New: 97,000+ 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

Nexus Agents

by ProfSynapse in ProfSynapse/nexus

How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy.

MITAuto-check passed

Install Nexus Agents

skills CLI
$ npx skills add ProfSynapse/nexus --skill nexus-agents -a claude-code

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

GitHub CLI
$ gh skill install ProfSynapse/nexus nexus-agents --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/ProfSynapse/nexus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.skills/nexus-agents .claude/skills/nexus-agents && 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
nexus-agents
GitHub stars
154
Token cost
~843 tokens
SKILL.md length
366 words
Files
13 (incl. scripts, references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy.

  • Works in 4 steps: Get current truth before you write… → Take the protocol for the job. Read it… → You MUST finish at protocols/verify.md,… → …
  • Modifying an agent
  • SKILL.md covers Workflow, Map and Siblings
  • Runs Python scripts from its folder; calls npm and node

What it does

Nexus Agents is an agent skill from ProfSynapse/nexus. How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy. Use when adding or modifying an agent or tool, when a documented command does not resolve, when wiring registration or capability gating, or when touching the ToolManager payload shape.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `protocols/add-agent.md`, `protocols/add-tool.md` and `protocols/change-payload-contract.md`).

The licence is MIT.

When your agent uses it

  • Modifying an agent
  • A documented command does not resolve
  • Wiring registration
  • Capability gating

Example prompts

  • “/nexus-agents”

Requirements

  • Python 3

Workflow steps

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

  1. Get current truth before you write anything. Trust no inventory in any
  2. Take the protocol for the job. Read it before acting; a summarized procedure
  3. You MUST finish at protocols/verify.md, whichever path you took. Discovery
  4. At the end of a session that used this skill, run protocols/self-refine.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 6cb7bce. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • node

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

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Nexus Agents loads about 843 tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~843
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.9k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from ProfSynapse/nexus at commit 6cb7bce, republished under its MIT licence (© ProfSynapse). 366 words, ~843 tokens.

Download SKILL.mdSave it as .claude/skills/nexus-agents/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
nexus-agents
description
How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy. Use when adding or modifying an agent or tool, when a documented command does not resolve, when wiring registration or capability gating, or when touching the ToolManager payload shape.

Nexus agents and tools

Context: Nexus exposes exactly two MCP tools — getTools (discovery) and useTools (execution). Every agent is internal and reached through those two, so adding an agent adds no MCP tool; it adds something discoverable through them. This file routes. The detail loads when you take the path.

Workflow

  1. Get current truth before you write anything. Trust no inventory in any document, including this one — regenerate the catalog and read it. It lists every command a caller can actually type, and it is the artifact the shipped-docs gate reads:
    bash
    npm run schemas:release                                         # refresh committed catalogs
node scripts/generate-tool-schemas.mjs --output - --selector "storage" # inspect, write nothing
ls src/agents/ src/agents/apps/                                 # who exists
grep -n "slug:" src/agents/<agent>/<agent>.ts                   # that agent's slugs
  2. Take the protocol for the job. Read it before acting; a summarized procedure is one you will improvise.
    • Adding a tool to an existing agent: protocols/add-tool.md
    • Adding an agent (core or app): protocols/add-agent.md
    • Changing the useTools/getTools payload or the CLI grammar: protocols/change-payload-contract.md
    • Something already broke: start at references/failure-modes.md, which is keyed by the symptom you are seeing.
  3. You MUST finish at protocols/verify.md, whichever path you took. Discovery and executability fail separately: a tool can register and still not run, and a command that reads correctly in source can advertise under a different name. Neither is visible from a build that passes.
  4. At the end of a session that used this skill, run protocols/self-refine.md.
Show full SKILL.md (158 more words)Show less

Map

  • protocols/ the procedures: add-tool, add-agent, change-payload-contract, verify, self-refine.
  • references/ read on demand: contract.md (the invariants a change must not break), cli-names.md (what a slug becomes on the command line, and the parsing rules that follow), registration.md (where an agent gets wired and what actually gates one), failure-modes.md (symptom → cause → proof).
  • scripts/ run them, do not reimplement:
    • scripts/cli_name.py — what a slug advertises as, derived from the live transform in source rather than guessed.
    • scripts/check_documented_commands.py — every Nexus command written in a doc, checked against the generated catalog. The repo's own shipped-docs test does not read .claude/skills/**, so this is the only thing standing between this skill and a command that no longer resolves.

Siblings

Name them, do not re-derive them. Test lanes, the live in-app loop and the eval harness belong to nexus-testing; exporting schemas as a deliverable to nexus-tool-schemas; provider adapters to nexus-llm-adapters; anything that must survive a restart to nexus-storage; mobile-safe imports and vault-path confinement to nexus-mobile-compat.

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

Files

SKILL.md and 12 other files (scripts, references) in .skills/nexus-agents of ProfSynapse/nexus.

  • SKILL.md
  • protocols/add-agent.md
  • protocols/add-tool.md
  • protocols/change-payload-contract.md
  • protocols/self-refine.md
  • protocols/verify.md
  • references/cli-names.md
  • references/contract.md
  • references/failure-modes.md
  • references/registration.md
  • refinement-log.md
  • scripts/check_documented_commands.py
  • scripts/cli_name.py

Open the folder on GitHubat commit 6cb7bce

Compare with similar skills

Nexus Agents 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.

Nexus Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nexus Agents this skillProfSynapse/nexus154—~843Automated safety check: PassMIT
Flow Nexus Neuralruvnet/agentic-flow8165 repos~4.1kAutomated safety check: PassNone
Flow Nexus Platformruvnet/agentic-flow8164 repos~6.4kAutomated safety check: PassNone
Flow Nexus Swarmruvnet/agentic-flow8164 repos~4.2kAutomated safety check: PassNone
Nexus Configurationnexus-research-lab/nexus150—~768Automated safety check: PassApache-2.0
Nexus Managernexus-research-lab/nexus150—~432Automated safety check: PassApache-2.0

Similar skills

  • Flow Nexus Neural

    ruvnet/agentic-flow

    Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

    816 GitHub starsUsed in 5 repos~4.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Flow Nexus Platform

    ruvnet/agentic-flow

    Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

    816 GitHub starsUsed in 4 repos~6.4k tokens
    Backend & APIsAuto-check passed

  • Flow Nexus Swarm

    ruvnet/agentic-flow

    Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

    816 GitHub starsUsed in 4 repos~4.2k tokens
    Backend & APIsAuto-check passed

  • Nexus Configuration

    nexus-research-lab/nexus

    在当前 Nexus 私聊或 Room 中读取、规划、确认并验证调用者有权管理的产品配置，包括管理员的用户账号、Agent、Room、Provider、偏好、Channel、Connector、Skill、Session、模型、工具和 MCP 设置。

    150 GitHub stars~768 tokensUpdated yesterday
    Auto-check passed

  • Nexus Manager

    nexus-research-lab/nexus

    由 Nexus 主智能体查询或管理 owner scope 内的平台资源，包括 Agent、DM/Room、conversation、Session、其他 Agent workspace 与 Skill。产品配置、Goal、Execution 和 Automation 使用各自专用 Skill，不走本控制面。

    150 GitHub stars~432 tokensUpdated yesterday
    Auto-check passed

  • Nexus Mapper

    Haaaiawd/Nexus-skills

    Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots.

    166 GitHub starsUsed in 1 repo~2.5k tokens
    DevelopmentAuto-check: notes

More from ProfSynapse/nexus

All 12 skills in this repo

  • Nexus Eval Harness

    ProfSynapse/nexus

    Work on the Nexus LLM eval harness in tests/eval/ — author or fix a scenario fixture, write an eval config, change the executors, assertions or reports, or explain a run that produced nothing…

    154 GitHub stars~1k tokensUpdated 5 days ago
    Auto-check passed

  • Nexus Model Eval

    ProfSynapse/nexus

    Grade how well a model drives the Nexus two-tool protocol (getTools/useTools) and decide whether a low score is the model's fault or the harness's.

    154 GitHub stars~1k tokensUpdated 5 days ago
    Auto-check passed

  • Nexus Model Updates

    ProfSynapse/nexus

    Add, change or verify a Nexus LLM model definition — the registry entry, the provider default, and proof the model id actually works against the live endpoint.

    154 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed

  • Nexus Release

    ProfSynapse/nexus

    Cut a Nexus release — bump the version with the repo's own machinery, get the docs and generated sources right, push a tag the GitHub Actions workflow will actually pick up, and recover when it does…

    154 GitHub stars~944 tokensUpdated 5 days ago
    Auto-check passed

  • Nexus Storage

    ProfSynapse/nexus

    How to change, persist, migrate and recover Nexus data without losing it.

    154 GitHub stars~749 tokensUpdated 5 days ago
    Auto-check passed

  • Nexus Testing

    ProfSynapse/nexus

    Verify a Nexus change — pick a Jest lane, write a test that can actually fail, run the in-app Obsidian CLI loop, drive the eval harness, or fix a shipped-docs drift failure.

    154 GitHub stars~994 tokensUpdated 5 days ago
    Auto-check passed

Questions about Nexus Agents

What does Nexus Agents do?

How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy. Nexus Agents is an agent skill from ProfSynapse/nexus. How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy.

When should I use Nexus Agents?

Nexus Agents fits situations like: modifying an agent; A documented command does not resolve; wiring registration; capability gating.

How do I install Nexus Agents in Claude Code?

Run `npx skills add ProfSynapse/nexus --skill nexus-agents -a claude-code`. Or copy the skill folder (.skills/nexus-agents in ProfSynapse/nexus) into .claude/skills/nexus-agents in your project. Claude Code loads it when a task matches its description.

How do I install Nexus Agents in Codex?

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

Can I use Nexus Agents 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 ProfSynapse/nexus --skill nexus-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nexus-agents, .gemini/skills/nexus-agents, .github/skills/nexus-agents and .opencode/skills/nexus-agents in your project.

What does Nexus Agents need to run?

Going by SKILL.md and its folder, Nexus Agents needs Python for the scripts in its folder and the command-line tools its instructions call (npm and node). Our summary lists: Python 3.

Does Nexus Agents access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Nexus Agents 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Nexus Agents use?

Nexus Agents 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 Nexus Agents use?

About 843 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.1k tokens, read only when the agent opens those files.

What are the alternatives to Nexus Agents?

Skills that share tags, products or a category with Nexus Agents: Flow Nexus Neural (ruvnet/agentic-flow, 816 stars), Flow Nexus Platform (ruvnet/agentic-flow, 816 stars), Flow Nexus Swarm (ruvnet/agentic-flow, 816 stars) and Nexus Configuration (nexus-research-lab/nexus, 150 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nexus Agents?

ProfSynapse (a GitHub user) maintains it in ProfSynapse/nexus, which has 154 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 2, 2026.

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