Agent skill

Agent Harness Construction

by affaan-m in affaan-m/ECC

“设计和优化AI代理的动作空间、工具定义和观察格式,以提高完成率。”

— description from SKILL.md by affaan-m
MITAuto-check passed

Install Agent Harness Construction

skills CLI
$ npx skills add affaan-m/ECC --skill agent-harness-construction -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC agent-harness-construction --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/zh-CN/skills/agent-harness-construction .claude/skills/agent-harness-construction && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-harness-construction
GitHub stars
276k
Used in
2 other repos
Token cost
~222 tokens
SKILL.md length
69 words
Files
1
Skills in repo
683
Repo updated
First seen
Licence
MIT

At a glance

  • Works in 4 steps: 行动空间质量 → 观察质量 → 恢复质量 → …
  • SKILL.md covers 核心模型, 行动空间设计, 粒度规则 and 观察设计, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Agent Harness Construction is a skill in affaan-m/ECC (276k stars). Its SKILL.md is about 222 tokens, and copies of it appear in 2 other owners' repositories. Licence: MIT.

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 行动空间质量
  2. 观察质量
  3. 恢复质量
  4. 上下文预算质量

What it can do on your machine

Read from SKILL.md and the folder at commit 4eb71d9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Harness Construction loads about 222 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 69 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~222

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit 4eb71d9, republished under its MIT licence (© affaan-m). 69 words, ~222 tokens.

Download SKILL.mdSave it as .claude/skills/agent-harness-construction/SKILL.md (or your agent's skills folder).
name
agent-harness-construction
description
设计和优化AI代理的动作空间、工具定义和观察格式,以提高完成率。
origin
ECC

智能体框架构建

当你在改进智能体的规划、调用工具、从错误中恢复以及收敛到完成状态的方式时,使用此技能。

核心模型

智能体输出质量受限于:

  1. 行动空间质量
  2. 观察质量
  3. 恢复质量
  4. 上下文预算质量

行动空间设计

  1. 使用稳定、明确的工具名称。
  2. 保持输入模式优先且范围狭窄。
  3. 返回确定性的输出形状。
  4. 除非无法隔离,否则避免使用全能型工具。

粒度规则

  • 对高风险操作(部署、迁移、权限)使用微工具。
  • 对常见的编辑/读取/搜索循环使用中等工具。
  • 仅当往返开销是主要成本时使用宏工具。

观察设计

每个工具响应都应包括:

  • status: success|warning|error
  • summary: 一行结果
  • next_actions: 可执行的后续步骤
  • artifacts: 文件路径 / ID

错误恢复契约

对于每个错误路径,应包括:

  • 根本原因提示
  • 安全重试指令
  • 明确的停止条件

上下文预算管理

  1. 保持系统提示词最少且不变。
  2. 将大量指导信息移至按需加载的技能中。
  3. 优先引用文件,而不是内联长文档。
  4. 在阶段边界处进行压缩,而不是任意的令牌阈值。

架构模式指导

  • ReAct:最适合路径不确定的探索性任务。
  • 函数调用:最适合结构化的确定性流程。
  • 混合模式(推荐):ReAct 规划 + 类型化工具执行。

基准测试

跟踪:

  • 完成率
  • 每项任务的重试次数
  • pass@1 和 pass@3
  • 每个成功任务的成本

反模式

  • 太多语义重叠的工具。
  • 不透明的工具输出,没有恢复提示。
  • 仅输出错误而没有后续步骤。
  • 上下文过载,包含不相关的引用。

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/zh-CN/skills/agent-harness-construction of affaan-m/ECC.

Open the folder on GitHubat commit 4eb71d9

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in affaan-m/ECC, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Agent Harness Construction next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Harness Construction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Harness Construction this skillaffaan-m/ECC276k2 repos~222Automated safety check: PassMIT
Nexrad Mosaic Constructionsickn33/agentic-awesome-skills47k1 repos~3.1kAutomated safety check: PassMIT
Attack Tree Constructionwshobson/agents40k8 repos~623Automated safety check: PassMIT
Slack Construct Agentsnanocoai/nanoclaw31k—~308Automated safety check: PassMIT
Construction LawLeoYeAI/openclaw-master-skills2.2k—~2.3kAutomated safety check: PassMIT
Nomogram Constructionaipoch/medical-research-skills1.9k—~2.7kAutomated safety check: PassMIT

Similar skills

  • Nexrad Mosaic Construction

    sickn33/agentic-awesome-skills

    Construct a quality-aware NEXRAD multi-radar mosaic from aligned single-site products with explicit coverage, beam geometry, quality weighting, overlap resolution, and provenance.

    47k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed
  • Builds attack trees that map how an attacker could reach a goal, with AND and OR nodes and cost, time, skill and detection ratings, to find defense gaps.

    40k GitHub starsUsed in 8 repos~623 tokens
    SecurityAuto-check passed
  • Slack Construct Agents

    nanocoai/nanoclaw

    Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline.

    31k GitHub stars~308 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Construction Law

    LeoYeAI/openclaw-master-skills

    Construction law analysis covering FIDIC (2017 suite), PSSCOC, SIA Conditions, NEC4, and JCT.

    2.2k GitHub stars~2.3k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Nomogram Construction

    aipoch/medical-research-skills

    A skill your agent uses when constructing a prognosis nomogram from survival-related clinical predictors, exporting the nomogram bundle and C-index table, and optionally rendering the final nomogram…

    1.9k GitHub stars~2.7k tokensUpdated 24 days ago
    Documents & OfficeAuto-check passed
  • Qec Construct

    Muuuun/luxas

    Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T).

    1.2k GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

More from affaan-m/ECC

All 682 skills in this repo
  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    277k GitHub starsUsed in 5 repos~3.1k tokens
    Auto-check passed
  • Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    277k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes
  • Docs Governance

    affaan-m/ECC

    Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references.

    277k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    277k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed
  • Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    277k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Set an ECC-specific frontend design direction for production UI work.

    277k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Questions about Agent Harness Construction

How do I install Agent Harness Construction in Claude Code?

Run `npx skills add affaan-m/ECC --skill agent-harness-construction -a claude-code`. Or copy the skill folder (docs/zh-CN/skills/agent-harness-construction in affaan-m/ECC) into .claude/skills/agent-harness-construction in your project. Claude Code loads it when a task matches its description.

How do I install Agent Harness Construction in Codex?

Run `npx skills add affaan-m/ECC --skill agent-harness-construction -a codex`. Or copy the skill folder (docs/zh-CN/skills/agent-harness-construction in affaan-m/ECC) into .agents/skills/agent-harness-construction in your project. Codex loads it when a task matches its description.

Can I use Agent Harness Construction in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill agent-harness-construction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-harness-construction, .gemini/skills/agent-harness-construction, .github/skills/agent-harness-construction and .opencode/skills/agent-harness-construction in your project.

What does Agent Harness Construction need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Harness Construction is instructions for the agent only.

Does Agent Harness Construction access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Harness Construction safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Harness Construction use?

Agent Harness Construction is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Harness Construction use?

About 222 tokens (SKILL.md is roughly 888 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Harness Construction?

Skills that share tags, products or a category with Agent Harness Construction: Nexrad Mosaic Construction (sickn33/agentic-awesome-skills, 47k stars), Attack Tree Construction (wshobson/agents, 40k stars), Slack Construct Agents (nanocoai/nanoclaw, 31k stars) and Construction Law (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Harness Construction?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 276,111 GitHub stars. The repository holds 683 skills in this directory. The repository was last updated on October 10, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.