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 instructions/lalitmee/codecompanion-spinners.nvim/gemini-mdgit clone --depth 1 https://github.com/lalitmee/codecompanion-spinners.nvimWrote 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/instructions/lalitmee/codecompanion-spinners.nvim/gemini-md)<a href="https://agentmods.dev/instructions/lalitmee/codecompanion-spinners.nvim/gemini-md"><img src="https://agentmods.dev/badge/instructions/lalitmee/codecompanion-spinners.nvim/gemini-md.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 | $0.06414 | $0.06414 |
| Opus 5 | $0.03207 | $0.03207 |
| Sonnet 5 | $0.01283 | $0.01283 |
| Haiku 4.5 | $0.00641 | $0.00641 |
Grade A, and why
codecompanion-spinners.nvim GEMINI.md 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 — 719 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeCompanion Spinner - Comprehensive Context
Project Overview
This is a Neovim plugin extension for codecompanion.nvim that provides beautiful, configurable status spinners and notifications to give you real-time feedback on AI activity.
Repository: https://github.com/lalitmee/codecompanion-spinners.nvim Maintained by: Lalit Kumar Mehta License: MIT (inferred from typical Neovim plugin practices)
Architecture
Core Components
-
Extension Entry Point (
lua/codecompanion/_extensions/spinner/init.lua)- Main setup function that loads configuration and initializes the selected spinner
- Handles dynamic loading of spinner implementations
- Provides error handling for missing spinner styles
-
Configuration Management (
lua/codecompanion/_extensions/spinner/config.lua)- Manages user configuration with sensible defaults
- Provides deep merging of user options
- Exposes helper functions for accessing configuration
-
State Tracker (
lua/codecompanion/_extensions/spinner/tracker.lua)- Central event handler for all CodeCompanion events
- Maintains internal state counters for requests, tools, diffs
- Provides state machine logic with defined states:
IDLE: No active operationsTHINKING: AI is processing a requestRECEIVING: AI is streaming responseTOOLS_RUNNING: Tools are being executedTOOLS_PROCESSING: Tool output is being processedDIFF_AWAITING: Diff is attached and awaiting review
- Includes
state_maptable for converting numeric states to string names used by spinners - Includes
one_off_eventstable for mapping CodeCompanion events to content keys for notifications
-
Spinner Implementations (
lua/codecompanion/_extensions/spinner/styles/)cursor-relative.lua: Floating window spinner near cursorfidget.lua: Integration with fidget.nvimsnacks.lua: Rich notifications via snacks.nvim or vim.notifylualine.lua: Statusline component for lualine.nvimheirline.lua: Statusline component for heirline.nvimnoice.lua: Rich notifications via noice.nvim
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 · 719 lines · 6,414 tokens per session scan A 4a5a408b5018
codecompanion-spinners.nvim GEMINI.md is an instructions file published in the GitHub repository lalitmee/codecompanion-spinners.nvim (24 stars, last pushed 2mo ago), licensed MIT. It adds 6,414 tokens to every session, about $0.0321 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.
Other instructions, from other repositories
fff AGENTS.md
AGENTS.md instructions for dmtrKovalenko/fff, covering to clankers, development commands, building, testing and development tools and code quality.
review.nvim CLAUDE.md
Claude Code instructions for vuki656/review.nvim, covering claude.md, commands, lint, run all tests and run a single test file.
fff CLAUDE.md
Claude Code instructions for dmtrKovalenko/fff, a project described as: The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS.
agentic.nvim AGENTS.md
Instructions for carlos-algms/agentic.nvim, covering agents guide, nested instructions, skill driven, domain glossary — lazy read and architectural decisions (adrs) — optional read.
hlchunk.nvim AGENTS.md
Instructions for shellRaining/hlchunk.nvim, covering agents.md, 项目定位, 技术栈约束, 本地命令 and 目录地图.
agentic.nvim CLAUDE.md
Instructions for carlos-algms/agentic.nvim: CRITICAL See @AGENTS.md for Instructions, it's the source of truth for all my instructions, no exceptions, it should be read and be part of your context before any other action.