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/agently-task-devnpx skills add okwinds/miscellany --skill agently-task-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 | $0.00131 | $0.04274 |
| Opus 5 | $0.00066 | $0.02137 |
| Sonnet 5 | $0.00026 | $0.00855 |
| Haiku 4.5 | $0.00013 | $0.00427 |
Grade A, and why
agently-task-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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agently Task Dev
Overview
把“用 Agently 开发任务/工作流”标准化成可回归的工程流程：先最小可运行，再逐步叠加 Agently 的能力（结构化输出、流式输出、工具、TriggerFlow、KB、MCP、服务化），并用能力清单做回归检查，避免遗漏与“重造轮子”。
这里的“通用”指 Agently 框架用法的通用性：不把方法论绑定到某个业务任务（写文章/写总结/写代码）上，而是覆盖 Agently 的能力面与工程化交付流程。
When To Use / When NOT To Use
适用：
- 你要写 Agently 任务/工作流，并且需要可回归测试（离线 stub + 可选真模型集成）。
- 你明确需要：
schema + ensure_keys、delta/instant/streaming_parse、Search/Browse、TriggerFlow、ChromaDB、MCP、SSE/WS/HTTP任意一项。
不适用（或应先确认再用）：
- 用户没有要用 Agently（只是泛泛讨论 streaming/tests），或明确说“不用 Agently”。
- 你只要“写个 prompt/纯文本输出”，不关心测试、结构化输出、streaming 或工具。
- 当前环境无法
import agently（需要先解决依赖环境）。
Read This First (Your TDD Definition)
你要求的“测试驱动”不是写文档，而是：
- 写任务的同时写测试（回归测试是交付物的一部分）
- 用 Agently 的输出/事件流来测可用性（schema/ensure_keys、instant streaming、SSE 等）
- 测试通过才算任务交付成功；否则不允许宣称“用 agently-task-dev 开发的任务没问题”
本 skill 自带 3 份“验收与回归”材料（用它们驱动开发）：
- 任务契约（接口约定）：
references/task-contract.md - 测试策略（离线回归 + 真模型集成）：
references/testing-strategy.md - 能力清单（不遗漏准绳）：
references/capability-inventory.md
另外提供若干份“可复用最佳实践”材料（避免踩坑、提升可迁移性）：
- Streaming UX（打字机 + 高性能 + 回归护栏）：
references/streaming-ux-playbook.md - Common Pitfalls（通用排障）：
references/common-pitfalls.md - OpenAICompatible 配置与鉴权 cookbook：
references/openai-compatible-settings-cookbook.md - Configure Prompt（YAML/JSON 模板化）：
references/configure-prompt-guide.md - Auto Loop（plan→tool→final）与 guardrails：
references/auto-loop-patterns.md - Response/Result & streaming 速查表：
references/response-result-cheatsheet.md - Settings & Prompt 结构化（全局/实例、slots/mappings、schema 顺序）：
references/settings-and-prompt-structure.md - Advanced Integrations（MCP/ChatSession/Attachment/Blueprint/运维）：
references/advanced-integrations.md - *CAP 覆盖索引（CAP- → skill 落点）**：
references/capability-coverage-map.md
最短闭环（推荐）：
- 用脚手架生成 task + tests（见下方 Quick Start）
- 先跑离线回归（不需要 key、稳定可重复）
- 必要时再开真模型集成测试（可选，依赖 key）
Quick Start: Scaffold Task + Regression Tests
用脚手架一次性生成“任务 + 测试 + OpenAI-compatible stub（离线）”：
What ships with it
21 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 270 B
- README.md 2.4 KB
- README.zh-CN.md 2.4 KB
- references/advanced-integrations.md 3.6 KB
- references/auto-loop-patterns.md 2.5 KB
- references/baseline-findings.md 3.1 KB
- references/capability-coverage-map.md 3.8 KB
- references/capability-inventory.md 9.1 KB
- references/common-pitfalls.md 3.8 KB
- references/configure-prompt-guide.md 2.7 KB
- references/mcp-safety-checklist.md 2.6 KB
- references/openai-compatible-settings-cookbook.md 3.7 KB
- references/pressure-scenarios.md 4.3 KB
- references/repo-reading-map.md 2.0 KB
- references/response-result-cheatsheet.md 2.3 KB
- references/settings-and-prompt-structure.md 4.1 KB
- references/streaming-ux-playbook.md 6.7 KB
- references/task-contract.md 2.0 KB
- references/testing-strategy.md 3.2 KB
- scripts/scaffold_task_with_tests.py 13 KB runs code
- scripts/validate_inventory_against_repo.py 3.5 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.
- 2d ago First seen · 391 lines · 131 tokens per session scan A ed5e05faddb3
agently-task-dev is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 4,274 once invoked, about $0.0007 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.