nyann:gh-protect

nyann:gh-protect is a command for Claude Code from thettwe/nyann. It costs 31 tokens per session (566 once invoked), scanned A, original, MIT.

A command for checking or changing GitHub repository security settings, including branch protection, tag rules, signing requirements, and other repository rules. GitHub is a service for hosting and collaborating on code.

In plain words
What is it for?
Use it to audit protection on branches and tags, review configuration drift, enforce required signing or review rules, and apply repository settings from a defined profile.
Why use it?
It shows where the repository's actual protections differ from an expected profile and can apply stricter matching settings after confirmation. Its check mode only reads the current state.

Command for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the nyann plugin — 41 skills, 41 commands, 3 hooks 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 commands/thettwe/nyann/gh-protect
Clone the repo
git clone --depth 1 https://github.com/thettwe/nyann

Made for: Claude Code.

Or install nyann, the plugin that ships this one along with the rest of its 41 skills, 41 commands, 3 hooks.

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 nyann:gh-protect

README.md
[![agentmods](https://agentmods.dev/badge/commands/thettwe/nyann/gh-protect.svg)](https://agentmods.dev/commands/thettwe/nyann/gh-protect)
Your own site
<a href="https://agentmods.dev/commands/thettwe/nyann/gh-protect"><img src="https://agentmods.dev/badge/commands/thettwe/nyann/gh-protect.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 $0.00031 $0.00566
Opus 5 $0.00015 $0.00283
Sonnet 5 $0.00006 $0.00113
Haiku 4.5 $0.00003 $0.00057

Measured 5d ago against content hash ca9571d851c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nyann:gh-protect 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 5d 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.

commands/gh-protect.md · 59 lines

What it actually says

Plugin root: This is a Claude Code plugin, NOT a CLI tool. Do NOT search via which, npm list, pip list, or brew list. This file is at <plugin_root>/commands/. All scripts: <plugin_root>/bin/. Read the matching skills/*/SKILL.md for the full flow.

/nyann:gh-protect

Wraps bin/gh-integration.sh. Two modes:

Mode What happens
--check (default) Read-only audit. Emits a ProtectionAudit JSON showing drift between profile expectations and GitHub state.
apply (on confirmation after audit) Tightens branch protection, tag rulesets, and repo settings to match the profile. Never downgrades stricter remote rules.

When to invoke

  • After changing .github fields in your profile → audit and apply.
  • Periodic check that protection hasn't drifted → audit only.
  • After bootstrap if protection wasn't applied (e.g. gh was missing at bootstrap time) → apply now.

Output

  • Audit: ProtectionAudit JSON (schemas/protection-audit.schema.json) with per-branch, per-rule drift classification (critical / warn / ok).
  • Apply: GhIntegrationResult JSON (schemas/gh-integration-result.schema.json) with applied[], noop[], errors[].

Requires

  • gh CLI installed and authenticated (gh auth status).
  • Repository must have a GitHub remote.

See also:

  • /nyann:doctor — includes protection audit as one health signal
  • /nyann:bootstrap — applies protection during initial setup
  • /nyann:inspect-profile — view the .github block in the active profile
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. 5d ago First seen · 59 lines · 31 tokens per session scan A ca9571d851c8

Subscribe to this mod's changes

nyann:gh-protect is a command published in the GitHub repository thettwe/nyann (6 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 566 once invoked, about $0.0002 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 2026-08-31.