Borrowing it
Nothing to install: this file belongs to hsr88/scavi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hsr88/scavi/main/AGENTS.mdgit clone --depth 1 https://github.com/hsr88/scaviWrote 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/hsr88/scavi/agents-md)<a href="https://agentmods.dev/instructions/hsr88/scavi/agents-md"><img src="https://agentmods.dev/badge/instructions/hsr88/scavi/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/hsr88/scavi/agents-md"><img src="https://agentmods.dev/badge/instructions/hsr88/scavi/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01830 | $0.01830 |
| Opus 5.5 | $0.00732 | $0.00732 |
| Sonnet 5.5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade B, and why
scavi AGENTS.md scanned grade B with 1 finding 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 2mo 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
* execute arbitrary commands extracted from documentation How it starts
The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scavi — Agent Instructions
Scavi is an open-source context linter for AI coding agents.
The context linter for AI coding agents. Keep your agents in sync with your code.
These instructions apply to AI coding agents working inside the Scavi repository.
Core principle
Scavi should never use an LLM when the repository can provide a deterministic answer.
This is the most important architectural rule in the project.
Before introducing an LLM call, ask:
- Can this be determined from the filesystem?
- Can this be determined from a manifest or configuration file?
- Can this be determined from Git metadata?
- Can this be determined through static parsing?
- Can this be determined through deterministic repository search?
If the answer to any of these is yes, do not use an LLM.
Examples of deterministic checks:
- whether a referenced path exists
- whether a package script exists
- which package manager the repository uses
- whether a dependency is installed
- what version is declared in a manifest
- whether a referenced file exists
- whether two context files give conflicting package-manager instructions
LLMs are reserved for claims that require semantic interpretation.
Product behavior
Scavi validates instructions intended for AI coding agents against the actual repository.
Initial context formats include:
AGENTS.md
CLAUDE.md
GEMINI.md
.github/copilot-instructions.md
.cursor/rules/*.mdc
Scavi should detect:
- stale instructions
- invalid paths
- invalid commands
- outdated dependency/version claims
- package-manager mismatches
- missing referenced files
- conflicting instructions across context files
- semantic claims that no longer match implementation
Engineering priorities
When making implementation decisions, prioritize in this order:
- correctness
- low false-positive rate
- explainability
- deterministic behavior
- privacy
- performance
- extensibility
A context linter that produces noisy warnings will be disabled.
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.
- 2mo ago First seen · 477 lines · 1,830 tokens per session scan B a169e53adc4f
scavi AGENTS.md is an instructions file published in the GitHub repository hsr88/scavi (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,830 tokens to every session, about $0.0073 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
scavi AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scavi AGENTS.mdhsr88/scavi | Instructions file | 1 | 2mo ago | MIT | B | 1,830 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |