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/rcarmo/vibes/agents-mdgit clone --depth 1 https://github.com/rcarmo/vibesWhat 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 | $0.01495 | $0.01495 |
| Opus 5 | $0.00747 | $0.00747 |
| Sonnet 5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
vibes 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository.
Project shape
Vibes is a Go backend with an embedded Bun-built frontend:
- Backend:
cmd/,internal/ - Frontend source:
static/js/,static/css/ - Generated frontend bundle:
static/dist/ - Frontend build script:
build.js - E2E tests:
tests/
Always treat static/dist/* as generated output. Change source files first, then rebuild through the Makefile:
make frontend
Use the Makefile
Use make targets for normal development, validation, builds and serving. Do not run ad-hoc go, bun, or node commands when an equivalent Makefile target exists.
Common targets:
make frontend # typecheck converted TS modules + rebuild static/dist/
make lint-frontend # run frontend ESLint
make typecheck-frontend # type-check converted TypeScript frontend modules
make build # frontend + Go binary
make build-go # Go binary only, assumes static/dist exists
make test # Go tests
make lint # Go vet
make check # lint + test + coverage
make serve # build and run
make dev # run from source for local development
make e2e # Playwright E2E flow
If a workflow needs a raw command that is not represented in Makefile, prefer adding or updating a Makefile target first. Use raw go, bun, or node commands only for one-off diagnostics, dependency maintenance, or when explicitly requested, and mention why in your notes.
Frontend development principles
The frontend should move steadily away from large monolithic files and toward small, typed, capability-oriented modules.
Modularity
Prefer small files with clear responsibilities over expanding existing large modules.
Recommended structure as the frontend grows:
static/js/
app.js # app wiring only; avoid adding feature logic here
api/ # API clients grouped by backend area
components/ # reusable Preact components
components/compose/ # compose box subcomponents
components/timeline/ # timeline subcomponents
features/ # feature-level modules, e.g. backends, workspace, settings
hooks/ # reusable Preact hooks
lib/ # pure utilities with no DOM assumptions
types/ # shared TS types once TypeScript is introduced
ui/ # low-level UI helpers
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 · 205 lines · 1,495 tokens per session scan A 5382962a1e65
vibes AGENTS.md is an instructions file published in the GitHub repository rcarmo/vibes (190 stars, last pushed 1mo ago), licensed MIT. It adds 1,495 tokens to every session, about $0.0075 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 2026-09-01.
Other instructions, from other repositories
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
paseo CLAUDE.md
Claude Code instructions for getpaseo/paseo, covering claude.md, repository map, docs, writing docs and doc voice.
copilot copilot-instructions.md
Instructions for navikt/copilot, covering copilot instructions for navikt/copilot, repository overview, nav development standards, nav principles and nav tech stack.
copilot AGENTS.md
Instructions for navikt/copilot, covering agents.md for navikt/copilot, what this repo is, efficiency rule, standard commands and conventions.
paseo AGENTS.md
AGENTS.md instructions for getpaseo/paseo, a project described as: Orchestrate multiple coding agents from desktop and mobile.
awesome-reviewers CLAUDE.md
Instructions for baz-scm/awesome-reviewers, covering awesome reviewers — repository guidelines, what this project is, source of truth, site layer and machine interface.