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-telemetrynpx skills add Peiiii/nextclaw --skill development-task-telemetrygit 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 | $0.00044 | $0.01187 |
| Opus 5 | $0.00022 | $0.00593 |
| Sonnet 5 | $0.00009 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
development-task-telemetry 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Task Telemetry
定位
作为开发生命周期的可选只读 observer,声明可移植的任务/阶段边界。只观察 lifecycle 已决定的状态,不改变阶段、返工、完成门或模型路由,不自报 Token 数值。
激活
- 根任务加载本 Skill 后,以
task=start激活;子 Agent 只有拿到父任务传入的 task-id 和当前 phase 后才能用task=join激活。 - marker 必须附着在原本就要发送的进度或最终消息第一物理行,位于
[我严格遵守规则]、[深思模式]等前缀之后;除用户显式要求收尾汇报外,禁止为 marker 新增消息、模型调用或工具调用。 - 只在真实 task / phase 转换时输出;同一阶段的普通进度不重复输出。
- 加载失败时说明
telemetry unavailable并继续开发,不得阻塞任务。 - 触达 marker、解析或默认收尾汇报时,必须运行定向测试,并以真实 rollout 和同一 task-id 复验报告;静态规则检查不能替代。
固定合同
根任务开始:
[nextclaw.dev/v1 task=start id=<task-id> name="<task-name>" type=<task-type> phase=<phase>]
子 Agent 加入:
[nextclaw.dev/v1 task=join id=<task-id> phase=<phase>]
当前线程切换阶段:
[nextclaw.dev/v1 phase=<phase>]
子 Agent 离开:
[nextclaw.dev/v1 task=leave id=<task-id> status=<status>]
根任务结束:
[nextclaw.dev/v1 task=end id=<task-id> status=<status>]
字段顺序和拼写固定。task-type 只允许 feature、bugfix、small-change,原样记录 lifecycle 已冻结的类型,不自行推断或修正;phase 只允许 task-understanding、design、implementation、validation、review、delivery、retrospective;status 只允许 completed、blocked、cancelled、failed。
根任务生成一次 dt- 加 8 位小写十六进制 task-id,并在 reopen 时复用。task-name 使用能让人直接识别目标的简短名称,建议 8–30 个字符,最多 64 个字符,不含 "、] 或换行;reopen 时保持原名称和类型。子 Agent 原样复用父任务 ID,禁止自行生成或重新分类。解析器继续兼容缺少 name 或 type 的历史 task=start marker,但新 marker 必须同时提供名称和类型;历史缺失值保持未知,不从自然语言猜测。
每条 assistant 消息首行最多一个 marker。不要在首行示例、引用、用户内容、工具输出或总结中伪造 marker。
AI 查询与汇报
用户说“查看统计”“这个任务用了多少 Token”或给出 task/thread/session ID 时,AI 是查询入口:自己定位并运行脚本,禁止把命令交给用户执行。定位顺序是显式 task-id、当前上下文最近的 marker、用户给出的 thread/session ID;仍有多个候选时先列出简短候选,不猜测归属。
node .agents/skills/development-task-telemetry/scripts/report-task-phase-usage.mjs --sessions-root ~/.codex/sessions [--thread <thread-id>] [--task <task-id>] [--format json]
AI 默认文本回答,需要比较或计算时用 JSON。按需报告给任务类型、总 Token、阶段占比、模型/effort、调用与工具轮次、耗时、覆盖率和警告;无 marker 时只报告可观察总量并说明不能可靠分阶段。
启用 observer 的根开发任务默认收尾汇报:把 task=end 附在完成进度首行,待该 frame 落盘后按 task-id 运行脚本,最终答复末尾附 Token:约 <total>(输入 <input> / 输出 <output>,覆盖率 <coverage>);只追加最关键警告。统计截止 task=end,后续 observer 开销不递归计入任务。
What ships with it
12 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 244 B
- dashboard/index.html 6.0 KB
- dashboard/task-telemetry-dashboard.css 9.6 KB
- dashboard/task-telemetry-dashboard.js 14 KB runs code
- scripts/lib/codex-rollout-adapter.mjs 4.6 KB runs code
- scripts/lib/task-phase-analyzer.mjs 15 KB runs code
- scripts/lib/task-phase-protocol.mjs 3.8 KB runs code
- scripts/lib/task-telemetry-dashboard-server.mjs 11 KB runs code
- scripts/report-task-phase-usage.mjs 6.2 KB runs code
- scripts/report-task-phase-usage.test.mjs 16 KB runs code
- scripts/serve-task-telemetry-dashboard.mjs 5.8 KB runs code
- scripts/serve-task-telemetry-dashboard.test.mjs 6.2 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 · 75 lines · 44 tokens per session scan A 2354557df4f5
development-task-telemetry is a skill published in the GitHub repository Peiiii/nextclaw (253 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,187 once invoked, about $0.0002 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-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-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-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…
feishu
Use when the user mentions 飞书 / Feishu / Lark workspace operations: docx (云文档) read/write, bitable (多维表格) records / views / dashboards, drive (云盘) upload/download, wiki (知识库) link resolution, approval (审批) instance create/cancel/query, calendar (日历) event create/list/update + attendees, contact (联系人) user/department…