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/sarv/sarvterminal/agents-mdgit clone --depth 1 https://github.com/Sarv/SarvTerminalWrote 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/sarv/sarvterminal/agents-md)<a href="https://agentmods.dev/instructions/sarv/sarvterminal/agents-md"><img src="https://agentmods.dev/badge/instructions/sarv/sarvterminal/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 | $0.00836 | $0.00836 |
| Opus 5 | $0.00418 | $0.00418 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
SarvTerminal 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Development Guide
A file for guiding coding agents.
Commands
- Build:
zig build- If you're on macOS and don't need to build the macOS app, use
-Demit-macos-app=falseto skip building the app bundle and speed up compilation.
- If you're on macOS and don't need to build the macOS app, use
- Test (Zig):
zig build test- Prefer to run targeted tests with
-Dtest-filterbecause the full test suite is slow to run.
- Prefer to run targeted tests with
- Test filter (Zig):
zig build test -Dtest-filter=<test name> - Formatting (Zig):
zig fmt . - Formatting (Swift):
swiftlint lint --strict --fix - Formatting (other):
prettier -w .
libghostty-vt
- Build:
zig build -Demit-lib-vt - Build WASM:
zig build -Demit-lib-vt -Dtarget=wasm32-freestanding -Doptimize=ReleaseSmall - Test:
zig build test-lib-vt -Dtest-filter=<filter>- Prefer this when the change is in a libghostty-vt file
- All C enums in
include/ghostty/vt/must have a_MAX_VALUE = GHOSTTY_ENUM_MAX_VALUEsentinel as the last entry to force int enum sizing (pre-C23 portability).
Directory Structure
- Shared Zig core:
src/ - macOS app:
macos/ - GTK (Linux and FreeBSD) app:
src/apprt/gtk
Linux/GTK Port Roadmap (LINUX-ROADMAP.md)
LINUX-ROADMAP.md(repo root) is the single hand-off file for porting our macOS Vaults behavior to the Linux/GTK app (src/apprt/gtk). It captures, per change: the symptom, the root-cause reasoning, the platform-agnostic logic/algorithm, the macOS→GTK equivalents (which AppKit/Swift/libproc/ARC bits map to which GTK/Zig mechanism), and how to verify on Linux. The goal: a future AI agent can read only this file and reproduce the exact same behavior on Linux.- Process rule — update it at COMMIT time, not per edit. Whenever you commit a
change under
macos/, add (in the same commit) a matching entry toLINUX-ROADMAP.md. We record at commit time because a commit lands only after multiple iterations of testing/fixing once the code actually runs correctly — so the entry captures the final, working logic, not the intermediate churn. - Keep one section per logical change, mirroring the commit. Preserve the subsection shape already in the file (Symptom / Root cause & reasoning / platform-agnostic logic / macOS→Linux equivalents / How to verify on Linux).
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 · 68 lines · 836 tokens per session scan A d64e93de3e20
SarvTerminal AGENTS.md is an instructions file published in the GitHub repository Sarv/SarvTerminal (56 stars, last pushed 4d ago), licensed MIT. It adds 836 tokens to every session, about $0.0042 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
SForum AGENTS.md
AGENTS.md instructions for zhuchunshu/SForum, covering agent guide, project intent, working principles, stack and directory map and commands.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
redd-archiver CLAUDE.md
Instructions for 19-84/redd-archiver, covering claude.md, project overview, deviations from global standards, build & run commands and docker development (primary method).