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 skills add BuildrAI/Buildr --skill buildr-releasegit 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/buildr-release)<a href="https://agentmods.dev/skills/buildrai/buildr/buildr-release"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/buildr-release/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/buildrai/buildr/buildr-release"><img src="https://agentmods.dev/badge/skills/buildrai/buildr/buildr-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00052 | $0.02303 |
| Opus 5.5 | $0.00021 | $0.00921 |
| Sonnet 5.5 | $0.00010 | $0.00461 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
buildr-release 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 yesterday.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buildr 发布
日常修改涉及初始化、安装、源码包或验证工具时，使用现有受影响入口覆盖相关链路，不等发布才检查。候选运行期间不改源码；同轮先跑完独立检查、汇总失败，取得用户同意后修复；接续只重跑失败项并首次执行未执行项。定位源码检查失败直接使用现有 test:focus -- <step-id>，正常日志保留用例名称和耗时，同轮已通过的真实结果直接采用，不再手写旁路诊断后重复跑一次。原包失败继续使用准确原包的原验包入口，不重新制包。
本技能（Skill）拥有 Buildr 自举工作空间的发布流程与随附发布代码，不作为 npm 内置技能分发。先读唯一流程正文 projects/product/knowledge/docs/flows/open-source-release.md：固定候选、跑测试、打包、验包、发布。人决定目标和公开授权；智能体（Agent）按当前事实推进。
执行入口
发布代码的唯一源是所选源码检出位置的 skills/buildr-release/scripts/。从该位置的 projects/product/services/buildr/ 使用 tools/development/run-development-node ../../../../skills/buildr-release/scripts/release-orchestration-runner.ts --help 查看当前参数，再调用 prepare、inspect、publish --authorized 或 resume。投射到智能体的技能副本用于发现和指引；不要从投射目录运行绑定源码的脚本。工作流（Workflow）也调用同一源码脚本。
正常准备和接续使用 --wait，由程序等待同一远端运行，每次状态变化只返回简短进度；默认最多等待 30 分钟，可用 --wait-timeout-ms 调整。默认输出摘要；需要原始证据时使用 --output <file>，仅诊断具体问题时使用 --detail full。等待期间不反复调用 inspect 或读取全部日志；真实失败、缺少本机证明或授权时，程序返回对应缺项。
冻结所选包、独立版本、分支（Branch）、准确提交（Commit）、源码树和准确对端，正常准备不跟随 dev。全部检查及结果汇总交给产品既有验证框架；先查看本轮普通日志中的成功、失败、未执行项和耗时，再只执行失败及未执行部分。不要因阶段切换重复执行仍有效的检查；一轮集中收集互不依赖的失败，经用户同意修复后只补失败及未执行项。同一发布轮内源码输入变化时，使用 source.ts --invalidate <step-id,...> 只重跑受影响步骤，其余通过记录继续采用；新候选轮次（新版本或新选择）从头完整执行。修复确认并提交版本材料后，直接以本次 selectionId/roundId 运行源码轮并写入候选 round 路径，使该轮成为候选证据；不要先跑一套独立全量再重复候选全量。本机能充分证明的在本机完成，GitHub 只补真实平台、干净环境或受保护执行边界。相关开发检查在改动交付前完成，避免到发布时才修过时检查。不要在检查运行时改变其源码或共享 Git 比较事实。
通用产品逻辑与功能只有一套，不按系统重复。操作系统相关的源码和原包检查是独立节点：本机是 macOS 就本机完成 macOS、远端补 Windows；本机是 Windows 则交换。源码入口 test/verification/source.ts --round <selection-id> --output <round-log.json> --scope common|platform|all 使用同一检查登记；默认先满足本机源码，远端补另一系统源码，全部通过后 GitHub 生产唯一原包。
README 固定标题、章节和编辑表达不作发布门槛。检查失败先判断是否保护功能、安全或交付正确性，无独立价值的措辞检查直接删除；必要的文档链接、渲染、资源引用和敏感信息检查按实际影响选择，不因文档改动追加整组快速检查，也不为技能（Skill）正文另写措辞断言。架构及规范静态检查留在相关开发检查中，不加入候选必跑集合。插件本机源码预检使用 tools/verify-source.ts（可用 --round <selection-id> --output <round-log.json> --invalidate <step-id,...> 保存普通结果），无需准备软件开发工具包（SDK）或旧主包对端；准确候选配对仍保留完整检查。
新准备把通用原包检查与本机系统验包留给本机。制包上传后，下载同一原包，与另一系统的远端验包并行；使用实际 Node 24.15.0 运行 tools/development/run-development-node test/verification/artifact.ts --artifact-dir <原包目录> --output <证据目录>，默认一次检查通用原包、本机启动和最低 Node，不另跑当前版本。--scope common 只检查通用原包，--scope platform 只检查本机系统；macOS 和 Windows 对称选择，互不附带另一系统或已完成的通用检查。实际程序与系统随结果保留。local-artifact-verification-required 或远端 incomplete 表示仍等本机缺项，不是完整候选通过；完成后继续原 prepare --artifact-verification <证据目录>，仅采用原包与有效结果、补缺项和完整汇总，不重新产包。远端发布始终另需准确授权。
What ships with it
51 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.
- scripts/application-payload-entry.ts 1.8 KB runs code
- scripts/application-payload.ts 15 KB runs code
- scripts/candidate-failed-shard-retry.ts 15 KB runs code
- scripts/candidate-package.ts 4.1 KB runs code
- scripts/candidate-repair-operation.ts 6.5 KB runs code
- scripts/candidate-source-binding.ts 16 KB runs code
- scripts/candidate-step-timings.ts 4.9 KB runs code
- scripts/dsh-plugin/candidate-adoption.ts 2.9 KB runs code
- scripts/dsh-plugin/release-candidate.ts 13 KB runs code
- scripts/dsh-plugin/release-workflow.ts 27 KB runs code
- scripts/dsh-plugin/release.ts 8.9 KB runs code
- scripts/dsh-plugin/trusted-publish.ts 28 KB runs code
- scripts/environment-approval.ts 2.5 KB runs code
- scripts/github-release-ensure.ts 9.4 KB runs code
- scripts/mysql-connection-entry.ts 288 B runs code
- scripts/package-artifact-observation.ts 15 KB runs code
- scripts/package-compatibility.ts 15 KB runs code
- scripts/package-pair-diagnostics.ts 2.2 KB runs code
- scripts/package-release-operation.ts 54 KB runs code
- scripts/package.json 42 B
- scripts/plugin-hosted-release.ts 25 KB runs code
- scripts/registry-version-state.ts 12 KB runs code
- scripts/release-artifact.ts 20 KB runs code
- scripts/release-authority-oidc-probe.ts 10 KB runs code
- scripts/release-authority-preflight.ts 14 KB runs code
- scripts/release-authority.ts 2.0 KB runs code
- scripts/release-contract.ts 4.5 KB runs code
- scripts/release-convergence.ts 12 KB runs code
- scripts/release-execution-binding.ts 14 KB runs code
- scripts/release-executor-admission.ts 8.0 KB runs code
- scripts/release-executor-recovery.ts 12 KB runs code
- scripts/release-failure.ts 2.2 KB runs code
- scripts/release-files.ts 5.6 KB runs code
- scripts/release-git-convergence.ts 49 KB runs code
- scripts/release-lifecycle.ts 6.0 KB runs code
- scripts/release-notes.ts 2.6 KB runs code
- scripts/release-observation.ts 6.5 KB runs code
- scripts/release-orchestration-runner.ts 112 KB runs code
- scripts/release-package-evidence.ts 16 KB runs code
- scripts/release-phase-timeline.ts 10 KB runs code
- scripts/release-publication.ts 18 KB runs code
- scripts/release-readiness.ts 18 KB runs code
- scripts/release-rehearsal.ts 32 KB runs code
- scripts/release-selection.ts 54 KB runs code
- scripts/release-tag-ensure.ts 7.8 KB runs code
- scripts/release-targets.ts 9.8 KB runs code
- scripts/release-task-evidence-correlation.ts 12 KB runs code
- scripts/release-transaction-evidence.ts 26 KB runs code
- scripts/release-transaction-runner.ts 34 KB runs code
- scripts/runtime.ts 482 B runs code
- scripts/trusted-publish.ts 6.8 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.
- yesterday Changed 146383f5e978
- 5d ago Changed · +14 lines 3e2470a19f03
- 7d ago Changed · +14 lines 146887f2b4c8
- 9d ago Changed · -24 lines · +2 tokens per session 5c4f1f3143a7
- 25d ago Changed · +1 lines 809ec135c41b
- 1mo ago Changed b8fa2208f1d1
- 1mo ago Changed · -99 lines · -47 tokens per session 36c0da05b850
- 1mo ago Changed 711a0b3b0a05
- 1mo ago First seen · 135 lines · 97 tokens per session scan A 6fd782f916a5
buildr-release is a skill published in the GitHub repository BuildrAI/Buildr (28 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,303 once invoked, about $0.0002 per session on Opus 5.5. 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
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.