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/sa4hnd/vibra-code/claude-mdgit clone --depth 1 https://github.com/sa4hnd/vibra-codeWhat 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 | $0.04072 | $0.04072 |
| Opus 5 | $0.02036 | $0.02036 |
| Sonnet 5 | $0.00814 | $0.00814 |
| Haiku 4.5 | $0.00407 | $0.00407 |
Grade A, and why
vibra-code CLAUDE.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 2d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 2d ago First seen · 413 lines · 4,072 tokens per session scan A 9800ba9d46dd
vibra-code CLAUDE.md is an instructions file published in the GitHub repository sa4hnd/vibra-code (125 stars, last pushed 6mo ago), licensed AGPL-3.0. It adds 4,072 tokens to every session, about $0.0204 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
OpenTagViewer AGENTS.md
Instructions for parawanderer/OpenTagViewer, covering agents.md, what this project is, rules, 1. never ship a room schema change without a migration and 2. do not claim something works if you have not run it.
OpenTagViewer CLAUDE.md
Instructions for parawanderer/OpenTagViewer: The rules for this repo live in AGENTS.md, so that every agent reads the same file rather than two copies that drift apart. This one exists only to pull it in — Claude Code loads CLAUDE.md automatically, and the line below imports the real thing.
lotti AGENTS.md
AGENTS.md instructions for matthiasn/lotti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
apk-analyzer AGENTS.md
AGENTS.md instructions for MartinStyk/apk-analyzer, covering apk analyzer agent instructions, non-negotiables, development workflow, engineering principles and verifying a change.
lotti CLAUDE.md
Claude Code instructions for matthiasn/lotti, a project described as: A private logbook with a staff of personal AI assistants. Agents read what you record and propose what to do next — you approve the changes. End-to-end encrypted sync between your own devices — servers only ever see ciphertext. Local AI optional.
JiwuChat CLAUDE.md
Claude Code instructions for KiWi233333/JiwuChat, covering claude.md, project overview, technology stack, essential development commands and development.