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 arrrrny/zuraffa --skill docsgit clone --depth 1 https://github.com/arrrrny/zuraffaWrote 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/arrrrny/zuraffa/docs)<a href="https://agentmods.dev/skills/arrrrny/zuraffa/docs"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/docs/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/arrrrny/zuraffa/docs"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/docs.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 | $0.00065 | $0.00934 |
| Opus 5.5 | $0.00026 | $0.00374 |
| Sonnet 5.5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
zuraffa-cli 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 8d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zuraffa CLI (v7) Skill
Use this skill when
- creating or updating Zorphy entities
- generating CRUD architecture around an entity
- adding data, VPC, DI, test, cache, mock, route, gql, or graphql layers
- generating a custom use case or orchestrator
- guiding another agent or user through the current v7 workflow
The canonical workflow
Always prefer this sequence:
zfa entity create -n Product \
--field id:String \
--field name:String \
--field price:double
zfa make Product \
--preset=crud \
--methods=get,getList,create,update,delete \
--with=vpc \
--state \
--di \
--test
zfa build
Golden rules
- Use
zfa makeas the primary generator. - Use
zfa entity createfor entities. Never hand-create them. - Use
zfa buildafter generation. Do not teachbuild_runnerdirectly as the normal workflow. - Treat
zfa feature scaffoldas a wrapper, not the canonical command. - Assume the domain root is fixed to
lib/src/domain. - Assume entities are Zorphy-first on public v7 surfaces.
Fixed paths and assumptions
Entity files belong at:
lib/src/domain/entities/{entity_snake}/{entity_snake}.dart
Example:
lib/src/domain/entities/product/product.dart
Recommended make patterns
CRUD slice
zfa make Product --preset=crud --methods=get,getList,create,update,delete
CRUD + UI + tests
zfa make Product \
--preset=crud \
--methods=get,getList,create,update,delete \
--with=vpc \
--state \
--test
Add DI, cache, and mocks
zfa make Product \
--preset=crud \
--methods=get,getList \
--cache \
--di \
--mock \
--use-mock
Custom use case
zfa make SearchProducts usecase \
--domain=search \
--params=SearchQuery \
--returns=List<Product>
Inspect the plan before writing files
zfa make Product --preset=crud --with=vpc --plan --format=json
feature wrapper rule
If you see or receive zfa feature scaffold, interpret it as wrapper syntax for the feature preset.
What ships with it
16 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.
- architecture/offline-first-sync.md 14 KB
- CACHING.md 10 KB
- CLI_GUIDE.md 13 KB
- hand-authored-g-dart-placeholders.md 6.6 KB
- INSIGHTS.md 5.8 KB
- integrations/api-plugin-testing.md 4.4 KB
- integrations/vm-service-api-bridge.md 9.2 KB
- openwiki/cli.md 80 KB
- package_migration_guide.md 16 KB
- PUBLISH.md 5.5 KB
- README.md 1.7 KB
- skin_plugin.md 5.6 KB
- tunnel.md 6.3 KB
- VISION.md 5.2 KB
- writing_zuraffa_packages.md 12 KB
- zfa-tdd-guide.md 30 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.
- 8d ago First seen · 159 lines · 65 tokens per session scan A 2d0cf2dd0053
zuraffa-cli is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 934 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-31.
zuraffa-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zuraffa-cliarrrrny/zuraffa | Skill | 5 | today | MIT | A | 65 | Claude Code, Codex |
| fl-testingphanbaohuy96/flutter_base_structure | Skill | 10 | 1mo ago | none | A | 21 | Claude Code, Codex |
| verify-workHoangNguyen0403/agent-skills-standard | Skill | 583 | yesterday | MIT | A | 23 | Codex |
| mocktailevanca/flutter-ai-rules | Skill | 668 | 2d ago | MIT | A | 34 | Claude Code |
| brooks-testhyhmrright/brooks-lint | Skill | 1.6k | yesterday | MIT | A | 161 | Claude Code |
| merge-queue-readinessZaxbyHub/opencode-swarm | Skill | 517 | yesterday | MIT | A | 39 | OpenCode |
| run-affected-test-file-in-isolation-and-in-co-run-with-its-test-ZaxbyHub/opencode-swarm | Skill | 517 | yesterday | MIT | A | 36 | OpenCode |