goal-spec

A tool for turning a complex coding goal into a structured specification for an automated improvement loop. It checks the repository for existing tests and commands, then separates requirements into machine-checked goals, safeguards, manual checks, and excluded work.

In plain words
What is it for?
Use it for multi-part coding tasks that need tests, protected files, budgets, environment details, validation, and a baseline check before automated changes begin.
Why use it?
It prevents an automation loop from relying on invented commands or vague success criteria. It also checks the starting state before suggesting that the loop run.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/voidtechnology/voidtech-claude-plugins/goal-spec
Any agent
npx skills add VoidTechnology/voidtech-claude-plugins --skill goal-spec
Clone the repo
git clone --depth 1 https://github.com/VoidTechnology/voidtech-claude-plugins

Made for: Claude Code, Codex.

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00110 $0.00989
Opus 5 $0.00055 $0.00495
Sonnet 5 $0.00022 $0.00198
Haiku 4.5 $0.00011 $0.00099

Measured yesterday against content hash e88414a0c809, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goal-spec 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.

plugins/voidtech-loop/skills/goal-spec/SKILL.md · 48 lines

What it actually says

goal-spec — 复杂任务到 Goal Spec 的编译器

把语言描述的复杂任务编译成一份可被控制器执行、经过校验和基线验证的 Goal Spec。这是编译器,不是通用 YAML 编辑器:只负责编译并验证草稿是否满足启动条件,绝不启动循环、不改业务代码、不实现第二套校验逻辑、不把不可机器判定的产品要求伪装成 eval。

执行流程(PRD 4.1)

  1. 探查仓库:用 Read/Grep/Glob 找出已有的测试、构建、CI 与项目规则命令,不发明不存在的命令。找不到对应命令时标记缺口并问用户,不要编造。

  2. 归档每项要求为四类之一:

    • target——本轮必须达成的、可机器判定的变化(绝对退出码;一期不支持相对基线比较器);
    • invariant——不得退化、且在 base commit 上已成立的守护条件;
    • manual_review——只能人工确认的产品/设计要求,进报告不进 eval;
    • out_of_scope——明确不做的(含相对基线指标,一期归此并提示二期)。
  3. 复杂度闸门:单 target、默认能力、可用一条安全命令表达的任务不生成 YAML,直接返回一行 --check 启动命令,引导用户用 /voidtech-loop:goal

  4. 复杂任务补齐 protected paths、预算、cwd、环境;需要网络/外部服务/自定义 worker 能力时拒绝并说明不属于一期。草稿默认写入 .voidtech-loop/specs/<slug>.yaml

  5. 校验(唯一入口,禁止另写规则)

    ${CLAUDE_PLUGIN_ROOT}/scripts/goal-spec validate .voidtech-loop/specs/<slug>.yaml --json
    
  6. 基线 dry-run

    ${CLAUDE_PLUGIN_ROOT}/scripts/goal-spec baseline .voidtech-loop/specs/<slug>.yaml --json
    

    spec 含 shell: true 的 eval 或 setup 命令时,该命令会完整展示将执行的 shell 命令并以退出码 2 停止。把命令清单转达给用户;只有得到明确同意后,才可追加 --allow-shell 重新执行。baseline 与正式启动共用同一确认门,不得替用户默认确认。

    裁定规则:全部 target 已满足 → 报告“目标在基线已满足”,不交付可启动结论;任一 invariant 基线不成立 → 要求改角色或先修基线;命令超时/需未声明网络/未声明副作用 → 停止,不交付“可启动”。只有“至少一个 target 未满足且全部 invariant 成立”才可启动。

  7. 输出:目标/不变量摘要、基线结果、固定 best-effort 能力、manual review 清单,以及准确的启动命令:

    ${CLAUDE_PLUGIN_ROOT}/scripts/loop goal --spec .voidtech-loop/specs/<slug>.yaml
    

    若已为同一冻结 spec 明确确认过 shell 命令,启动命令追加 --allow-shell;否则保留确认门。绝不自动启动循环、绝不修改业务代码。

参考

字段规则与角色语义见 references/authoring-rules.md;它与 schemas/goal-spec.schema.json 同源,任何调用方不得复制字段清单或另写宽松校验。

Files

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.

Changes

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.

  1. yesterday First seen · 48 lines · 110 tokens per session scan A e88414a0c809

Subscribe to this mod's changes

goal-spec is a skill published in the GitHub repository VoidTechnology/voidtech-claude-plugins (2 stars, last pushed 28d ago), licensed Apache-2.0. It adds 110 tokens to every session and 989 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens