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/kcaldas/vim-navigator/agents-mdgit clone --depth 1 https://github.com/kcaldas/vim-navigatorWhat 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 | $0.01207 | $0.01207 |
| Opus 5 | $0.00603 | $0.00603 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
vim-navigator AGENTS.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 2d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vim Navigator — Agent Guide
You have access to a Neovim instance that the user is watching. Use it to show things, not just tell. This turns code explanations from walls of text into guided visual walkthroughs.
When to use vim-navigator
- Code walkthroughs: Opening files, jumping to key lines, annotating the important parts.
- Architecture explanations: Split two related files side by side (e.g. proto definition + Go implementation).
- Code reviews: Highlight the lines that changed, annotate what matters.
- Debugging: Navigate to the problem, highlight the bug, annotate the fix.
- Onboarding: Walk through a codebase layer by layer, folding away noise.
Tools at a glance
| Tool | Use for |
|---|---|
open_file(path, line) |
Open a file, jump to a line. Always use absolute paths. |
goto_line(line) |
Move within the current file. |
highlight_lines(start, end, label) |
Draw attention to a range. Add a label to explain why. |
annotate(line, text) |
Add a short note at end of a line. Keep it under ~60 chars. |
fold_range(start, end) |
Hide irrelevant code to reduce noise. |
unfold_all() |
Show everything again. |
clear() |
Wipe all highlights/annotations from current buffer. Always clear before switching topics. |
close_splits() |
Go back to a single window. |
split_open(path, line, vertical) |
Show two files side by side. Great for contract vs implementation. |
get_context() |
Check what the user is currently seeing (file, cursor, visible lines). |
vim_command(command) |
Escape hatch for anything else (e.g. set number, syntax on). |
Walkthrough mode
When the user asks for a walkthrough (e.g. "walk me through this PR", "show me how this works"), follow this interactive pattern:
-
Plan the layers — Break the walkthrough into logical steps (e.g. by feature layer, data flow, or file boundary). Mention the plan briefly so the user knows the shape of what's coming.
-
For each step:
clear()any previous highlights.- Open the relevant file, highlight and annotate the key parts.
- Write a brief text explanation of what you're showing and why it matters. Keep it to 2-4 sentences — the code is already on screen.
- Pause and ask the user a question — either to confirm understanding or invite questions before continuing. Don't move on until they respond.
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.
- 2d ago First seen · 114 lines · 1,207 tokens per session scan A 5e0b1ed8f2e3
vim-navigator AGENTS.md is an instructions file published in the GitHub repository kcaldas/vim-navigator (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,207 tokens to every session, about $0.0060 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.