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/alsi-lawr/agent-term.nvim/agents-mdgit clone --depth 1 https://github.com/alsi-lawr/agent-term.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/alsi-lawr/agent-term.nvim/agents-md)<a href="https://agentmods.dev/instructions/alsi-lawr/agent-term.nvim/agents-md"><img src="https://agentmods.dev/badge/instructions/alsi-lawr/agent-term.nvim/agents-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 5.1 | $0.01321 | $0.01321 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
agent-term.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 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Direction
- Prefer clean, direct design with explicit module boundaries. Add compatibility layers only when there is a concrete supported-compatibility requirement.
- Keep the plugin agent-neutral. Use
agent,session,terminal, or capability-oriented names for new code. - Use
codexonly for the Codex preset/default command, demo material, or user-facing examples that explicitly refer to Codex. - Do not add root-level shim modules in
lua/agent_term/just to re-export deeper modules. Require the real module path directly. - Favor clear module boundaries over broad compatibility surfaces. If an API is internal, keep it internal and update call sites when it moves.
Project Structure
- Core plugin code lives in
lua/agent_term/. - Entry point:
lua/agent_term/init.lua. - Functional areas are split by concern:
lua/agent_term/runtime/: terminal session lifecycle, resume behavior, and shared state.lua/agent_term/ui/: float, panel, and view-controller behavior.lua/agent_term/context/: editor context capture, message building, hook submission, and diagnostics formatting.lua/agent_term/setup/: defaults, preset expansion, schema helpers, commands, and keymaps.
- Tests live under
tests/:tests/spec/: Plenary/Busted specs.tests/helpers/: test utilities.
- Docs/media live in
README.md,docs/, andassets/.
Agent And Context Semantics
- Agent behavior should be expressed as capabilities on
agent, not as hard-coded agent names. - Presets may provide defaults, but explicit user config should override preset behavior.
- Context submission supports agent modes:
paste: send context visibly to the running terminal job.hook: emit the configuredUserautocmd hook and fall back to paste if no receiver handles it.
- Hook mode is agent-driven, not view-driven. It must work from panel mode, float mode, and source windows while a panel exists.
- Do not infer hook context support from an agent having hooks generally. For example, Copilot and Opencode use paste mode because their hooks are not compatible with this context-injection path.
- Panel focus only affects which editor context is used. When the panel is focused, use the last captured source context instead of reading context from the terminal buffer.
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 · 115 lines · 1,321 tokens per session scan A 0b8b8a72d593
agent-term.nvim AGENTS.md is an instructions file published in the GitHub repository alsi-lawr/agent-term.nvim (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,321 tokens to every session, about $0.0066 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
agentrq AGENTS.md
AGENTS.md instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, desktop app (desktop/), three traps that are invisible in source and running tests.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
grix AGENTS.md
AGENTS.md instructions for askie/grix, covering grix agent guide, repository boundaries, required workflows, shared agent configuration and cross-component contracts.
moo-tasks AGENTS.md
Instructions for dizlexic/moo-tasks, covering agents.md, 1. what is the moo tasks board?, 2. connecting your agent, 3. available mcp tools and 4. recommended workflow for agents.
pi CLAUDE.md
Instructions for share-skills/pi, covering 强制, 内部目标（不可写入公开文件）, 跑分规范 and eval 驱动优化规则.