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/capability-adaptationnpx skills add BuildrAI/Buildr --skill capability-adaptationgit 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/capability-adaptation)<a href="https://agentmods.dev/skills/buildrai/buildr/capability-adaptation"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/capability-adaptation.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 | $0.00096 | $0.01396 |
| Opus 5 | $0.00048 | $0.00698 |
| Sonnet 5 | $0.00019 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
capability-adaptation 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作能力适配
本 Skill 承载 Agent 工作能力适配(Agent-managed Capability Adaptation)。用户只拥有工作意图和关键决策;Agent 维护工作资产;Buildr 维护依赖结构和 runtime 投射;capability contract 只保护跨 Skill 最小协作边界。
1. 建立影响基线
- 解析 Buildr workspace、实际 scope 和当前 Agent,运行
buildr doctor --agent <agent> --target <workspace> --json。 - 读取目标 Skill 源、
skills/manifest.yml、相关 contracts、当前 bindings 和 doctorcapabilitiesgraph;同时区分 Agent runtime 基于 description 的入口发现与 Skill 加载后的 dependency resolution。routing evidence 存在时,只在对应产品入口已经命中的前提下检查其内部用户意图覆盖。 - 列出目标 Skill 提供的 capabilities、直接/递归 consumers、required/optional mode、当前 selected provider 和修改后的 blocked/degraded 风险。用户无需知道这些资产名称。
- 修改 Buildr builtin 时不得直接编辑用户 workspace 中的受管副本;组织差异使用组织自有 provider,Buildr 产品行为变化走产品 change。
2. 判断如何落地
按以下顺序选择最小变化:
- 只属于单个 Skill 内部,且不被组合、不需替换、consumer 不依赖稳定保证或结果证据、生命周期无需影响诊断:普通 Skill 维护,不创建 contract。
- 触达已有 contract 且变化位于
Allowed Variations:修改用户自有 provider,或为 builtin 创建组织 provider;保持 contract identity 和 guarantees。 - 另一工作流无法在缺少该能力的稳定保证或结果证据时安全继续、需要替换实现,或生命周期需要影响诊断:创建最小 contract 和
provides/requires。不要因为 Agent 执行时会同时读取多个 Skills,就把它们建模为方法调用依赖。 - 新行为突破既有前置条件、副作用、授权、结果证据或失败语义:升级 contract major version,或同步修改 consumers;不得把不兼容实现继续声明为旧版本 provider。
判断的是稳定协作边界,不是用户是否说出 capability 名字。命令、算法、merge/rebase policy 和组织工具留在 provider;只有 consumer 无法安全继续时依赖的保证进入 contract。
3. 先开发候选,再改变当前实现
- 在 canonical task worktree 或任务候选目录中修改或创建 Skill,记录当前 provider、binding 和 source integrity;不得先卸载或覆盖当前有效实现。
- 为候选写清触发 description、职责边界、授权/停止条件和结果证据。实现既有 contract 时逐项核对 contract;新增 contract 时使用最小 frontmatter 和固定语义章节。替换顶层入口 capability provider 时,必须验证新 provider 的 description 覆盖原用户意图,并检查旧入口或其他 Skill 是否造成触发歧义;binding ready 不能替代这项验证。
- 运行 Skill frontmatter/package 静态检查、provider 专项测试和每个受影响 consumer 的组合场景。
ready只表示结构可路由,不能替代行为证据。 - 候选不满足 contract、组合验证失败或计划会产生用户未接受的 blocked consumer 时停止;保留当前实现和 binding,向用户说明真正需要决定的语义差异。
4. 激活与恢复
- 使用
buildr skills add ... --provides/--requires或--replace写入已验证候选;不要要求用户手改 manifest。 - 安装新 provider 不会自动改变流程。确认候选可见后使用
buildr skills bind <capability>@<version> --provider <skill-id> --scope <scope> --target <workspace>显式选择。 - 在新 binding ready 之前不卸载旧 provider;一个 Skill 提供多个仍被使用的 capabilities 时,逐项检查后才能完整卸载。
- 执行当前 Agent 的
buildr sync或最小 scope render,再运行最终 doctor,核对受影响 consumers、runtime paths,以及已加载产品入口内部适用的 routing evidence。顶层入口发生替换时,同时确认 selected provider 已投射到 runtime,且入口 description 与激活计划一致。 - 激活后出现新的结构 error 时,使用记录的旧 binding 恢复选择并重新 doctor;不得留下明知 blocked 的半完成适配。已经发生且无法安全自动恢复的外部副作用必须如实报告。
What ships with it
1 file 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.
- 5d ago First seen · 57 lines · 96 tokens per session scan A 97de3f4aa27d
capability-adaptation is a skill published in the GitHub repository BuildrAI/Buildr (24 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,396 once invoked, about $0.0005 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…