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/voidtechnology/voidtech-claude-plugins/goalnpx skills add VoidTechnology/voidtech-claude-plugins --skill goalgit clone --depth 1 https://github.com/VoidTechnology/voidtech-claude-pluginsWhat 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 | $0.00106 | $0.00863 |
| Opus 5 | $0.00053 | $0.00432 |
| Sonnet 5 | $0.00021 | $0.00173 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
goal 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.
What it actually says
goal — 启动工程内循环
把一个完成条件可机器判定的任务交给确定性控制器无人值守推进。控制器逐轮驱动受限 worker、生成 checkpoint、对指定 commit 跑 eval；eval 全部通过只产生 EVALS_PASSED，合入永远由人执行。
何时用 / 何时不用
- 用：目标能落到一条命令的退出码上——修测试到
npm test退出码 0、消 TS 错误到tsc --noEmit退出码 0、按契约测试实现接口。 - 不用：完成条件靠产品 taste / 用户研究 / 主观判断（“让代码更好”）。这类任务先用
/voidtech-loop:goal-spec破题，或根本不适合循环。
执行方式
-
从用户输入解析任务描述与参数。简单模式（单一验收命令）直接构造：
${CLAUDE_PLUGIN_ROOT}/scripts/loop goal "<任务>" --check "<命令>" --max-iterations <N>任务复杂（多 target、invariant、protected paths、自定义 cwd/env）时，先让用户走
/voidtech-loop:goal-spec生成 spec，再用--spec <file>启动。 -
不要替用户猜
--max-iterations：它必须由用户显式给出。缺失时停下来问一次。 -
用 Bash 运行上述脚本。脚本在前台完成启动体检（试点 OS、版本、Git、基线 eval）、获取项目锁、创建循环分支与 worktree 并写入初始状态，随后 detach 后台控制器、等其握手回执后返回：成功时直接输出 run ID，失败时输出具体失败阶段与原因（退出码非零）——失败不会假报“已启动”。
-
spec 含
shell: true的 eval 或setup命令时，脚本会完整展示这些命令并以退出码 2 要求确认；把命令清单转达给用户，得到明确同意后再追加--allow-shell重新启动，不得替用户默认加上。 -
把脚本输出的 run ID、循环分支和
loop status/loop cancel提示原样转达给用户。不要声称任务已完成——完成与否由后续 eval 与人工accept决定。
边界
- 循环不自动 push、merge、建 PR 或改写用户分支。
- 运行期中断走
${CLAUDE_PLUGIN_ROOT}/scripts/loop cancel <runId>（幂等）；交互会话的 Ctrl+C 不影响已 detach 的守护进程。 - 查看进度：
${CLAUDE_PLUGIN_ROOT}/scripts/loop status [runId]。 EVALS_PASSED后复核接受：${CLAUDE_PLUGIN_ROOT}/scripts/loop accept <runId>。
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 First seen · 38 lines · 106 tokens per session scan A 99ecdfff348e
goal is a skill published in the GitHub repository VoidTechnology/voidtech-claude-plugins (2 stars, last pushed 28d ago), licensed Apache-2.0. It adds 106 tokens to every session and 863 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…