agents-md-slim

agents-md-slim is a skill for Claude Code, Codex from astordu/qoderharness. It costs 66 tokens per session (1,379 once invoked), scanned A, original, MIT.

A guide for shortening AGENTS.md, the repository instruction file read by coding agents. It focuses on keeping essential project rules while removing details agents can discover from the code.

In plain words
What is it for?
Reviewing oversized AGENTS.md files, removing fragile file paths and redundant details, and replacing them with concise descriptions of project conventions.
Why use it?
It reduces repeated instructions and lowers the amount of guidance loaded into every task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Reviewing oversized AGENTS.md files, removing fragile file paths and redundant details, and replacing them with concise descriptions of project conventions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/astordu/qoderharness/agents-md-slim
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 astordu/qoderharness --skill agents-md-slim
Clone the repo
git clone --depth 1 https://github.com/astordu/qoderharness

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 agents-md-slim

README.md
[![agentmods](https://agentmods.dev/badge/skills/astordu/qoderharness/agents-md-slim.svg)](https://agentmods.dev/skills/astordu/qoderharness/agents-md-slim)
Your own site
<a href="https://agentmods.dev/skills/astordu/qoderharness/agents-md-slim"><img src="https://agentmods.dev/badge/skills/astordu/qoderharness/agents-md-slim.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,379 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00066 $0.01379
Opus 5 $0.00033 $0.00690
Sonnet 5 $0.00013 $0.00276
Haiku 4.5 $0.00007 $0.00138

Measured 7d ago against content hash e337e5abf9ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agents-md-slim 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.

.qoder/skills/agents-md-slim/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

精简 AGENTS.md 内容

AGENTS.md 在每次请求时都会被完整加载,因此必须精简。本 skill 遵循三条精简原则。

三条精简原则

原则一:控制指令预算

AGENTS.md 应尽可能小。每一条信息都要占用 token 并与任务指令竞争注意力。

应保留

  • 一句话项目描述
  • 包管理器(非 npm 时必须注明)
  • 非标准的构建/类型检查命令
  • 真正与每个任务都相关的全局约定

应移除的过度细节

  • 详细的路径表格、架构清单 → 压缩为一句话能力描述
  • 多行展开的组件列表 → 合并为单行概括
  • 重复说明的调用链路 → 保留方向,去掉冗余前缀

判断标准:如果移除某条信息后 Agent 仍能通过阅读代码自行理解,则该信息属于过度细节。

原则二:描述能力,而非路径

文件路径是 AGENTS.md 中最容易过时的内容。路径重命名或文件移动后,AGENTS.md 就会变成误导信息。

禁止

  • 列出具体文件路径,如 app/api/routes/<指标>.py
  • 引用具体函数名,如 calc_trend() 函数
  • 描述文件组织结构的表格中包含路径列

应该

  • 描述能力和职责,如"Routes 解析请求并委派 Service"
  • 描述组织模式,如"按指标名分文件组织"
  • 描述整体形状,让 Agent 自己探索定位

原则三:移除 Agent 可自行发现的信息

不要把 Agent 阅读代码就能知道的信息写进 AGENTS.md。

应移除的冗余信息

  • 语言/框架标准模式(如"每层通过 __init__.py 统一导出")
  • 代码级实现细节(如"Service 使用静态方法")
  • 配置级细节(如"数据库为 SQLite,启动时通过 Base.metadata.create_all() 自动建表")
  • 框架默认行为(如"所有 API 调用均为带类型的函数")

应保留的关键信息

  • 非显而易见的架构约定(如"修改数据结构时前后端类型必须同步更新")
  • 与标准做法的偏离(如"包管理器为 uv 而非 pip")
  • Agent 无法从代码推断的隐式约定(如"CORS 仅配置了 localhost:5173")

执行步骤

1. 逐条审查

读取现有 AGENTS.md,对每一条信息判断:

  • 是否包含文件路径?→ 原则二
  • 是否为 Agent 可自行发现的信息?→ 原则三
  • 是否为过度细节?→ 原则一

2. 提出修改建议

对标记为问题的内容,用能力描述替换路径引用,用简洁概括替换冗长细节。将修改建议列出,等待用户确认后再修改。

3. 验证

确认修改后的 AGENTS.md:

  • 不包含具体文件路径
  • 不包含 Agent 可自行发现的信息
  • 描述简洁,每节尽量用一句话概括

示例

示例 1:路径表格 → 能力描述

Before:

| 层级 | 路径 | 职责 |
|------|------|------|
| Routes | `app/api/routes/<指标>.py` | FastAPI 路由,解析请求,委派给 Service |
| DTOs | `app/api/dtos/<指标>.py` | Pydantic 模型,负责请求/响应序列化 |
| Services | `app/services/<指标>.py` | 业务逻辑层,调用 Repo 并转换为 DTO |
| Repos | `app/db/repos/<指标>.py` | 数据访问层,封装 SQLAlchemy 查询 |
| Models | `app/db/models/<指标>.py` | SQLAlchemy ORM 表定义 |

After: 每项健康指标在各层都遵循相同模式:Routes 解析请求并委派 Service,DTOs 负责序列化,Services 处理业务逻辑,Repos 封装数据查询,Models 定义 ORM 表。按指标名分文件组织。

示例 2:文件清单 → 一句话概括

Before:

- `src/api/client.ts` - 集中式 axios 客户端,所有 API 调用均为带类型的函数
- `src/types/health.ts` - TypeScript 接口,与后端 Pydantic DTO 一一对应
- `src/hooks/useHealthData.ts` - 自定义 Hook,通过 `Promise.all` 并行拉取所有指标数据
- `src/components/DashboardGrid.tsx` - 编排组件,将数据分发给各指标卡片
- `src/components/<指标>Card.tsx` - 每个指标一个卡片组件,通过 props 接收数据
- `src/components/TrendChart.tsx` - 共享的 recharts 折线图组件,被各卡片复用

Read the full file on GitHub · 122 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 · 122 lines · 66 tokens per session scan A e337e5abf9ee

Subscribe to this mod's changes

agents-md-slim is a skill published in the GitHub repository astordu/qoderharness (24 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,379 once invoked, about $0.0003 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 2026-08-30.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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