New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ade Harnesses

by arul28 in arul28/ADE

A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.

AGPL-3.0Auto-check passedAgent Workflows

Install Ade Harnesses

skills CLI
$ npx skills add arul28/ADE --skill ade-harnesses -a claude-code

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

GitHub CLI
$ gh skill install arul28/ADE ade-harnesses --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/arul28/ADE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-harnesses .claude/skills/ade-harnesses && 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
ade-harnesses
GitHub stars
114
Token cost
~1.6k tokens
SKILL.md length
673 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.

  • You need to run a chat
  • SKILL.md covers See what this machine can run, See what each harness can reach, Launch on a specific setup and Run a custom setup in your own…, plus 2 more sections
  • Calls claude
  • A subagent on a specific setup — any model you pay for inside any harness (e.g

What it does

Ade Harnesses is an agent skill from arul28/ADE. Use this skill when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g. OpenCode Go's DeepSeek inside Claude Code), a saved Custom provider (a "harness preset" internally), one of this machine's provider accounts, or one stored API key — instead of whatever ADE would pick by default. Covers listing what is reachable (ade harness routes, ade chat models, ade providers accounts list), launching with --via, --preset, --credential, or --instance…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents. It works with DeepSeek. The licence is AGPL-3.0.

When your agent uses it

  • You need to run a chat
  • A subagent on a specific setup — any model you pay for inside any harness (e.g

Example prompts

  • “s DeepSeek inside Claude Code), a saved Custom provider (a”
  • “internally), one of this machine”
  • “/ade-harnesses”

What it can do on your machine

Read from SKILL.md and the folder at commit fbbd974. 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

    Shell commands in SKILL.md call:

    • claude

    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

Ade Harnesses loads about 1.6k tokens when it runs. Until then it costs about 161 tokens; SKILL.md has 673 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~161
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 arul28/ADE at commit fbbd974, republished under its AGPL-3.0 licence (© arul28). 673 words, ~1,619 tokens.

Download SKILL.mdSave it as .claude/skills/ade-harnesses/SKILL.md (or your agent's skills folder).
name
ade-harnesses
description
Use this skill when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g. OpenCode Go's DeepSeek inside Claude Code), a saved Custom provider (a "harness preset" internally), one of this machine's provider accounts, or one stored API key — instead of whatever ADE would pick by default. Covers listing what is reachable (`ade harness routes`, `ade chat models`, `ade providers accounts list`), launching with `--via`, `--preset`, `--credential`, or `--instance`, checking a pairing (`ade harness test`), and running one in a plain terminal (`ade harness env`).

ADE harnesses: picking what a session runs on

ADE separates the harness (which agent runs: Claude Code, Codex, Droid, OpenCode, …) from the model provider (where it gets its intelligence: a native sign-in, a provider signed in to OpenCode — OpenCode Go, Zen, or any provider connected there — a stored API key, or a subscription borrowed through ADE's proxy). Any routable harness can run any model its sources serve: ADE points the harness straight at the source when they speak the same API, and translates through its local proxy when they do not.

A harness preset — shown in the app as Custom (Settings › Providers › Custom) — is one saved pairing of the two, with the model, the thinking level and the subagent pins attached. It has an id, and that id is the only thing a launch needs. The permission tier is not part of a preset: it is chosen at launch, the same way it is for every other provider.

See what this machine can run

bash
ade chat models --text                 # every model, grouped by provider
ade chat models --provider claude --text
ade providers accounts list --text     # Claude/Codex accounts on this machine
ade providers accounts list --provider codex --text

Presets and accounts also ride the AI status payload, which is the one call that answers what a session can run on without three round trips:

bash
ade actions run ai getStatus --text

Read harnessPresets[] ({id, name, harness, model, source}) and providerAccounts[] ({id, provider, label, isDefault, signedIn}). Neither carries a key or a config path — only the ids the flags below take.

See what each harness can reach

bash
ade harness routes --harness claude --text   # every model Claude Code can run, by source
ade harness routes --text                    # the same for every routable harness

Rows tagged via ADE proxy are translated (the proxy starts on demand). Check one pairing with a one-token request before relying on it — the verdict is remembered, so later launches route around a protocol the model refused:

bash
ade harness test --harness claude --via opencode-go --model deepseek-v4.1-flash --text

Launch on a specific setup

you wantflag
any reachable model, no saved preset--provider <harness> --via <source> --model <id>
a saved custom setup (harness preset)--preset <preset-id>
one stored API key, no preset--credential <credential-id>
a specific Claude/Codex account--instance <account-id>
bash
# A chat on a saved preset — model, effort and subagent pins all come from
# the preset, so nothing else needs stating.
ade chat create --lane <lane> --preset hp_opus_work

# A tracked CLI terminal on the same preset.
ade new chat --mode cli --lane <lane> --provider claude --preset hp_opus_work

# A key saved on a provider page, with no preset around it.
ade chat create --lane <lane> --provider claude --credential openrouter

# A specific account, without a preset.
ade chat create --lane <lane> --provider claude --instance work

# OpenCode Go's DeepSeek inside Claude Code, chat or CLI, no preset.
ade chat create --lane <lane> --provider claude --via opencode-go --model deepseek-v4.1-flash
ade new chat --mode cli --lane <lane> --provider codex --via opencode-go --model glm-5.3

--via takes opencode-go, opencode (Zen), opencode:<provider>, or key:<provider>[:<credentialId>]. Subagents follow the main model unless a preset pins them.

Run a custom setup in your own terminal

bash
eval "$(ade harness env <preset-id> --text)" && claude --model <model>

The output holds the provider token. It is printed for eval and never written anywhere; do not paste it into a chat or a file.

--preset and --credential are mutually exclusive: each names a whole setup, and passing both would leave ADE guessing which one you meant.

Show full SKILL.md (296 more words)Show less

Run subagents on a different preset

A subagent is a chat, so it takes the same flag. Spawn one on a cheaper or faster preset than the parent and keep working:

bash
ade chat create --lane <lane> --preset hp_haiku_cheap \
  --type subagent --permission-mode full-auto \
  --prompt "Find every caller of resolveLaunchBrain and report the list."

For a harness that takes one, you do not have to spawn a separate chat at all: a preset can name its subagents' model and thinking level (Settings › Providers › Custom › Subagents), which apply to every subagent the chat spawns natively, with no extra flag. Claude Code, Codex CLI, Grok and OpenCode take a subagent model; Claude Code and Codex CLI take a level too. Claude Code, Grok and OpenCode also let you pin individual named roles (Explore, Plan, general-purpose) under Subagent naming. A harness the preset's wizard says runs subagents on the main model takes neither.

What does not take a preset

Three CLIs read their identity from their own sign-in and accept no key or endpoint from the launch: Cursor, Copilot, Kimi. A preset on one of them in CLI mode is dropped and the native CLI starts — a working session on the harness's own account, with the reason recorded. (Grok used to be here; it now runs routed models from an ADE-owned GROK_HOME.)

OpenCode's free Zen models only answer inside OpenCode itself, so they are never offered in another harness.

Two more have no key path at all, in either mode:

  • Pi reads its endpoints and model ids from its own models.json. Add the provider in Pi; a preset key has nowhere to go.
  • Cursor holds one key at a time in its own store, so a per-preset key would change every other Cursor session on the machine.

When a preset cannot be honoured, the chat says which capability was dropped and runs on the harness's own sign-in. It never fails the launch.

© arul28, AGPL-3.0. 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 apps/desktop/resources/agent-skills/ade-harnesses of arul28/ADE.

Open the folder on GitHubat commit fbbd974

Compare with similar skills

Ade Harnesses 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.

Ade Harnesses compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ade Harnesses this skillarul28/ADE114—~1.6kAutomated safety check: PassAGPL-3.0
Codex Deepseek Subagentoil-oil/codex-deepseek-subagent376—~673Automated safety check: PassMIT
Subagentethanhq/cc-fleet215—~4.9kAutomated safety check: PassApache-2.0
DeepSeek Harness DelegationCherryHQ/cherry-studio52k1 repos~359Automated safety check: PassAGPL-3.0
Subagentethanhq/cc-fleet215—~4.3kAutomated safety check: PassApache-2.0
DeepSeek V4 Thinking-Mode Rulescodewhale-hq/Codewhale41k—~443Automated safety check: PassMIT

Similar skills

  • Codex Deepseek Subagent

    oil-oil/codex-deepseek-subagent

    配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent，支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用；普通 API 问题与配置后的日常编码任务不触发。

    376 GitHub stars~673 tokensUpdated 28 days ago
    Agent WorkflowsAuto-check passed

  • Subagent

    ethanhq/cc-fleet

    Fan out a one-shot or flat parallel batch of cc-fleet PROVIDER subagents (headless cc-fleet subagent) that return a result — DeepSeek / GLM / Kimi / Qwen / MiniMax, or a Codex/Claude subscription.

    215 GitHub stars~4.9k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • DeepSeek Harness Delegation

    CherryHQ/cherry-studio

    Hands a bounded repository task to the DeepSeek Harness CLI (dsh) in headless mode, then checks the exit code and the diff before reporting back.

    52k GitHub starsUsed in 1 repo~359 tokens
    Agent WorkflowsAuto-check passed

  • Subagent

    ethanhq/cc-fleet

    Run a one-shot or flat parallel batch of provider LLM subagents (headless cc-fleet subagent) that return a result.

    215 GitHub stars~4.3k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • DeepSeek V4 Thinking-Mode Rules

    codewhale-hq/Codewhale

    Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line.

    41k GitHub stars~443 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Go Spec Reviewer

    inference-gateway/inference-gateway

    Review a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces…

    214 GitHub stars~1.2k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed

More from arul28/ADE

All 28 skills in this repo

  • Ade App Control

    arul28/ADE

    A skill your agent uses when you need to run or drive a local Electron/desktop app and capture what it does — launch it or attach to a running renderer, read its logs or answer its terminal prompts…

    114 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Ade Autoresearch

    arul28/ADE

    Iteratively optimize an ADE tab's CPU/memory/IPC/render performance.

    114 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Ade Browser

    arul28/ADE

    A skill your agent uses for any browser behavior at all — opening a URL, checking a localhost page, clicking or filling a form, logging in, screenshotting, inspecting the DOM, or verifying a page…

    114 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Ade Deeplinks

    arul28/ADE

    A skill your agent uses when an agent needs to mint, share, or open ADE deeplinks (lane, work session, file, commit, artifact, branch, PR, Linear issue) so users — or the agent itself — can jump…

    114 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

  • Ade Lanes Git

    arul28/ADE

    A skill your agent uses when creating, inspecting, syncing, committing, pushing, archiving, or rebasing ADE lanes and lane worktrees through ade lanes and ade git.

    114 GitHub stars~594 tokensUpdated today
    Auto-check passed

  • Ade Linear

    arul28/ADE

    A skill your agent uses whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state…

    114 GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Ade Harnesses

What does Ade Harnesses do?

A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g. Ade Harnesses is an agent skill from arul28/ADE.g.

When should I use Ade Harnesses?

Ade Harnesses fits situations like: you need to run a chat; A subagent on a specific setup — any model you pay for inside any harness (e.g.

How do I install Ade Harnesses in Claude Code?

Run `npx skills add arul28/ADE --skill ade-harnesses -a claude-code`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-harnesses in arul28/ADE) into .claude/skills/ade-harnesses in your project. Claude Code loads it when a task matches its description.

How do I install Ade Harnesses in Codex?

Run `npx skills add arul28/ADE --skill ade-harnesses -a codex`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-harnesses in arul28/ADE) into .agents/skills/ade-harnesses in your project. Codex loads it when a task matches its description.

Can I use Ade Harnesses 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 arul28/ADE --skill ade-harnesses -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ade-harnesses, .gemini/skills/ade-harnesses, .github/skills/ade-harnesses and .opencode/skills/ade-harnesses in your project.

What does Ade Harnesses need to run?

Going by SKILL.md and its folder, Ade Harnesses needs the command-line tools its instructions call (claude).

Does Ade Harnesses 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 Ade Harnesses 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 Ade Harnesses use?

Ade Harnesses is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ade Harnesses use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Ade Harnesses?

Skills that share tags, products or a category with Ade Harnesses: Codex Deepseek Subagent (oil-oil/codex-deepseek-subagent, 376 stars), Subagent (ethanhq/cc-fleet, 215 stars), DeepSeek Harness Delegation (CherryHQ/cherry-studio, 52k stars) and Subagent (ethanhq/cc-fleet, 215 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ade Harnesses?

arul28 (a GitHub user) maintains it in arul28/ADE, which has 114 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

Source: arul28/ADE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.