superctx:add

superctx:add is a skill for Claude Code from MrShininnnnn/SuperCtx. It costs 46 tokens per session (612 once invoked), scanned A, original, MIT.

A command for adding a local instruction file to SuperCtx, a shared context system for AI coding tools.

In plain words
What is it for?
Use it when you have an existing SuperCtx setup and want to start tracking a specific file, such as an editor or coding-assistant instruction file.
Why use it?
It keeps a chosen project instruction file connected to SuperCtx so it can be tracked as part of that shared context setup.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the superctx plugin — 3 skills, 3 hooks shipped together

Good fit Use it when you have an existing SuperCtx setup and want to start tracking a specific file, such as an editor or coding-assistant instruction file.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MrShininnnnn/SuperCtx
Claude Code
/plugin install superctx

Made for: Claude Code.

Or install superctx, the plugin that ships this one along with the rest of its 3 skills, 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 superctx:add

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrshininnnnn/superctx/add.svg)](https://agentmods.dev/skills/mrshininnnnn/superctx/add)
Your own site
<a href="https://agentmods.dev/skills/mrshininnnnn/superctx/add"><img src="https://agentmods.dev/badge/skills/mrshininnnnn/superctx/add.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00046 $0.00612
Opus 5 $0.00023 $0.00306
Sonnet 5 $0.00009 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 7d ago against content hash 950dae2349e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

superctx:add 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 7d 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/add/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SuperCtx Add

Add a local candidate file to the SuperCtx manifest to begin tracking it.

If SuperCtx is not set up yet (no .ctx/ directory exists), do not run this command first. Use /superctx:sync for the global setup/check/repair flow, then use /superctx:add <path> for targeted file connection after the shared context hub exists.

If .ctx/ exists but the configuration manifest is missing or invalid, the command will raise an error with inspect guidance.

  1. Direct User Invocation: If the user explicitly typed /superctx:add <path> or asked you to connect a file, you have consent. Announce the action:

    Using SuperCtx to connect as a local context file.

  2. Agent-Initiated Flow: If you detect an untracked candidate file during a task and want to add it, you MUST obtain explicit natural-language user consent first. Offer to connect it, explain what it does, and run the command internally only after getting consent.

Check File Existence First

Before running the add command, check whether the file exists in the project.

If the file exists: Run the add command normally:

PYTHONPATH="${CLAUDE_PLUGIN_ROOT}/scripts" python3 -m superctx add "$ARGUMENTS"

If the file does not exist and is a known standard convention (e.g. GEMINI.md, .claude/CLAUDE.md, .codex/AGENTS.md, .github/copilot-instructions.md):

Explain that the file does not exist yet, and offer to create it as a generated shim:

I do not see an existing <path>. I can create it as a generated shim pointing to .ctx/SUPERCTX.md. Proceed?

After the user confirms, run with --create-shim:

PYTHONPATH="${CLAUDE_PLUGIN_ROOT}/scripts" python3 -m superctx add --create-shim "$ARGUMENTS"

Do not create any file before receiving the user's explicit consent.

If the file does not exist and is not a known standard convention:

Explain clearly that the file must exist before it can be tracked:

<path> does not exist yet. SuperCtx tracks existing instruction files. Please create the file first or let me know if you would like me to create and connect it for you.

Read the full file on GitHub · 53 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. 7d ago First seen · 53 lines · 46 tokens per session scan A 950dae2349e7

Subscribe to this mod's changes

superctx:add is a skill published in the GitHub repository MrShininnnnn/SuperCtx (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 612 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.