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/buildrai/buildr/declaration-intakenpx skills add BuildrAI/Buildr --skill declaration-intakegit clone --depth 1 https://github.com/BuildrAI/BuildrWrote 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/buildrai/buildr/declaration-intake)<a href="https://agentmods.dev/skills/buildrai/buildr/declaration-intake"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/declaration-intake.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.01083 |
| Opus 5 | $0.00039 | $0.00541 |
| Sonnet 5 | $0.00016 | $0.00217 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
declaration-intake 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 4d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Declaration Intake Skill
本 Skill 是 Project Declaration Intake 的 Agent 编排入口。它只管理两类 Project-owned 长期声明：
projects/<project>/preparation.yml：怎么准备 Task Environment；projects/<project>/verification.yml：怎么验证 Task 交付目标。
Intake 不保存状态、不拥有 schema 或 writer，也不管理 capabilities.yml、commands.yml。缺少 Skill/provider 时交给 Capability 体系；缺少 CLI/runtime 时只报告 Commands/Doctor 诊断。
1. 确认触发与范围
识别 trigger：Project 注册、Service 注册、首次 Task scope、依赖/构建/测试入口变化、Environment declaration/Recipe gap、Verification coverage gap，或用户显式初始化/刷新。
只使用已登记 Project 和本次明确 Project/Service scope。Project-only 不虚构 Service；多 Service 分别列出事实与候选，不复制其他 Service 的结论。不得递归扫描整个仓库、按目录名猜技术栈，或读取 Task lifecycle/current projection 作为声明来源。
2. 只读 Discovery
读取以下最小事实：
- Project/Service registry、各 scope 的真实根与适用规则；
- 当前
preparation.yml、verification.yml和所属 schema； - 明确的 package/build/test wrapper、lockfile或配置、CI与项目文档；
- 当前 Commands/Capability readiness，仅用于外部依赖诊断。
对每个 scope 输出：trigger、当前声明状态、Preparation Recipe 候选/差异、Verification Capability 候选/差异、证据、外部缺口和建议写入。没有稳定事实时标记 gap，不创建技术栈 adapter、测试、wrapper 或工具安装方案。
Discovery、Project/Service 注册、Buildr Web GET、Doctor、Environment inspect 与 Task Finish 均不得创建、修改或删除长期声明。
3. 区分 routine maintenance 与用户决定
任何写入前都先展示精确diff，并按以下closed条件分类：
routine-maintenance：只让声明追上当前用户目标和已登记scope内已经确认的wrapper、lockfile、build/test入口或既有authority；不新增/删除Project或Service scope，不改变discovery、usable targets或affected/full/provider边界，不引入capability、外部效果、安全例外，且authority无冲突。Agent可以在当前用户目标授权内直接交给owner维护并验证，无需让用户承担内部声明步骤。user-decision-required：新增/删除scope，改变discovery、usable targets或affected/full/provider边界，引入新的capability、外部效果或安全例外，或authority证据冲突。必须在写入前请求用户确认精确变化。
分类与展示至少包含：
- 精确目标文件；
- 新增、修改或删除的 Recipe/Capability identity 与 scope；
- 关键 invocation、inputs/outputs、environment/effects 差异；
- 尚未解决的 Commands/Capability 或测试建设缺口。
user-decision-required没有确认时只报告当前缺口与候选；不得用触发检查、Formal Task或一次宽泛确认覆盖两个文件、新增scope或其他长期决策。routine-maintenance也不得静默扩大scope、伪造capability或绕过owner，只是不为已确认事实重复请求人类授权。
4. 交给声明 owner
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.
- 4d ago First seen · 72 lines · 79 tokens per session scan A ddf90cc6dfb0
declaration-intake is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,083 once invoked, about $0.0004 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…