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 rexleimo/aios --skill implement-specgit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/implement-spec)<a href="https://agentmods.dev/skills/rexleimo/aios/implement-spec"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/implement-spec/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/rexleimo/aios/implement-spec"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/implement-spec.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00091 | $0.01023 |
| Opus 5.5 | $0.00036 | $0.00409 |
| Sonnet 5.5 | $0.00018 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
implement-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 9d 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.
What it actually says
Implement-Spec（整份 spec → 并行实现 → 收口）
交付链的执行入口：输入一份 spec（含验收标准与工作项），把它整份实现完。不重造调度器——把既有入口按序接起来：/plan（依赖分组）→ aios work（并发派发，需批准）→ /review（审查收尾）。本入口只由用户显式触发，不自动进入。
前置检查（缺一就停，先补齐，不猜）
| 缺什么 | 先补什么 |
|---|---|
| spec 含糊 / 缺验收标准 | /grill 或 /spec |
| 无工作项 / 无依赖分组 | /tickets 或 /plan |
| 工作项文件所有权重叠 | 重划边界；画不清就串行，不硬派 |
执行顺序
- 读 spec 建任务图：工作项是带阻塞关系的任务图，不是步骤列表。取当前前沿（无阻塞、可同时开工的集合）——即
/plan产出的依赖分组；没有就先跑/plan。 - 探索（可选）：需要摸代码或查外部资料时，先派只读探索子代理，笔记写到
.aios/（不入库），供实施子代理引用——实施阶段专注写码而非探索。 - 核对可并行性：按
aios-work-dispatch准入条件核对（≥2 个独立工作项、文件所有权不重叠、无严格前后序）。不满足 → 串行逐项/implement。 - 派发实施：
aios work预览 → 人工显式批准 → 后台并发执行；需要隔离与可续的长工作项用aios harness（自带 worktree）。并行工作项各占一个 worktree，开工前确认基于同一集成基点。 - 推进前沿：某项完成并在任务图上解锁新前沿 → 继续派发（保持最大并发）；仍被阻塞的不派。
- 集成分支收口：多 worktree 先汇到一条集成分支确认整体一致（回归 + 交叉依赖），再回主线流程。
- 审查收尾：整合结果跑
/review（标准与规格双查）；提出的问题一次性修完，重跑验证。 - 清理与报告：清理 worktree；未达验收标准的工作项如实列出，不勾掉。
通讯纪律（子代理之间）
通讯尽量稀疏，主要走上下文指针：spec、工作项、探索笔记、commit。不复制已可由指针取得的信息。
完成判据（缺一不得报完成）
- 每条验收标准都有对应执行证据（真实命令输出），不是勾选框；
/review无未处理项；- 任务图所有工作项收口，或如实列出未完成项与原因；
- worktree 已清理。
与其他入口的边界
- 单工作项 / 小改动：直接
/implement或/single，不走本入口。 - 多个独立工作项的一次性并发：
/team。 - 一个长且可续的目标：
/harness。 - 本入口的语义 = 一份 spec 的完整落地（跨多轮、多工作项）。
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.
- 9d ago First seen · 54 lines · 91 tokens per session scan A d8329d9fa248
implement-spec is a skill published in the GitHub repository rexleimo/aios (61 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 1,023 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
development-workflow
Spec-driven development lifecycle — EARS requirements, technical design docs, implementation tracking, and contribution guidelines. Use when planning features, defining requirements, or managing project lifecycle.
kirby-project-tour
Maps a Kirby project using Kirby MCP tools/resources, including roots, templates, snippets, controllers, models, blueprints, plugins, runtime status, and key config. Use when a user wants a project overview, file locations, or a quick orientation before making changes.
survey
Propose handrail Rules for the current repository from the facts it states (lockfiles, CI workflows, .env files, git hooks and more) and the prohibitions its instruction files write down, with per-rule approval. Also proposes rules from the user's own CLAUDE.md or AGENTS.md when asked. Use when the user wants rules…
git-worktree-workspaces
Sets up and uses Git worktrees for parallel task workspaces in the same repository clone, including safe cleanup of local worktrees. Invoked when the user asks to work on multiple branches at once, isolate tasks without extra clones, or create/remove worktrees.
pm-ticketing-integration
Ticket-driven development protocol.