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 commands/mnvsk97/eyeroll/initgit clone --depth 1 https://github.com/mnvsk97/eyerollWhat 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 | $0.00000 | $0.00514 |
| Opus 5 | $0.00000 | $0.00257 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
init 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 3d 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.
What it actually says
/eyeroll:init
Set up eyeroll for the current project -- pick a backend, install dependencies, and generate codebase context.
Usage
/eyeroll:init
No arguments needed.
What it does
Step 1: Check installation
Checks if eyeroll CLI is installed. If not, asks which backend you want and installs the appropriate package:
| Choice | Install command |
|---|---|
| Gemini | pip install eyeroll[gemini,download] |
| TwelveLabs | pip install eyeroll[twelvelabs] |
| OpenAI / OpenRouter / Groq / Grok / Cerebras / openai-compat | pip install eyeroll[openai,download] |
| Ollama | pip install eyeroll[download] |
Step 2: Configure backend
Runs eyeroll init interactively:
- Prompts for backend choice (Gemini, TwelveLabs, OpenAI, Ollama, OpenRouter, Groq, Grok, Cerebras, openai-compat)
- For Gemini/TwelveLabs/OpenAI: prompts for API key and validates the local SDK setup
- For Ollama: verifies Ollama is running (or starts it)
- Saves configuration to
~/.eyeroll/.env
Step 3: Generate codebase context
Explores the project and writes .eyeroll/context.md:
- Reads
CLAUDE.md,README.md,pyproject.tomlorpackage.json - Checks
git log --oneline -10and current branch - Lists root and key source directories
- Skims 2-3 key source files
The resulting file is a short summary (under 80 lines) that eyeroll uses to ground its analysis in real file paths.
What gets created
| File | Location | Purpose |
|---|---|---|
.env |
~/.eyeroll/.env |
Backend preference and API key |
context.md |
.eyeroll/context.md |
Project summary for grounded analysis |
When to re-run
Re-run /eyeroll:init when:
- You want to switch backends
- Your API key has changed
- The project structure has changed significantly (major refactor, new directories)
The codebase context file is what makes the difference between vague guesses and precise file references in eyeroll reports.
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.
- 3d ago First seen · 62 lines · 0 tokens per session scan A 2d1fb41e26a2
init is a command published in the GitHub repository mnvsk97/eyeroll (17 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 514 tokens. 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.
Other commands, from other repositories
frontend
Injects context of all relevant cli files.
cleanup-back-to-main
Go back to main and clean up the branch.
spec-research
需求 → 约束集（并行探索 + OPSX 提案）.
spec-design
Create comprehensive technical design for a specification.
OPSX: Bulk Archive
Archive multiple completed changes at once.
result
Fetch the output of a finished background Antigravity (agy) job, then verify it.