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/peiiii/nextclaw/development-task-understandingnpx skills add Peiiii/nextclaw --skill development-task-understandinggit clone --depth 1 https://github.com/Peiiii/nextclawWhat 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 | $0.00065 | $0.01068 |
| Opus 5 | $0.00032 | $0.00534 |
| Sonnet 5 | $0.00013 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
development-task-understanding 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 3d 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.
What it actually says
Development Task Understanding
目标
回答“用户要解决什么，系统实际怎样”。沿用户指出的入口取证，不凭文件名、局部调用或截图外推，也不从愿景、使用信号或市场发明需求；相邻机会只记为范围外。
进入
标准开发任务轻量进入；明确要求调查、完整链路、复杂调试或根因，或局部证据不足时正式展开。
先冻结：
- 用户或系统可观察问题；
- 最小完整结果及其必要链路；
- 任务类型、Design/设计文档建议及证据；
bugfix另含复现决策与修后判定； - 期望行为和成功条件；
- 范围、非目标和约束；
- 当前已知事实、假设和未知项；
- 最近 owner、影响面和 L0-L4 风险。
涉及框架、协议或通用抽象时，先用真实场景证明零改动闭环；能成立就不改。只有可复现、无法由业务或 adapter 承接且阻断当前结果的共同缺口才升级；未来可能和“更通用”不算证据。
调查顺序
- 明确判断对象和会改变的下一步决策。
- 读取对象本体，记录它实际产生、保存、转换或消费的事实。
- 用
rg查调用方、被调用方、同类入口和规范事实源。 - 沿最近完整链路核对
producer -> owner/state -> boundary -> consumer。 - 扫同 owner 或责任链的同类问题，但不无界扩张到全仓库。
- 区分已确认事实、合理假设和仍需验证的未知项。
- 判断路径是否显然，或存在会改变结果、owner、复杂度或验证的真实设计空间。
Bug 复现门
bugfix 必须选择 reproduce 或 skip-reproduction：
- 根因、违约边界或修后判定任一不确定时，选择
reproduce，用命中同一违约点的最低成本复现。 - 仅当直接证据锁定根因和边界且有贴近风险的修后验证时，才选择
skip-reproduction，并记录依据和替代验证。 - 时间、环境和 Token 只影响复现层级，不降低证明门槛。
reproduce 保留失败入口、输入和指标供 Validation 复验；skip-reproduction 披露没有修前基线。复现不新增 phase。
每次新增调查必须改变一个设计、实现或验证决策；已确认且未变化的长文件、日志和命令输出不得重读。
外部协议按端点和操作取证，不从单个成功端点外推。有状态机制分别核对触发、输入、替换、持久化/恢复、重试和测试；registry/catalog 投影对照 canonical 来源。
条件方法
- 用户只给出方向、目标边界模糊或“做到什么程度”会改变交付时，读取最小完整结果边界。
- 跨多 hop、runtime、transport、异步边界，或真实复现昂贵时，读取链路切片。
- 用户要求系统根因、事故复盘或机制沉淀，且已有足够直接证据时，读取根因分层。
普通任务理解不读取这些参考；一次只选择当前需要的一种方法。
输出
- 需求、最小完整结果、必要链路、范围、非目标、成功条件和风险；
- 任务类型、Design/设计文档建议与分叉依据；
bugfix另含复现决定、依据和修后判定； - 已查 producer、owner、boundary、consumer 范围；
- 已确认事实、仍待验证假设和证据缺口；
- 路径是否显然、是否需要正式设计；
- 推荐下一阶段、继续调查或不改，以及原因。
本阶段不冻结实现方案、不编辑产物、不执行最终验证，也不枚举并加载所有可能的专项 skill。
What ships with it
4 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.
- 3d ago First seen · 71 lines · 65 tokens per session scan A 7c2a383ff465
development-task-understanding is a skill published in the GitHub repository Peiiii/nextclaw (253 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 1,068 once invoked, about $0.0003 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
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the exec tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败'…
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
ha-data-analytics
Hope-native local-first data analysis and Artifact reporting. Use for CSV/XLSX analysis, KPI readouts, metric diagnosis, product/business analysis, data-quality review, dashboards, charts, analytical reports, 数据分析, 指标诊断, 数据质量, 分析报告, or when the user wants a shareable offline HTML/ZIP/Markdown/PDF result. Produces the…