default

default is a skill for Claude Code, Codex from MarecGents/marec-agent-skills. It costs 143 tokens per session (3,317 once invoked), scanned A, original, MIT.

A general-purpose workflow skill for tasks that do not match a more specific skill. It requires brainstorming, file-based planning, skill matching, and an archive step at the end.

In plain words
What is it for?
Use it as a fallback for building, developing, organizing, analysing, or handling a task without a dedicated skill, including work involving GitHub repositories.
Why use it?
It gives unstructured development requests a repeatable process and keeps progress, findings, and the final task record organized. It also requires checking for more suitable skills during planning.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it as a fallback for building, developing, organizing, analysing, or handling a task without a dedicated skill, including work involving GitHub repositories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marecgents/marec-agent-skills/default
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.

Any agent
npx skills add MarecGents/marec-agent-skills --skill default
Clone the repo
git clone --depth 1 https://github.com/MarecGents/marec-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for default

README.md
[![agentmods](https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/default.svg)](https://agentmods.dev/skills/marecgents/marec-agent-skills/default)
Your own site
<a href="https://agentmods.dev/skills/marecgents/marec-agent-skills/default"><img src="https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/default.svg" alt="Measured on agentmods" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00143 $0.03317
Opus 5 $0.00072 $0.01658
Sonnet 5 $0.00029 $0.00663
Haiku 4.5 $0.00014 $0.00332

Measured 7d ago against content hash d17c7739ca39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

default 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 7d 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.

skills/default/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Default — 通用默认工作流

当你收到一个用户任务,且没有更具体的专项技能匹配时,按照本技能定义的三阶段工作流执行。


核心原则

  1. 必须先调用 brainstorming — 每次任务执行必须先调用 brainstorming 技能进行前期构思和分析,不得跳过此步骤。这帮助你在动手之前全面理解用户意图、项目目标和潜在挑战。
  2. 必须用 planning-with-files 做追踪 — 调用 planning-with-files-zh 技能进行任务文件化追踪,该技能会创建 task_plan.mdfindings.mdprogress.md 三个核心追踪文件,让整个过程有迹可循、可回溯。
  3. 任务结束后清理并归档 — 基于三个规划文件生成最终的任务日志文档,存入 ./docs/,然后删除过程中产生的无用文件。
  4. 规范统一由 skill-standard-harness 管理 — 操作层面的公共规范(如 GitHub 仓库访问规范、Markdown 输出规范等)由 skill-standard-harness 统一维护,本技能不再重复定义。
  5. 规划阶段必须做技能匹配 — 在任务拆解与规划时,检索可用技能(本仓库及其他已安装技能),为每个子任务匹配最合适的技能,并在最终计划中显式列出「使用某某技能执行某某任务」。避免有现成技能不用、重复造轮子。
  6. 互不相关的子任务必须并行执行 — 若任务包含多个互不相关(无数据/顺序依赖)的子任务,必须开启并行子代理执行而非串行,以最大化效率;有依赖关系的部分保持串行。

GitHub 仓库访问规范

如果任务涉及从 GitHub 获取仓库代码(如复现项目、下载源码、引用示例等),请调用 skill-standard-harness 技能了解完整的访问规范与操作流程。


三阶段工作流

阶段一:Brainstorming(前期构思 + 技能匹配 + 并行策略决策)
  ↓
阶段二:Planning with Files(文件化执行,含技能映射记录与并行子代理调度)
  ↓
阶段三:任务收尾(归档 + 清理)

阶段一:Brainstorming(前期构思 + 技能匹配)

触发条件:接收到用户任务后立即进入此阶段。

执行步骤:

  1. 调用 brainstorming — 对任务进行初步分析构思。思考:

    • 用户到底想要什么?核心诉求是什么?
    • 这个任务涉及哪些方面?
    • 可能遇到哪些主要挑战?
    • 需要哪些前置条件或资源?
  2. 遵循 brainstorming 流程

    • 探索项目上下文(文件、文档、最近的变更)
    • 逐一提出澄清性问题,理解目的、约束和成功标准
    • 提出 2-3 种方案,附上权衡分析和你的推荐
    • 分部分呈现设计,每部分获得用户确认后再继续
    • 将确认后的设计写入设计文档(按 brainstorming 默认路径)
    • 让用户审查书面规格
    • 重要:在用户批准设计之前,不得开始任何实现工作
  3. 技能匹配(必做) — 在设计中识别各子任务所需能力,检索可用技能列表(本仓库及全局已安装技能),为每个子任务匹配最合适的技能。技能匹配规则:

    • 优先级从高到低:① 专用专项技能(如复现项目用 github-project-replication、处理 docx 用 docx、下载抖音用 douyin-downloader)→ ② 通用工作流技能(本 default)→ ③ 不匹配任何技能时直接执行
    • 匹配依据技能的 description 与任务意图的契合度,不凭名字猜
    • 将匹配结果暂存于设计文档(brainstorming 的设计文档),阶段二初始化 task_plan.md 后正式写入,格式:- [子任务] → 技能:<skill-name>(原因:...)
  4. 执行策略决策(并行 or 串行) — 对设计中的子任务做依赖分析:

    • 无依赖(互不相关):标记为可并行
    • 有依赖(顺序/数据依赖):标记为串行,明确依赖链
    • 将决策暂存于设计文档,阶段二初始化 task_plan.md 后正式记录(见阶段二)
  5. 设计获得批准后,进入阶段二。

阶段二:Planning with Files(文件化执行)

Read the full file on GitHub · 219 lines

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. 7d ago First seen · 219 lines · 143 tokens per session scan A d17c7739ca39

Subscribe to this mod's changes

default is a skill published in the GitHub repository MarecGents/marec-agent-skills (3 stars, last pushed 9d ago), licensed MIT. It adds 143 tokens to every session and 3,317 once invoked, about $0.0007 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

ponytail-gain

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".

dmae97/omk · 83 tokens

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

loop

Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.

QwenLM/qwen-code · 66 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

oma-recap

Analyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate themed daily/period work summaries. Filter by date or time window.

first-fluke/oh-my-agent · 47 tokens

tmux

Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).

Team-Commonly/commonly · 48 tokens