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/okwinds/miscellany/bf-caprt-devnpx skills add okwinds/miscellany --skill bf-caprt-devgit clone --depth 1 https://github.com/okwinds/miscellanyWhat 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 | $0.00258 | $0.05849 |
| Opus 5 | $0.00129 | $0.02925 |
| Sonnet 5 | $0.00052 | $0.01170 |
| Haiku 4.5 | $0.00026 | $0.00585 |
Grade A, and why
bf-caprt-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bf-caprt-dev
定位
本技能用于指导编码智能体通过 capability-runtime 落地业务能力，而不是绕过它去直接拼接上游框架。
默认心智模型：
skill / agent / workflow -> Runtime public surface -> NodeReport / host summary / service surfaces
自包含约束
本技能是一个自包含技能：
- 只允许引用当前技能目录内的
references/与evals/ - 不允许把
docs/、examples/、tests/、help/、README.md等外部仓库路径写成技能依赖 - 如需补充 capability-runtime 的新事实，先复制或整理到本技能目录，再在技能正文中引用
开场动作
- 先确认当前 Python 环境是否已经可导入
capability_runtime。 - 若还不能导入，优先使用 PyPI 安装；只有本地源码开发或 monorepo 场景，才改用 editable install。
- 只在临时验证时使用
PYTHONPATH兜底，不要把它当长期交付方案。 - 能导入之后再继续看
references/triad-and-routing.md与references/api-reference.md，不要一边猜环境一边写业务代码。
本地环境准备
如果是本地源码开发，再记本地仓库目录为 CAPRT_REPO_ROOT：
export CAPRT_REPO_ROOT=/abs/path/to/capability-runtime
先做 import 预检：
python3 -c "import capability_runtime; print('capability_runtime import ok')"
如果导入失败，优先使用 PyPI 安装：
pip install capability-runtime
如果你正在改本地源码，或仓库是 monorepo / 需要跟随未发布改动，再对包含 pyproject.toml 的本地源码目录做 editable install：
pip install -e "$CAPRT_REPO_ROOT"
如果仓库是 monorepo，pyproject.toml 不在根目录，就把上面的路径改成实际 Python 包目录。
只做临时验证时，才使用 PYTHONPATH 兜底：
export PYTHONPATH="$CAPRT_REPO_ROOT${PYTHONPATH:+:$PYTHONPATH}"
python3 -c "import capability_runtime; print('capability_runtime import ok')"
继续前，至少完成一个 smoke check：
python3 -c "from capability_runtime import Runtime, RuntimeConfig; print('caprt api ok')"
何时使用
当任务目标符合下面任一情形时，优先使用本技能：
- 用
capability-runtime新建业务 capability、agent、workflow、service 接口或离线回归样例 - 把已有业务 skills、Agent 壳、Workflow 编排统一收敛到 Runtime public surface
- 需要
Runtime.run()/run_stream()/run_structured()/run_structured_stream() - 需要
NodeReport、descriptor、host summary 作为程序判断或审计真相源 - 需要
RuntimeServiceFacade/RuntimeSession做 service/session continuity 落地 - 需要
invoke_capability、approval/waiting-human、resume、legacy host convergence
不要使用
下面这些情况不应触发本技能：
- 普通通用编码，与 capability-runtime 无关
- 只改 prompt，不关心 Runtime、测试、注册、NodeReport 或执行链路
- 想直接学习上游原生框架 API，例如 Agently/TriggerFlow 的原生写法
- 明确要求绕过 capability-runtime，直接把 provider SDK 或上游框架接进业务主流程
- 明确要求“直接用
skills-runtime-sdk/Agently/ provider SDK 完成业务”，并且不需要AgentSpec/WorkflowSpec/Runtime
What ships with it
8 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.
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.
- 2d ago First seen · 539 lines · 258 tokens per session scan A 16f0345f5a89
bf-caprt-dev is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 3mo ago), licensed MIT. It adds 258 tokens to every session and 5,849 once invoked, about $0.0013 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…