Borrowing it
Nothing to install: this file belongs to multei/web. 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/multei/web/main/AGENTS.mdgit clone --depth 1 https://github.com/multei/webWrote 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/multei/web/agents-md)<a href="https://agentmods.dev/instructions/multei/web/agents-md"><img src="https://agentmods.dev/badge/instructions/multei/web/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/multei/web/agents-md"><img src="https://agentmods.dev/badge/instructions/multei/web/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 | $0.00828 | $0.00828 |
| Opus 5.5 | $0.00331 | $0.00331 |
| Sonnet 5.5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
web 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Commits
Always use progressive, atomic commits (see CONTRIBUTING.md):
- One logical change per commit.
- Every commit must leave the project green and cherry-pickable — install/build/test (and CI) should pass if that commit alone is applied on the default branch.
- Do not mix unrelated work or land half-finished changes that break the pipeline mid-series.
- Prefer a sequence of small commits over one large commit.
- Commit messages in English, using Conventional Commits (
feat,fix,docs,chore,refactor,test,ci, …).
Pull requests
- Always squash merge PRs:
gh pr merge <N> --squash. - Do not use
--mergeor--rebaseunless a maintainer explicitly asks for an exception. - Prefer an English Conventional Commits subject for the squash commit message.
- Before merge: assign
cursoragentwhen assignable, otherwisejimmyandrade, and ensure at least one meaningful label. Never merge without both.
Issues
- Create and edit GitHub issues in English (title and body). Do not open new issues in Portuguese.
- Prefer Conventional Commit-style titles when helpful (
ci: …,docs: …,feat: …).
When implementing a GitHub issue, always:
- Read the full issue (scope checklists, acceptance criteria, notes) before coding.
- After implementation finishes, update the issue body:
- Mark completed items with
- [x]. - Leave unfinished items unchecked and note what is still pending.
- Mirror the same for acceptance criteria.
- Mark completed items with
- Comment with a short summary of what shipped and follow-ups (English).
- Close only when acceptance criteria are satisfied; otherwise leave open (or reopen) with remaining items clear.
Troubleshooting
Whenever you encounter an error while installing, building, developing, testing, or deploying this project:
- Check
TROUBLESHOOTING.mdfor an existing entry first. - If the error is new, add a section to
TROUBLESHOOTING.mdfollowing the same format as the existing entries:- A short heading describing the failure
- When/how it appears (command + terminal excerpt)
- Numbered recovery steps that worked (or the best known workaround)
- Prefer documenting durable fixes over one-off environment hacks, but record workarounds when that is all that unblocks the task.
- Do this in the same session you hit the error — do not wait to be asked.
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 · 61 lines · 828 tokens per session scan A d3c6adf453ad
web AGENTS.md is an instructions file published in the GitHub repository multei/web (4 stars, last pushed today), licensed MIT. It adds 828 tokens to every session, about $0.0033 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 2026-11-07.
web AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| web AGENTS.mdmultei/web | Instructions file | 4 | today | MIT | A | 828 | 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 | today | 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 |