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/vestaterm/vesta/agents-mdgit clone --depth 1 https://github.com/vestaterm/VestaWrote 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/vestaterm/vesta/agents-md)<a href="https://agentmods.dev/instructions/vestaterm/vesta/agents-md"><img src="https://agentmods.dev/badge/instructions/vestaterm/vesta/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 | $0.01229 | $0.01229 |
| Opus 5 | $0.00615 | $0.00615 |
| Sonnet 5 | $0.00246 | $0.00246 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
Vesta 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — rules for AI agents working in Vesta
Vesta is a native macOS terminal built on libghostty (linked as
GhosttyKit.xcframework, not a fork), with a project sidebar, tmux-style
splits, a persistent-session daemon, embedded Lua plugins, and a scriptable
vesta CLI. Swift/AppKit. Bundle id io.github.notnaki.vesta.
Read this before changing anything. Follow it.
Golden rules
- Match the surrounding code. Comment density, naming, and idioms vary by file — imitate the file you're editing. Don't reformat code you didn't change.
- Minimal diffs (ponytail). Ship the smallest change that works. No
speculative abstractions, no scaffolding "for later", delete before adding.
Mark deliberate shortcuts with a
ponytail:comment. - Never hardcode the version. It's stamped from the git tag by
make-app.sh. ReadUpdater.currentVersion(orCFBundleShortVersionString) — see the past bug where About/sidebar showed a stale0.1.0. - Verify against a RELEASE build, not just
swift run. Several bugs only appeared in the signed/notarized bundle (resource lookup, release-onlyassertelision). When in doubt,./make-app.sh releaseand run the bundle.
Build / run / test
swift build # fetches GhosttyKit automatically
swift run vesta selfcheck # pure-logic checks — MUST pass before commit
./make-app.sh [release|debug] # build Vesta.app (stamps version/build/commit)
open Vesta.app
selfcheckis the test harness — add an assertion there for non-trivial logic. It also fails loudly if bundled resources (fonts) can't be found.assert(...)is compiled out in release. Never put a side-effecting call insideassert(...)— hoist the call out, assert on the result.
Architecture (where things live, all under Sources/)
Vesta/main.swift—AppDelegate, app lifecycle, ⌘ keybinds, Lua bridge, toasts/notifications, onboarding + update wiring.Vesta/Chrome.swift— window, titlebar accessories, sidebar (incl. the update badge + version footer).Vesta/Control.swift— thevestaCLI verbs + the Unix-socket server.Vesta/Tabs.swift—SessionStore(app-owned pool) +Workspace(per-window view).Vesta/Updater.swift— in-app self-update (download DMG → swap → relaunch).Vesta/Notifier.swift,AboutWindow.swift,OnboardingOverlay.swift— self-named.vestad/— the session daemon (oneforkpty'd shell per pane + raw output ring).vesta-attach/— the per-pane relay ghostty spawns; dumb byte pump over a0600socket.VestaMux/— shared wire protocol (MuxProtocol) + paths (MuxPaths).
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 · 90 lines · 1,229 tokens per session scan A f39441cd686c
Vesta AGENTS.md is an instructions file published in the GitHub repository vestaterm/Vesta (21 stars, last pushed 5d ago), licensed MIT. It adds 1,229 tokens to every session, about $0.0061 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
zetty AGENTS.md
Instructions for webteractive/zetty, covering zetty — agent & contributor guide, what this is, layout, build / run and design rules ← read before any ui work.
zetty CLAUDE.md
Instructions for webteractive/zetty, covering zetty — agent & contributor guide, what this is, layout, build / run and design rules ← read before any ui work.
FluidAudio CLAUDE.md
Claude Code instructions for FluidInference/FluidAudio, covering claude.md, project overview, critical development rules, never use @unchecked sendable and never create dummy models or synthetic data.
wispterm AGENTS.md
Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.
mectrics AGENTS.md
AGENTS.md instructions for farukkamcici/mectrics, covering agents.md — working agreement for mectrics, 0. golden rule: english-only repository, 1. project shape, 2. internationalization (i18n) and 3. menu bar rendering rules.
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.