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 Lulu-Eva/Eva-skill --skill eva-sharedgit clone --depth 1 https://github.com/Lulu-Eva/Eva-skillWrote 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/lulu-eva/eva-skill/eva-shared)<a href="https://agentmods.dev/skills/lulu-eva/eva-skill/eva-shared"><img src="https://agentmods.dev/badge/skills/lulu-eva/eva-skill/eva-shared.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.00381 |
| Opus 5 | $0.00043 | $0.00191 |
| Sonnet 5 | $0.00017 | $0.00076 |
| Haiku 4.5 | $0.00009 | $0.00038 |
Grade A, and why
eva-shared 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 7d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
57 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.
- agents/openai.yaml 242 B
- examples/asset-card.example.json 555 B
- examples/eva.link.example.json 586 B
- examples/link-registry.example.json 727 B
- examples/local.weibo-copy/eva.link.json 604 B
- examples/local.weibo-copy/module.md 1.1 KB
- examples/local.weibo-copy/tests/expected-asset.example.json 890 B
- examples/local.weibo-copy/tests/input.example.md 486 B
- examples/prompt-regression-matrix.json 121 KB
- references/asset/00_eva-asset_资产卡协议.md 9.7 KB
- references/audience/00_eva-audience-finder_话题人群识别器.md 14 KB
- references/benchmark/00_eva-benchmark-copy_对标文案拆解.md 4.7 KB
- references/commerce/00_eva-commerce_商单主入口.md 6.1 KB
- references/commerce/01_brief-parse_Brief基础解析.md 3.3 KB
- references/commerce/02_constraint-card_商单约束卡生成.md 5.1 KB
- references/commerce/03_draft-check_已有商单稿检查.md 3.6 KB
- references/commerce/04_sample-transfer_对标样本迁移.md 2.3 KB
- references/harness/00_eva-harness_状态与交接校验.md 7.4 KB
- references/interaction/00_eva-voice_互动语气节奏.md 7.8 KB
- references/learn/00_eva-learn.md 4.3 KB
- references/learn/01_探索式学习.md 13 KB
- references/learn/02_资料带学.md 13 KB
- references/learn/03_主题式阅读.md 8.2 KB
- references/learn/04_思想种子卡与内容链路交接.md 7.0 KB
- references/learn/05_eva-learn-project_分级建档与恢复.md 6.8 KB
- references/lens/00_eva-lens-discipline-divergence_学科发散.md 5.3 KB
- references/memory/00_eva-memory_点子卡沉淀与回溯.md 29 KB
- references/memory/01_eva-persona-memory_人设记忆采集.md 17 KB
- references/memory/02_eva-user-voice_用户表达文风提取.md 9.8 KB
- references/memory/03_eva-data-export_统一数据备份.md 10 KB
- references/memory/04_eva-product-service_产品与服务采集.md 14 KB
- references/quality/00_eva-ai-check_表达真实性审查.md 11 KB
- references/shared/00_handoff-cards_交接卡字段真源.md 5.4 KB
- references/shared/01_asset-state_资产状态归一表.md 6.5 KB
- references/shared/02_low-confidence_低置信度授权协议.md 4.4 KB
- references/shared/03_commercial-constraint-card_商单约束卡真源.md 5.2 KB
- references/shared/04_light-interaction_轻交互协议.md 11 KB
- references/shared/05_expression-asset-preload_表达资产轻量预加载协议.md 9.0 KB
- references/shared/06_external-material-safety_外部材料安全边界.md 1.9 KB
- references/shared/07_next-step-navigation_动态选路与下一步推荐.md 9.7 KB
- references/shared/08_acquisition-objective-overlay_获客目标覆盖层.md 17 KB
- schemas/asset-card.schema.json 9.7 KB
- schemas/asset-types.json 6.0 KB
- schemas/eva-link.schema.json 2.5 KB
- schemas/failure-record.schema.json 858 B
- schemas/handoff-targets.json 775 B
- schemas/initializer-card.schema.json 1.2 KB
- schemas/link-registry.schema.json 2.4 KB
- scripts/eva_asset_validate.py 19 KB runs code
- scripts/eva_common.py 21 KB runs code
- scripts/eva_data_export.py 77 KB runs code
- scripts/eva_doctor.py 28 KB runs code
- scripts/eva_link_check.py 23 KB runs code
- scripts/eva_memory_inventory.py 40 KB runs code
- scripts/eva_memory_save.py 38 KB runs code
- scripts/eva_prompt_lint.py 24 KB runs code
- scripts/eva_selftest.py 291 KB runs code
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.
- 7d ago First seen · 32 lines · 85 tokens per session scan A 5e5ef2a79855
eva-shared is a skill published in the GitHub repository Lulu-Eva/Eva-skill (49 stars, last pushed 17d ago), with no licence file. It adds 85 tokens to every session and 381 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…