Borrowing it
Nothing to install: this file belongs to veryfront/veryfront-code. 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/veryfront/veryfront-code/main/AGENTS.mdgit clone --depth 1 https://github.com/veryfront/veryfront-codeWrote 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/veryfront/veryfront-code/agents-md)<a href="https://agentmods.dev/instructions/veryfront/veryfront-code/agents-md"><img src="https://agentmods.dev/badge/instructions/veryfront/veryfront-code/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/veryfront/veryfront-code/agents-md"><img src="https://agentmods.dev/badge/instructions/veryfront/veryfront-code/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 | $0.04626 | $0.04626 |
| Opus 5.5 | $0.01850 | $0.01850 |
| Sonnet 5.5 | $0.00925 | $0.00925 |
| Haiku 4.5 | $0.00463 | $0.00463 |
Grade A, and why
veryfront-code 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 22d 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Veryfront code agent guide
This guide governs veryfront-code/. Deeper AGENTS.md files override it for their subtrees. The cli/ subtree has its own guide at cli/AGENTS.md and that guide is the narrower authority for CLI command work.
Veryfront Code is the Deno-first framework and runtime package for Veryfront. It contains the public veryfront/* APIs, the runtime server, SSR/RSC support, agent and workflow primitives, runs, tasks, MCP support, and CLI entrypoints.
Default working style
- Prefer the smallest viable diff.
- Preserve public API compatibility unless the task explicitly asks for a breaking change.
- For behavior changes, add or update a focused failing test before changing implementation.
- Reuse existing modules, schemas, adapters, and error patterns before adding new abstractions.
- Keep public behavior grounded in code evidence, generated types, and tests.
- Update docs, examples, generated references, and command help when public behavior changes.
- Do not rename, move, or refactor unrelated code.
- Do not add dependencies unless the task explicitly requires them.
Code Review Rules
- Review the complete branch diff against its base. Identify the changed invariants, then inspect
every affected caller and sibling path, including failure paths, cache readers/writers and
invalidation. Use
rgto check coverage beyond the changed lines. - Before reporting a defect, check other occurrences of the same root cause. Group those occurrences in one finding with the affected paths, a concrete trigger and consequence, and regression evidence where available. Do not stop investigating after the first occurrence.
- Distinguish actionable regressions and merge blockers from optional improvements. When revisiting feedback, verify the fix across its affected paths; report a recurring defect only with concrete evidence that it remains or a distinct path that the fix missed.
Fixing Review Findings
- Diagnose the violated invariant before patching a reported line. Search all callers and sibling paths and fix the same root cause throughout the affected area in one batch.
- Add or update regression tests for the affected behavior, including existing callers and failure paths. Demonstrate that a regression test fails without the fix and passes with it.
- Keep pull requests draft while implementing a feedback batch. Complete the related fixes, run
the repository's narrow affected checks (such as
deno task test:file), and satisfy the required local reviews before pushing the batch and requesting the next GitHub review. Use a local command wrapper when the workspace requires one. Preserve all required review and CI gates. - If another review finds the same violated invariant on a sibling path, reassess its ownership boundary and complete the caller sweep before requesting another review.
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.
- 22d ago Changed · +25 lines · +343 tokens per session bbae83a27727
- 1mo ago Changed · +2 lines · +68 tokens per session ff420ecf3ae2
- 1mo ago Changed · +28 lines · +316 tokens per session a8803209685d
- 1mo ago Changed · +10 lines · +152 tokens per session 548780d8ebeb
- 2mo ago Changed · +3 lines · +55 tokens per session 75c5fe96e35f
- 2mo ago First seen · 342 lines · 3,692 tokens per session scan A 64ca2357cf7e
veryfront-code AGENTS.md is an instructions file published in the GitHub repository veryfront/veryfront-code (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,626 tokens to every session, about $0.0185 per session on Opus 5.5. 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.
veryfront-code AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| veryfront-code AGENTS.mdveryfront/veryfront-code | Instructions file | 20 | yesterday | Apache-2.0 | A | 4,626 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |