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/makefinks/doubt.nvim/agents-mdgit clone --depth 1 https://github.com/makefinks/doubt.nvimWhat 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 | $0.01625 | $0.01625 |
| Opus 5 | $0.00813 | $0.00813 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
doubt.nvim 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 yesterday.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operational guidance for coding agents working in doubt.nvim.
This file is intentionally practical: run commands exactly as listed, follow module ownership, and preserve existing behavior unless explicitly changing it.
Project Snapshot
- Project:
doubt.nvim(Neovim plugin for skeptical code review and handoff export). - Language/runtime: Lua on Neovim APIs (
vim.api,vim.fn,vim.ui,vim.json,vim.uv). - Required dependency:
MunifTanjim/nui.nvim. - Entrypoints:
plugin/doubt.luabootstrap andrequire("doubt").setup(...). - Core workflow: create claims -> persist sessions -> refresh/reanchor freshness -> export XML/templates.
Repository Layout
plugin/doubt.lua: plugin bootstrap, command registration on load.lua/doubt/init.lua: top-level orchestration and public API.lua/doubt/config.lua: defaults, setup merge, highlights.lua/doubt/claims.lua: claim normalization, sorting, anchor validation.lua/doubt/state.lua: persistence and workspace-scoped session mutation.lua/doubt/render.lua: extmarks/signs/inline note rendering.lua/doubt/panel.lua: side panel UI and help modal.lua/doubt/export.lua: XML and template rendering.lua/doubt/input.lua: wrappers aroundnui.inputand checklist input.lua/doubt/commands.lua::Doubt*command wiring.lua/doubt/keymaps.lua: default keymaps and claim-kind mappings.tests/*_spec.lua: Plenary/Busted-style headless Neovim specs.tests/minimal_init.lua: minimal runtime setup for Plenary tests.tests/helpers/bootstrap.lua: test bootstrap and minimal assertions.
Build, Lint, and Test Commands
There is no separate build step and no configured linter/formatter in-repo (stylua, luacheck, selene, make, and CI config are absent).
Use the Plenary headless runner for tests. scripts/run_tests.sh downloads plenary.nvim to .deps/plenary.nvim if PLENARY_DIR is not set.
# Run full test suite (all spec files)
./scripts/run_tests.sh
# Run one specific test file (single-test workflow)
./scripts/run_tests.sh tests/plugin_bootstrap_spec.lua
# Example: run another specific spec file
./scripts/run_tests.sh tests/claim_anchor_model_spec.lua
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.
- yesterday First seen · 154 lines · 1,625 tokens per session scan A 770212c8aead
doubt.nvim AGENTS.md is an instructions file published in the GitHub repository makefinks/doubt.nvim (5 stars, last pushed 23d ago), licensed MIT. It adds 1,625 tokens to every session, about $0.0081 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
opencode.nvim AGENTS.md
Instructions for nickjvandyke/opencode.nvim, covering opencode.nvim — agent guide, what it is, entrypoints, config quirks and dependencies.
sidekick.nvim AGENTS.md
Instructions for folke/sidekick.nvim, covering agent cheat sheet, project overview, everyday commands, adding features and writing tests.
claude-code.nvim CLAUDE.md
Instructions for greggh/claude-code.nvim, covering project: claude code plugin, essential commands, project structure, current focus and multi-instance support.
dotfiles AGENTS.md
Cross-platform dotfiles managed by Chezmoi with Homebrew/apt and per-language version managers. One-command bootstrap for macOS and Linux with Neovim, Tmux, Zsh, and AI agent skills.
down.nvim copilot-instructions.md
Copilot instructions for clpi/down.nvim, a project described as: the (eventually) infinitely extensible markdown note-taking work environment that you can have in Neovim without having to ever leave the comfort of markdown.
claudecode.nvim CLAUDE.md
Instructions for coder/claudecode.nvim, covering claude.md, project overview, common development commands, testing and code quality.