by default.
- Preserve source frames, components, variables, prototypes, links, annotations, and statuses unless the user explicitly asks to edit them.
- Identify the exact scope, version, platform, implementation audience, release context, and risk before applying gates.
- Inspect existing components, properties, variables, modes, styles, layout rules, prototypes, annotations, Dev resources, and design-system conventions before proposing additions.
- Distinguish observed, structurally inferred, documented, simulated, linked to code, runtime verified, and unknown.
- Never treat Ready for dev, the absence of Changed, a prototype, a generated snippet, a matching layer name, or visual similarity as production proof.
- Never invent API behavior, data shape, permissions, breakpoints, semantics, analytics, asset rights, or engineering constraints as facts.
- Use the smallest evidence that resolves the implementation question. Do not annotate inspectable properties or every pixel.
- Apply gates proportionally. Never average away one unresolved critical blocker with many minor passes.
- Give every critical open decision an impact, owner, next action, and fallback when one exists.
- Reuse the existing product and design system. Do not create a parallel component or token system to make the handoff look cleaner.
- Treat handoff as a continuing collaboration. Readiness is attached to a version and can be invalidated by later changes.
Infer the mode
- Audit: inspect and issue a verdict without editing.
- Prepare: create or repair handoff structure after explicit edit intent.
- Verify: reinspect gates affected by corrections or changes without editing by default.
- Contract: summarize the handoff evidence and decisions without editing.
- Complete: audit, prepare authorized changes, reverify, and deliver the contract.
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 · 432 lines · 87 tokens per session scan A 60f8668788a3
balise-handoff is a skill published in the GitHub repository mrstev3n/balise-skills (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,833 once invoked, about $0.0004 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…