github-via-nyxid

github-via-nyxid is a skill for Claude Code from ChronoAIProject/NyxID. It costs 116 tokens per session (3,032 once invoked), scanned A, original, Apache-2.0.

A guide for letting an AI agent operate a user's GitHub account through a credential-brokering service called NyxID. GitHub is a code-hosting platform for repositories, issues, pull requests, and automation.

In plain words
What is it for?
Reading or changing repositories, files, issues, pull requests, branches, commits, Actions, and gists through GitHub's API when the required connection and scopes are available.
Why use it?
It allows GitHub API work without exposing the user's raw access token to the agent, while actions remain limited by the granted permissions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the nyxid plugin — 17 skills, 1 command shipped together

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.

agentmods
npx agentmods add skills/chronoaiproject/nyxid/github-via-nyxid
Any agent
npx skills add ChronoAIProject/NyxID --skill github-via-nyxid
Clone the repo
git clone --depth 1 https://github.com/ChronoAIProject/NyxID

Made for: Claude Code.

Or install nyxid, the plugin that ships this one along with the rest of its 17 skills, 1 command.

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 github-via-nyxid

README.md
[![agentmods](https://agentmods.dev/badge/skills/chronoaiproject/nyxid/github-via-nyxid.svg)](https://agentmods.dev/skills/chronoaiproject/nyxid/github-via-nyxid)
Your own site
<a href="https://agentmods.dev/skills/chronoaiproject/nyxid/github-via-nyxid"><img src="https://agentmods.dev/badge/skills/chronoaiproject/nyxid/github-via-nyxid.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00116 $0.03032
Opus 5 $0.00058 $0.01516
Sonnet 5 $0.00023 $0.00606
Haiku 4.5 $0.00012 $0.00303

Measured 6d ago against content hash 5349783a0fd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-via-nyxid 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 6d 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.

skills/github-via-nyxid/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operate GitHub via NyxID

Overview

This skill lets an AI agent act on a user's GitHub account using the GitHub REST API — read repos, open issues and pull requests, commit files, trigger Actions, etc. — on the user's behalf.

The one premise: the agent never holds a GitHub token. Every call goes through NyxID's credential-brokering proxy for the connected service api-github. NyxID stores the user's GitHub credential (connected via OAuth — "the GitHub account the user bound in NyxID") encrypted at rest, strips any client Authorization header, injects the GitHub credential server-side, and forwards the request to https://api.github.com. You only ever send your NyxID bearer; you never see, request, or log the GitHub token.

What "operate GitHub" really means here: anything the GitHub REST API allows and that the OAuth scopes granted to the api-github connection permit. The ceiling is the granted scopes, not the entire API surface (see Scopes & permissions).

1. Preflight — confirm GitHub is connected

Before the first call, confirm the user has the api-github service connected in NyxID. In an Aevatar turn, call the available nyxid_service_inventory with {} and select an exact user_service_id; use only the schema emitted for that request. The CLI and raw HTTP remain operator alternatives:

  • CLI: nyxid service list --output json → look for an entry with "slug": "api-github".
  • Raw HTTP: GET https://nyx-api.chrono-ai.fun/api/v1/services with Authorization: Bearer <NYXID_TOKEN>.

If api-github is not present, the user must connect it once (one-click OAuth to their own GitHub account). Tell them to run:

nyxid service add api-github --oauth

To grant write/admin capabilities up front, request extra scopes at connect time, e.g.:

nyxid service add api-github --oauth --scope "repo,workflow,read:org,gist"

Do not ask the user to paste a GitHub token into chat — the OAuth flow handles it. (If broader, user-controlled scopes are needed, the api-github-pat service — a user-supplied Personal Access Token — is the fallback; same proxy, slug api-github-pat.)

Read the full file on GitHub · 246 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. 6d ago First seen · 246 lines · 116 tokens per session scan A 5349783a0fd4

Subscribe to this mod's changes

github-via-nyxid is a skill published in the GitHub repository ChronoAIProject/NyxID (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 3,032 once invoked, about $0.0006 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

polish-docs-meta

Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.

cyanheads/git-mcp-server · 53 tokens

git-workflow

Git best practices for version control and collaboration.

athola/skrills · 12 tokens

p4-stream-workflows

P4 stream workflows — creation, branching, merging, copying, integration, switching, and spec management via P4 MCP tools. Use when: creating streams, branching, merging, copying between streams, integrating changes, switching workspaces, or managing stream specs in P4.

perforce/p4mcp-server · 61 tokens

memory-commit

Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.

n24q02m/mnemo-mcp · 72 tokens

p4-workspace-setup

P4 workspace setup and management — create, configure, sync, and switch workspaces via P4 MCP tools. Use when: creating workspaces, configuring client specs, syncing files, switching workspaces, or checking workspace status in P4.

perforce/p4mcp-server · 56 tokens

release-versioning

Discipline for release classification, version bumps, and changelogs, Conventional Commits classify the release range, SemVer computes the version from those commits, Keep a Changelog renders the result. Use when the user asks to cut a release, bump a version, write a changelog, decide if a change is a…

aethrox/doctrine · 84 tokens