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 MarecGents/marec-agent-skills --skill skill-install-managergit clone --depth 1 https://github.com/MarecGents/marec-agent-skillsWrote 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/marecgents/marec-agent-skills/skill-install-manager)<a href="https://agentmods.dev/skills/marecgents/marec-agent-skills/skill-install-manager"><img src="https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/skill-install-manager/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/marecgents/marec-agent-skills/skill-install-manager"><img src="https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/skill-install-manager.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 | $0.00187 | $0.03624 |
| Opus 5 | $0.00093 | $0.01812 |
| Sonnet 5 | $0.00037 | $0.00725 |
| Haiku 4.5 | $0.00019 | $0.00362 |
Grade A, and why
skill-install-manager 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-install-manager
技能安装管理器 — 自动读取技能列表文件，与当前全局已安装技能进行对比，找出未安装或存在更新的技能，并执行一键安装/更新。v3.0：所有流程、判断、渠道切换均由脚本自动完成，agent 只运行脚本并读取 JSON 报告。
触发条件
用户表达以下任一意图时触发。即使只是暗示或间接提及技能安装/管理工作，也应使用本技能：
- "检查并安装缺少的技能" / "看看哪些技能还没装"
- "同步技能列表" / "同步 skills" / "skill sync"
- "更新所有技能到最新版本" / "检查更新" / "skill update"
- "技能管理" / "skill manager" / "管理技能"
- "批量安装 skills" / "安装这些技能" / "一键安装"
- "从技能列表安装" / "按列表安装"
- "帮我整理技能" / "技能状态" / "看看技能"
- "把新技能装上" / "补一下缺少的技能"
- "npx skills" / "skills add" / "技能仓库"
执行模式（v3.0：单一脚本驱动）
agent 不再逐条执行安装命令。 全部流程由 scripts/sync-skills.js 一次跑完，
agent 只做四件事：
- 运行主编排脚本（默认全自动同步，或按需加参数）
- 读取 JSON 报告（脚本写入
~/.agents/skill-sync-report.json） - 向用户汇报结果（脚本输出的控制台摘要可直接转述）
- 处理脚本标注的异常（见「异常处理」节，通常只需转告用户）
| 脚本 | 职责 | 何时用 |
|---|---|---|
scripts/sync-skills.js |
主编排：自更新→读列表→对比→依赖→安装→报告，全自动 | 默认入口，覆盖 99% 场景 |
scripts/install-skill.js |
单技能安装（五通道回退） | 只装/只更一个技能时 |
scripts/compare-skills.js |
只对比不安装（兼容旧入口，转发到 sync --compare） | 只想看差异时 |
scripts/utils.js |
共享工具模块 | 被以上脚本引用，不直接调用 |
快速开始
🟢 一键同步（默认，最常用）
node "<skill-path>\scripts\sync-skills.js"
全自动完成：自更新 → 读取最新列表 → 对比安装状态 → 版本检查（并发+缓存）→ 依赖预检 → 安装/更新（五通道回退）→ 生成报告。
Agent 操作步骤：
- 确认技能包路径（
pwd后定位skill-install-manager/scripts/，路径大小写敏感） - 运行上面的命令（超时 10 分钟；脚本内部有逐级超时与降级，不会无限卡住）
- 读取
~/.agents/skill-sync-report.json，向用户汇报摘要 - 若报告中有 ❌ 失败项或 ⚠️ 依赖警告，如实转告用户并给出建议
🔵 只对比不安装
node "<skill-path>\scripts\sync-skills.js" --compare --list "<list-file>"
🟣 安装单个技能
node "<skill-path>\scripts\install-skill.js" --name <skill-name> --url <origin-url>
主编排脚本参数（sync-skills.js）
| 参数 | 说明 | 默认 |
|---|---|---|
--list <path> |
技能列表文件路径 | 自动查找（见下） |
--no-self-update |
跳过自更新 | 开启自更新 |
--cdn-first |
CDN 优先（codeload/jsDelivr 在 npx add 之前） | 官方优先 |
--dry-run |
演练模式：只打印将执行的命令，不真正安装 | 关闭 |
--concurrency <n> |
仓库级安装并发数 | 3 |
--agents <a,b,c> |
安装到的 Agent 列表 | reasonix,claude-code,opencode,codex |
--lock <path> |
锁文件路径 | ~/.agents/.skill-lock.json |
--report <path> |
报告输出路径 | ~/.agents/skill-sync-report.json |
--cache-ttl <min> |
远端 commit 缓存 TTL | 360 分钟（6 小时） |
--compare |
只对比不安装（输出 JSON） | 关闭 |
--only <name1,name2> |
只处理指定技能 | 全部 |
--skip-deps |
跳过依赖预检 | 执行依赖预检 |
What ships with it
6 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.
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.
- 12d ago First seen · 258 lines · 187 tokens per session scan A 31e82ce1130f
skill-install-manager is a skill published in the GitHub repository MarecGents/marec-agent-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 187 tokens to every session and 3,624 once invoked, about $0.0009 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
fabric-fusion
Multi-model deliberation. Two to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Act mode runs 1–4 read-only references, then one actor reconciles and executes. Use when the cost of being wrong justifies…
fabric-rlm
Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and multi-file refactors that do not fit one context.
fabric-exec
Python-only troubleshooting and advanced host API reference for fabricexec. Routine pi. coding calls are documented by ambient guidance; load this skill only after an argument-shape error or when an advanced surface needs exact contracts.
fabric-schema
Uses Fabric's typed Schema evidence loop and, when enabled, its bounded local-file transaction channel. Use when surprise must void a plan and mutation claims need explicit postconditions.
fabric-workflow
Runs a dynamic Pi Fabric workflow with code-held phases, fan-out, pipelines, structured agents, and best-effort verification. Use for large audits, migrations, parallel research, or explicit workflow requests.
fabric-council
Runs a bounded multi-perspective Pi Fabric council with independent reviewers and best-effort synthesis. Use for architecture choices, plans, reviews, and adversarial cross-checking.