Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/okwinds/miscellanynpx agentmods add skills/okwinds/miscellany/bf-skillsruntime-devWrote 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/okwinds/miscellany/bf-skillsruntime-dev)<a href="https://agentmods.dev/skills/okwinds/miscellany/bf-skillsruntime-dev"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/bf-skillsruntime-dev/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/okwinds/miscellany/bf-skillsruntime-dev"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/bf-skillsruntime-dev.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 | $0.00132 | $0.02661 |
| Opus 5.5 | $0.00053 | $0.01064 |
| Sonnet 5.5 | $0.00026 | $0.00532 |
| Haiku 4.5 | $0.00013 | $0.00266 |
Grade A, and why
bf-skillsruntime-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Runtime SDK 业务开发指南
核心原则:
- 离线优先:先让
FakeChatBackend跑通最小闭环,再接真模型 - Skills-First:角色能力先沉淀成
SKILL.md,编排层只负责组合 - 证据优先:副作用必须能在 WAL / approvals / tool events 中回放
- 双轨协作:固定角色用
Coordinator,动态子任务用 collab primitives
事实快照:
- 当前技能按 2026-04-02 / SDK 0.1.11 校对
- 本技能只引用当前目录内的
references/与scripts/ - 如果你发现仓库事实再次变化,先更新本技能的本地 references,再继续使用
开场动作
- 先定位本地仓库根目录,不要默认联网克隆。
- 优先确认当前环境是否已经安装
skills-runtime-sdk;未安装时再用本地仓库做 editable install。 - 先选开发形态,再决定读哪份本地 reference:
- 单 agent + 工具:看
references/recipes-index.md - Skills 注入 / references / actions:看
references/config-templates.md - 多 agent / 动态协作:看
references/api-cheatsheet.md+references/recipes-index.md - 安全 / 审批 / 沙箱:看
references/safety-and-sandbox.md - 回归 / 验证 / 证据:看
references/testing-strategy.md
- 单 agent + 工具:看
本地环境准备
如果已知仓库根目录,记为 REPO_ROOT:
export REPO_ROOT=/abs/path/to/skills-runtime-sdk
安装 SDK 二选一:
# 方式 A:开发模式安装(推荐)
pip install -e "$REPO_ROOT/packages/skills-runtime-sdk-python"
# 方式 B:临时 PYTHONPATH(不安装)
export PYTHONPATH="$REPO_ROOT/packages/skills-runtime-sdk-python/src"
CLI 两种入口都可用:
skills-runtime-sdk --help
python3 -m skills_runtime.cli.main --help
快速开始
1) 生成业务骨架
python3 scripts/scaffold_app.py my-app --out . --with-skills
# 预览:加 --dry-run
# 覆盖:加 --force
默认生成:
run.pyconfig/runtime.yamlskills/tests/
2) 离线跑通
python3 run.py --workspace-root /tmp/my-app --mode offline
3) 最小回归
pytest -q tests
如果你正在本仓内开发,再跑仓库门禁:
bash scripts/pytest.sh
pytest -q packages/skills-runtime-sdk-python/tests/test_examples_smoke.py
推荐导入与运行骨架
最小 Agent
from pathlib import Path
from skills_runtime.agent import Agent
from skills_runtime.llm.fake import FakeChatBackend, FakeChatCall
from skills_runtime.llm.chat_sse import ChatStreamEvent
agent = Agent(
workspace_root=Path("/tmp/demo").resolve(),
backend=FakeChatBackend(calls=[
FakeChatCall(events=[
ChatStreamEvent(type="text_delta", text="EXAMPLE_OK: done."),
ChatStreamEvent(type="completed", finish_reason="stop"),
])
]),
)
result = agent.run("完成任务")
print(result.status, result.final_output, result.wal_locator)
What ships with it
9 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.
- README.md 2.6 KB
- README.zh-CN.md 2.7 KB
- references/api-cheatsheet.md 6.4 KB
- references/config-templates.md 2.8 KB
- references/recipes-index.md 3.1 KB
- references/repo-reading-map.md 2.8 KB
- references/safety-and-sandbox.md 2.5 KB
- references/testing-strategy.md 2.9 KB
- scripts/scaffold_app.py 6.6 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.
- 2mo ago First seen · 313 lines · 132 tokens per session scan A 033c2fcbeb64
bf-skillsruntime-dev is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 5mo ago), licensed MIT. It adds 132 tokens to every session and 2,661 once invoked, about $0.0005 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 2026-08-30.
bf-skillsruntime-dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bf-skillsruntime-devokwinds/miscellany | Skill | 50 | 5mo ago | MIT | A | 132 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |