bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 agentmods add skills/bytedance/agentkit-samples/byted-ark-evolvenpx skills add bytedance/agentkit-samples --skill byted-ark-evolvegit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/byted-ark-evolve)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-ark-evolve"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-ark-evolve.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 | $0.00088 | $0.05702 |
| Opus 5 | $0.00044 | $0.02851 |
| Sonnet 5 | $0.00018 | $0.01140 |
| Haiku 4.5 | $0.00009 | $0.00570 |
Grade A, and why
byted-ark-evolve scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **无外网调用**：脚本不发起 HTTP/socket 请求(可代码层验证：无 `requests` / `urllib` / `http.client` / `socket` 等导入用于网络通信)。 How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolution Skill
Agent 自进化系统。进化单位是整个 Agent（Identity + Context + Protocol + Capability + Runtime）。
核心原则
- Quality > Reliability > Efficiency > Cost — 不允许牺牲质量换效率
- 帕累托约束 — 任何 mutation 如果导致某个维度退化，BLOCK 并请用户决策
- 写入即生效 — 用户确认变更后写入 workspace 文件，下次 session 即可加载新配置
- 先对齐再执行 — 进化方案必须先呈现给用户确认
数据安全与权限边界
- 本地存储：所有运行时数据(信号、轨迹、变异、报告)写入用户本地
~/.{*claw*}/workspace/evolution-data/，不上传任何外部服务。 - 无外网调用：脚本不发起 HTTP/socket 请求(可代码层验证：无
requests/urllib/http.client/socket等导入用于网络通信)。 - 变更前置确认：mutation 写入 workspace 文件前，必须由用户在对话中显式接受提案；用户未接受前不会修改任何文件。
- 作用范围：写入仅限
~/.{*claw*}/workspace/目录及其子目录；不访问/etc/、~/.ssh/、~/.aws/等敏感路径。 - 可审计：每次 apply 通过 git commit 留痕，用户可随时
git log查看完整变更历史。 - 可追溯：每条 mutation 在 SQLite DB 中保留 source(evolution / user-direct / snapshot-diff)、决策状态、时间戳。
- 可禁用：删除
evolution-data/目录或卸载 skill 即完全停止；删除~/.{*claw*}/workspace/不会影响其他 skill。
数据目录
Runtime 适配：workspace 根路径自动探测
~/.{*claw*}/workspace/(优先.arkclaw→.openclaw→ 其他含claw的目录),也可用CLAW_WORKSPACE环境变量显式指定。新装默认创建在~/.arkclaw/workspace/。
evolution-data/
├── file-registry.json ← 初始化扫描结果
├── evolution.db ← SQLite（信号、变异、轨迹）
├── snapshot.json ← Workspace 文件 hash 快照（兜底变更检测）
├── trajectories/
│ ├── golden/ ← 正确执行轨迹
│ └── corrections/ ← 错误→修正对
├── dashboard.html ← Dashboard 页面（dashboard-render.py 自动生成）
└── reports/
├── evolution-*.json ← 进化报告数据（JSON）
└── evolution-*.html ← 进化报告页面（渲染后）
References（按需读取，不随 session 加载）
| 文件 | 内容 | 何时读取 |
|---|---|---|
references/layer-model.md |
5 层模型 + 归因规则 | 进化分析时 |
references/pareto-rules.md |
帕累托约束 + 验证标准 | 进化分析时 |
references/file-semantic-map.md |
已知文件→层/语义/风险映射 | 初始化 + 归因时 |
references/init-rules.md |
状态判定规则 + 占位符列表 | 初始化时 |
references/signal-types.md |
信号识别规则 + 示例 | 信号收集时 |
references/trajectory-templates.md |
轨迹存储格式 + 示例 | 轨迹写入时 |
references/evolution-steps.md |
进化分析详细流程（Step 0-7） | /evolve 执行时 |
references/onboarding.md |
新手引导内容 | 首次安装时 |
references/report-schema-example.json |
报告 JSON 数据格式示例 | 生成报告时 |
references/dashboard-schema-example.json |
Dashboard JSON 数据格式示例 | 生成 Dashboard 时 |
What ships with it
40 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.
- LICENSE 11 KB
- README.md 5.1 KB
- references/dashboard-schema-example.json 3.3 KB
- references/evolution-steps.md 11 KB
- references/file-semantic-map.md 2.3 KB
- references/gene-contract.md 1.8 KB
- references/gene-library.json 89 KB
- references/init-rules.md 2.3 KB
- references/layer-model.md 2.2 KB
- references/onboarding.md 3.7 KB
- references/pareto-rules.md 2.1 KB
- references/pending-proposal-lifecycle.md 757 B
- references/report-schema-example.json 2.1 KB
- references/signal-types.md 3.3 KB
- references/trajectory-templates.md 2.0 KB
- scripts/_workspace.py 3.0 KB runs code
- scripts/apply-proposal.py 8.2 KB runs code
- scripts/dashboard-render.py 18 KB runs code
- scripts/dashboard-template.html 29 KB
- scripts/db-init.py 6.7 KB runs code
- scripts/db-migrate-source.py 2.2 KB runs code
- scripts/db-migrate-v031.py 4.6 KB runs code
- scripts/detect-signal.py 7.8 KB runs code
- scripts/gate-check.py 5.5 KB runs code
- scripts/gene.py 3.3 KB runs code
- scripts/orchestrator.py 18 KB runs code
- scripts/pending-evolution.py 6.8 KB runs code
- scripts/query.py 9.3 KB runs code
- scripts/report-gen.py 28 KB runs code
- scripts/report-render.py 16 KB runs code
- scripts/scan-history.py 16 KB runs code
- scripts/signal-record.py 3.3 KB runs code
- scripts/snapshot.py 7.5 KB runs code
- scripts/track-change.py 7.5 KB runs code
- scripts/trajectory-skill-check.py 6.0 KB runs code
- scripts/workspace-init.py 11 KB runs code
- test-conversations/conversation-1-research-before-asking.md 1.8 KB
- test-conversations/conversation-2-memory-access-boundary.md 1.6 KB
- test-conversations/conversation-3-report-usability.md 2.4 KB
- test-conversations/README.md 343 B
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.
- 5d ago First seen · 487 lines · 88 tokens per session scan A 6cf0e2163cdd
byted-ark-evolve is a skill published in the GitHub repository bytedance/agentkit-samples (446 stars, last pushed 2d ago), licensed Apache-2.0. It adds 88 tokens to every session and 5,702 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
sn-image-imitate
Generates a new image that imitates the style of a reference image while updating content based on user intent. Uses a three-stage pipeline: image annotation (long caption), caption rewriting, and image generation. Use when user asks to "imitate style", "保持这个风格重画", "按这张图风格生成", or "style transfer with new content".