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.
npx agentmods add skills/mrshininnnnn/superctx/using-superctxnpx skills add MrShininnnnn/SuperCtx --skill using-superctxgit clone --depth 1 https://github.com/MrShininnnnn/SuperCtxWrote 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.
[](https://agentmods.dev/skills/mrshininnnnn/superctx/using-superctx)<a href="https://agentmods.dev/skills/mrshininnnnn/superctx/using-superctx"><img src="https://agentmods.dev/badge/skills/mrshininnnnn/superctx/using-superctx.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01721 |
| Opus 5 | $0.00023 | $0.00860 |
| Sonnet 5 | $0.00009 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
using-superctx 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SuperCtx Reference Guide (Agent Reference / Advanced)
This is an agent reference and advanced skill. Normal users do not need to run this; the agent uses it automatically to orient itself on how to interact with the project-local SuperCtx context hub.
When to Use
Use this skill whenever:
- A
.ctx/directory exists in the project root. - The user asks about project context, agent instructions, or tool configuration.
- The user asks about sync, health, candidates, broken shims, or cross-tool context.
- The user asks to update or apply context changes across agents.
Core Model
SuperCtx provides a central project-local context layer using a hub-and-shim model:
.ctx/SUPERCTX.mdis the canonical project context hub.- Tool-specific instruction files (e.g.
.claude/CLAUDE.md,.codex/AGENTS.md) are generated shims/adapters pointing to the hub. .ctx/sources/contains inactive recovery copies of original instruction files.
Edit Policy
When updating shared project context, the agent edits .ctx/SUPERCTX.md directly. The other managed files are not authoring surfaces.
| File | Policy |
|---|---|
.ctx/SUPERCTX.md |
Author here. Canonical editable hub. Edit it to update shared project context. /superctx:sync preserves these edits. |
Tool files (.claude/CLAUDE.md, .codex/AGENTS.md, .agy/ANTIGRAVITY.md, …) |
Generated shims. Do not edit. Edit .ctx/SUPERCTX.md instead. |
.ctx/sources/** |
Backup only. Do not read, import, or edit as active context. Not live context. |
Agent Rules
- Stay quiet about internals. Do not explain hub/shim/backup mechanics unless the user asks. Use SuperCtx context naturally without announcing how it works.
- Announce SuperCtx interactions. When SuperCtx is relevant or actively shaping the work, announce in one short sentence before taking action:
Using SuperCtx to <purpose>.Keep the announcement task-specific. - Do NOT ask users to manually edit
manifest.tomlorSUPERCTX.md, or manually run/superctx:syncor/superctx:addas the happy path unless they explicitly ask for commands. Prefer agent action and internal command execution. If/superctx:syncreports setup, add, repair, or migration opportunities, offer the action in natural language and ask for consent. - Avoid saying "sync context" unless actually running
/superctx:sync. - Do NOT read, import, or edit
.ctx/sources/**as active context..ctx/sources/contains inactive recovery copies of original pre-SuperCtx files. These files are for recovery and audit only, not canonical editable context. When updating project context, edit.ctx/SUPERCTX.md. - Do NOT edit generated shims as the source of truth. Tool-specific files are thin generated pointers to
.ctx/SUPERCTX.md. - Use
/superctx:syncfor convergence. It handles initialization, health checks, and repairs. - Offer agent-guided setup with explicit user consent when relevant. If a candidate repository is detected (no
.ctx/folder but candidate files exist), do not run/superctx:syncor mutate files without the user's explicit natural-language consent. Present the detected files, explain what setup will do, and ask for confirmation. Use this exact consent prompt:Using SuperCtx, I can set up one shared context hub for this repo.
This will:
- create
.ctx/SUPERCTX.md - back up the original instruction files under
.ctx/sources/ - replace the live instruction files with generated shims pointing to the hub
Proceed?
- create
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.
- 5d ago First seen · 116 lines · 46 tokens per session scan A fbced75d00c9
using-superctx 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 1,721 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.
Other skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
antigravity-skill-orchestrator
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-memory
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.