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/aisee-lab/aisee-plugin/aisee-initnpx skills add AISEE-LAB/aisee-plugin --skill aisee-initgit clone --depth 1 https://github.com/AISEE-LAB/aisee-pluginWrote 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/aisee-lab/aisee-plugin/aisee-init)<a href="https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-init"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-init.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 | $0.00134 | $0.03537 |
| Opus 5 | $0.00067 | $0.01768 |
| Sonnet 5 | $0.00027 | $0.00707 |
| Haiku 4.5 | $0.00013 | $0.00354 |
Grade A, and why
aisee:init scanned grade A with 1 finding 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
node -e "const {execSync}=require('child_process'); try { execSync('openspec --version',{stdio:'ignore'}); console.log('openspec:ok'); } catch { console.log('openspec:missing'); }" How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aisee:init
对外 skill 名称是 aisee:init;目录名保持 aisee-init/。执行脚本时从当前 skill 目录解析 <skill-dir>/scripts/...;安装后的 hook 命令只引用目标项目内 aisee/hooks/。
目标
把一个项目整理成 OpenSpec 驱动的 Aisee 项目配置。
本 skill 是项目接入 / 治理阶段能力,不是默认新功能迭代 happy path 的必经节点。对于已经接入并正常运行 OpenSpec 工作流的项目,只有在配置缺失、hooks 漂移、memory 缺口、目录迁移或治理审计时才应再次触发。
适用前提:
- 项目已经在使用 OpenSpec;或
- 用户明确要把当前项目接入 OpenSpec / Aisee。
如果用户明确表示当前项目不使用 OpenSpec,且也不打算接入 OpenSpec,本 skill 不适用;不要生成 OpenSpec 风格的项目 AGENTS.md、openspec/project.md、hooks 或 aisee/ 规划布局。
本 skill 负责:
AGENTS.md:当前 Codex target 的项目规则、OpenSpec 工作流、工具调用约束、沙箱和验证要求。openspec/project.md:项目事实、技术栈、架构、开发命令;不放 AI 行为规则。aisee/docs/requirements/、aisee/docs/spec-migration/、aisee/docs/change-plan/:Aisee 当前主推链路相关目录。aisee/memory/rules.md与aisee/memory/index.md:项目本地记忆规则和记忆入口。aisee/docs/reflect/:会话复盘和 memory 候选区;不替代aisee/memory/。- 当前支持的 hook target 是 Codex:
.codex/hooks.json与.codex/config.toml。 aisee/hooks/:本技能安装到目标项目的 hook 脚本目录;runtime 从这里执行脚本,不依赖 skill 安装路径。
非目标:
- 不生成非 Codex hook target 配置。若用户需要其他 agent runtime,先输出差异和待设计项,不要套用 Codex hook 协议。
- 不安装或维护 OpenSpec custom schemas。
先决条件
执行任何初始化、审计或优化前,先确认项目已由 OpenSpec 初始化:
node -e "const fs=require('fs'); for (const [p,t] of [['openspec/specs','dir'],['openspec/changes','dir'],['openspec/changes/archive','dir']]) { try { const s=fs.statSync(p); console.log(p + ':' + ((t==='dir'?s.isDirectory():s.isFile())?'ok':'bad')); } catch { console.log(p + ':missing'); } }"
node -e "const {execSync}=require('child_process'); try { execSync('openspec --version',{stdio:'ignore'}); console.log('openspec:ok'); } catch { console.log('openspec:missing'); }"
如果缺少 openspec/specs/ 或 openspec/changes/,先判断用户是否明确要接入 OpenSpec:
- 若用户明确要接入:优先运行
aisee openspec ensure --json,并解析 JSON 结果;该命令会按当前 agent runtime 自动选择 OpenSpec tools(Codex 默认是codex;无法识别时回退到none),默认启用 Aisee 需要的 expanded workflow,确保 OpenSpec 的项目内 instructions / skills 已安装或已刷新。 - 若用户未明确要接入,或明确表示当前项目不使用 OpenSpec:停止,并说明
aisee:init不适用;不要生成项目级AGENTS.md或其它 OpenSpec/Aisee 配置文件。
What ships with it
11 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.
- agents/openai.yaml 275 B
- assets/codex-agents-template.md 6.1 KB
- assets/memory-index-template.md 652 B
- assets/memory-rules-template.md 2.9 KB
- assets/openspec-project-template.md 2.0 KB
- evals/evals.json 16 KB
- references/layout-migration.md 1.6 KB
- scripts/hooks/prompt-scan.js 3.4 KB runs code
- scripts/hooks/session-inject.js 9.3 KB runs code
- scripts/hooks/spec-drift.js 9.0 KB runs code
- scripts/setup-hooks.js 6.2 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.
- 4d ago First seen · 213 lines · 134 tokens per session scan A 891eb4a6b021
aisee:init is a skill published in the GitHub repository AISEE-LAB/aisee-plugin (11 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 3,537 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
openase-platform
Platform operations for tickets, projects, and runtime coordination inside OpenASE.
ticket-workpad
Maintain the persistent ticket work log comment on the current ticket and use it as the execution log.
task-breakdown
Turn a clarified spec into milestone-oriented tickets, dependency edges, and stage-gated delivery lanes.
report-issue
Create a detailed GitHub issue for OpenASE and add it to the OpenASE Automation project with a caller-selected status (defaults to Todo). Use when asked to report a bug, deployment regression, local repro, or design task into GitHub with reproducible evidence and project binding.
codex-sdd:plan
Create design.md with technical architecture and tasks.md with executable breakdown from an approved proposal. Second phase of OpenSpec workflow.
codex-sdd:tapd-openspec-proposal
Fetch TAPD story requirements before OpenSpec proposal generation. Use when the user asks OpenSpec propose with a TAPD story URL/id, says to import TAPD requirements, or asks to generate proposal.md from TAPD.