Agent skill

Agent Architecture Skill

Generate architecture-level agent context (no code细节) for Terrain projects.

Install Agent Architecture Skill

skills CLI

$ npx skills add sopaco/terrain --skill agent-architecture-skill -a claude-code

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

GitHub CLI

$ gh skill install sopaco/terrain agent-architecture-skill --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/sopaco/terrain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/preset_skills/agent-architecture-skill .claude/skills/agent-architecture-skill && 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/

Paste into Claude Code

Install the "agent-architecture-skill" agent skill from https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill into .claude/skills/agent-architecture-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-architecture-skill", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add sopaco/terrain --skill agent-architecture-skill -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install sopaco/terrain agent-architecture-skill --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sopaco/terrain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/preset_skills/agent-architecture-skill .agents/skills/agent-architecture-skill && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "agent-architecture-skill" agent skill from https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill into .agents/skills/agent-architecture-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-architecture-skill", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add sopaco/terrain --skill agent-architecture-skill -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install sopaco/terrain agent-architecture-skill --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sopaco/terrain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/preset_skills/agent-architecture-skill .cursor/skills/agent-architecture-skill && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "agent-architecture-skill" agent skill from https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill into .cursor/skills/agent-architecture-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-architecture-skill", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/sopaco/terrain.git --path preset_skills/agent-architecture-skill

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add sopaco/terrain --skill agent-architecture-skill -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install sopaco/terrain agent-architecture-skill --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sopaco/terrain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/preset_skills/agent-architecture-skill .gemini/skills/agent-architecture-skill && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "agent-architecture-skill" agent skill from https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill into .gemini/skills/agent-architecture-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-architecture-skill", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install sopaco/terrain agent-architecture-skill

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add sopaco/terrain --skill agent-architecture-skill -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/sopaco/terrain.git skills-src && mkdir -p .github/skills && cp -r skills-src/preset_skills/agent-architecture-skill .github/skills/agent-architecture-skill && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "agent-architecture-skill" agent skill from https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill into .github/skills/agent-architecture-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-architecture-skill", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add sopaco/terrain --skill agent-architecture-skill -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install sopaco/terrain agent-architecture-skill --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/sopaco/terrain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/preset_skills/agent-architecture-skill .opencode/skills/agent-architecture-skill && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "agent-architecture-skill" agent skill from https://github.com/sopaco/terrain/tree/main/preset_skills/agent-architecture-skill into .opencode/skills/agent-architecture-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-architecture-skill", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: agent-architecture-skill
GitHub stars: 256
Token cost: ~1.1k tokens
SKILL.md length: 464 words
Files: 2
Skills in repo: 5
Repo updated: Sep 29, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate architecture-level agent context (no code细节) for Terrain projects.

Works in 7 steps: 项目概览 (Project Overview) — purpose,… → 架构设计 (Architecture) — containers,… → 模块地图 (Module Map) — table: Module |… → …
Tasks that involve Codebase knowledge for agents
SKILL.md covers NOT this skill's job, Output contract, Developer meta… and Rules, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent Architecture Skill is an agent skill from sopaco/terrain. Generate architecture-level agent context (no code细节) for Terrain projects.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `terrain-meta.example.json`).

It sits in Agent Workflows, covering Codebase knowledge for agents. The repository describes itself as: AI-native engineering environment management that makes your codebase agent-ready. The licence is MIT.

When your agent uses it

Tasks that involve Codebase knowledge for agents

Example prompts

“/agent-architecture-skill”

Workflow steps

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

项目概览 (Project Overview) — purpose, consumers, key constraints (≤120 words)
架构设计 (Architecture) — containers, layers, major dependencies (table/bullets)
模块地图 (Module Map) — table: Module | Responsibility | Primary paths (≤12 rows)
核心流程 (Core Flows) — 2–4 critical flows as numbered steps (no code)
技术选型 (Tech Stack) — stack, frameworks, infra (bullet list)
系统边界 (System Boundaries) — external APIs, DBs, third-party, trust boundaries
代码映射索引 (Code Map Index) — table: Concept | Location (paths only) | Notes (≤15 rows)

What it can do on your machine

Read from SKILL.md and the folder at commit 0746b38. 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 (its code samples are json and bash).
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 Architecture Skill loads about 1.1k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 464 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~25
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 sopaco/terrain at commit 0746b38, republished under its MIT licence (© sopaco). 464 words, ~1,105 tokens.

Download SKILL.mdSave it as .claude/skills/agent-architecture-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: agent-architecture-skill
description: Generate architecture-level agent context (no code细节) for Terrain projects.

Agent Architecture Context Skill

Produce agent/context.md — a dense, architecture-oriented document for Coding Agents and Ask mode.

NOT this skill's job

Full source code or compressed signatures (that's agent/repomix.md — Ask reads via grep/read_file)
Human-friendly long-form narrative (that's human/ Litho docs)

Output contract

When Terrain runs context generation, return the complete markdown document as your reply; Terrain persists it as agent/context.md. Do not write the output file yourself in that mode — a reply that is only a completion summary will overwrite a good on-disk document.

When a prompt explicitly delegates file writing to you (no “Terrain will persist your reply” clause), write to TERRAIN_AGENT_CONTEXT_OUTPUT or the path given in the prompt.

Required sections (Markdown ## headings), in the language specified by the prompt's LANGUAGE directive (Chinese names below; English equivalents in parentheses — the prompt's explicit section list takes precedence):

项目概览 (Project Overview) — purpose, consumers, key constraints (≤120 words)
架构设计 (Architecture) — containers, layers, major dependencies (table/bullets)
模块地图 (Module Map) — table: Module | Responsibility | Primary paths (≤12 rows)
核心流程 (Core Flows) — 2–4 critical flows as numbered steps (no code)
技术选型 (Tech Stack) — stack, frameworks, infra (bullet list)
系统边界 (System Boundaries) — external APIs, DBs, third-party, trust boundaries
代码映射索引 (Code Map Index) — table: Concept | Location (paths only) | Notes (≤15 rows)

Developer meta (`terrain-meta.json`)

Repositories may ship one or more terrain-meta.json files (repo root, .terrain/, or nested). Before generating context, Terrain programmatically collects referenced files and injects them into the LLM prompt. The bundle is also written to agent/meta-inputs.md.

See terrain-meta.example.json in this skill directory.

Schema (version 1)

json

{
  "version": 1,
  "hints": {
    "module_roots": ["crates/", "src/"],
    "notes": "Free-form team hints"
  },
  "inputs": [
    { "label": "Modules doc", "type": "file", "path": "docs/architecture.md" },
    { "label": "ADRs", "type": "glob", "pattern": "docs/adr/*.md", "optional": true },
    { "label": "Glossary", "type": "inline", "content": "..." }
  ]
}

Input types: file (path relative to repo or meta file), glob, inline. Each input may set optional and max_chars (default 3500).

Show full SKILL.md (187 more words)Show less

How to use meta in output

Treat collected meta as authoritative for 模块地图 and 系统边界
Supplement with grep_agent_pack for path discovery only
Do not invent modules that contradict developer meta
Rule-based modules/ stubs are deprecated — synthesis is LLM-driven from meta + repomix

Rules

Hard limit: ≤14000 characters — trimmed to 16 KiB on save if exceeded
Macro sections (1–3) must be the densest; sections 4–7 can be shorter
No function bodies, no code blocks > 3 lines
Path references only — implementation detail lives in agent/repomix.md
Use grep_agent_pack only to discover paths, never paste grep output
Prefer tables and bullet lists over prose

ACP mode (Terrain)

When Terrain runs context generation in ACP mode, native function tools are unavailable. Use the terrain tools CLI instead:

bash

terrain tools pack-meta --project {slug}
terrain tools grep-pack --project {slug} --pattern "module_name"
terrain tools read-pack-file --project {slug} --file src/foo.rs --start-line 1 --end-line 80

See terrain-ask-skill for the full CLI reference. Do not read the live repository filesystem.

Environment variables set by Terrain:

Variable	Purpose
`TERRAIN_AGENT_ARCH_SKILL`	This skill directory
`TERRAIN_AGENT_CONTEXT_OUTPUT`	Write target for `agent/context.md`
`TERRAIN_KNOWLEDGE_ROOT`	Project `.terrain/` directory
`TERRAIN_PROJECT_SLUG`	Project slug
`TERRAIN_REPO_PATH`	Repository root

How Ask consumes this

Macro: 项目概览 + 架构设计 + 模块地图 preloaded in the question
Meso: other sections fetched on demand via read_agent_context(section=…)
Micro: source code via grep_agent_pack → read_agent_pack_file

Files

SKILL.md and 1 other file in preset_skills/agent-architecture-skill of sopaco/terrain.

SKILL.md
terrain-meta.example.json

Open the folder on GitHubat commit 0746b38

Compare with similar skills

Agent Architecture Skill 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 Architecture Skill compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Agent Architecture Skill this skillsopaco/terrain	256	—	~1.1k	Automated safety check: Pass	MIT	9 days ago
ccc Semantic Code Searchcocoindex-io/cocoindex-code	2.7k	—	~938	Automated safety check: Pass	Apache-2.0	2 days ago
Context Engineeringabashev/vfs-s3	106	9 repos	~2.6k	Automated safety check: Notes	Apache-2.0	yesterday
Repomix Codebase Packeryamadashy/repomix	29k	—	~1.3k	Automated safety check: Notes	MIT	5 days ago
Codebase Handbook BuilderRuhan-Wang/Harness_Handbook	332	—	~2.2k	Automated safety check: Pass	Apache-2.0	1 mo ago
CodemapJordanCoin/codemap	704	—	~1.8k	Automated safety check: Pass	MIT	2 days ago

Similar skills

ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
2.7k GitHub stars~938 tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed
Context Engineering
abashev/vfs-s3
Optimizes agent context setup. An agent skill from abashev/vfs-s3.
106 GitHub starsUsed in 9 repos~2.6k tokens
Agent WorkflowsAuto-check: notes
Repomix Codebase Packer
yamadashy/repomix
Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.
29k GitHub stars~1.3k tokensUpdated 5 days ago
Agent WorkflowsAuto-check: notes
Codebase Handbook Builder
Ruhan-Wang/Harness_Handbook
Generates, refreshes, validates and uses a compact handbook that maps where a change touches in a repository, using the active Codex session and no external LLM API.
332 GitHub stars~2.2k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed
Codemap
JordanCoin/codemap
Gives an agent a quick map of a codebase's structure, dependencies, changes and handoffs, and tunes per-project config so the output stays code-first.
704 GitHub stars~1.8k tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed
Repomix Context Skill
sopaco/deepwiki-rs
A skill your agent uses when an agent needs source code from the local repomix index under .terrain/agent/repomix.md (not committed; regenerate via Terrain scan).
3.1k GitHub stars~671 tokensUpdated 24 days ago
Agent WorkflowsAuto-check passed

Questions about Agent Architecture Skill

What does Agent Architecture Skill do?

Generate architecture-level agent context (no code细节) for Terrain projects. Agent Architecture Skill is an agent skill from sopaco/terrain. Generate architecture-level agent context (no code细节) for Terrain projects.

When should I use Agent Architecture Skill?

Agent Architecture Skill fits situations like: tasks that involve Codebase knowledge for agents.

How do I install Agent Architecture Skill in Claude Code?

Run `npx skills add sopaco/terrain --skill agent-architecture-skill -a claude-code`. Or copy the skill folder (preset_skills/agent-architecture-skill in sopaco/terrain) into .claude/skills/agent-architecture-skill in your project. Claude Code loads it when a task matches its description.

How do I install Agent Architecture Skill in Codex?

Run `npx skills add sopaco/terrain --skill agent-architecture-skill -a codex`. Or copy the skill folder (preset_skills/agent-architecture-skill in sopaco/terrain) into .agents/skills/agent-architecture-skill in your project. Codex loads it when a task matches its description.

Can I use Agent Architecture Skill 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 sopaco/terrain --skill agent-architecture-skill -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-architecture-skill, .gemini/skills/agent-architecture-skill, .github/skills/agent-architecture-skill and .opencode/skills/agent-architecture-skill in your project.

What does Agent Architecture Skill need to run?

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

Does Agent Architecture Skill 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 Architecture Skill 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 Architecture Skill use?

Agent Architecture Skill 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 Architecture Skill use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Architecture Skill?

Skills that share tags, products or a category with Agent Architecture Skill: ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.7k stars), Context Engineering (abashev/vfs-s3, 106 stars), Repomix Codebase Packer (yamadashy/repomix, 29k stars) and Codebase Handbook Builder (Ruhan-Wang/Harness_Handbook, 332 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Architecture Skill?

sopaco (a GitHub user) maintains it in sopaco/terrain, which has 256 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 29, 2026.

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

Agent Architecture Skill

Install Agent Architecture Skill

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent Architecture Context Skill

NOT this skill's job

Output contract

Developer meta (`terrain-meta.json`)

Schema (version 1)

How to use meta in output

Rules

ACP mode (Terrain)

How Ask consumes this

Files

Compare with similar skills

Similar skills

ccc Semantic Code Search

Context Engineering

Repomix Codebase Packer

Codebase Handbook Builder

Codemap

Repomix Context Skill

More from sopaco/terrain

Litho Document Skill

Agent Context Skill

Terrain Ask Skill

Sdd Workflow Skill

Questions about Agent Architecture Skill

Install Agent Architecture Skill

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent Architecture Context Skill

NOT this skill's job

Output contract

Developer meta (terrain-meta.json)

Schema (version 1)

How to use meta in output

Rules

ACP mode (Terrain)

How Ask consumes this

Files

Compare with similar skills

Similar skills

More from sopaco/terrain

Related

Questions about Agent Architecture Skill

Developer meta (`terrain-meta.json`)