Borrowing it
Nothing to install: this file belongs to GuionAI/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/GuionAI/web/main/AGENTS.mdgit clone --depth 1 https://github.com/GuionAI/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/guionai/web/agents-md)<a href="https://agentmods.dev/instructions/guionai/web/agents-md"><img src="https://agentmods.dev/badge/instructions/guionai/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/guionai/web/agents-md"><img src="https://agentmods.dev/badge/instructions/guionai/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 | $0.00343 | $0.00343 |
| Opus 5.5 | $0.00137 | $0.00137 |
| Sonnet 5.5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
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 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.
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.
What it actually says
AGENTS.md
Platform validation
Repository CI and local tests target Linux. Treat Windows behavior as best-effort here: keep Windows runners, Windows-specific smoke scripts, and simulated Windows tests out of this repository. Validate published packages on real Windows only in the downstream project that owns Windows usage.
DSH rc.1 Loader validation
For profile-local packaged plugins on DSH 0.1.2-rc.1 with Node 24, validate on the NUC through its installed official dsh CLI and real Loader. Keep DSH_HOME and every generated profile test-owned and disposable; the installed CLI and preset package are read-only inputs. Never use live profiles, presets, credentials, overrides, or services, and do not add custom runtime overrides or compatibility layers.
Managed DSH presets
The supported preset workflow is explicit: run web dsh sync before installing
or activating @guionai/dsh-web, then run web dsh doctor and require a zero
exit status. Sync compares standard, ptc, cordis, and minimal with the
official and compatible trees; modified same-id content requires interactive
confirmation or --yes. It must not mutate shipped presets, unrelated user
presets, credentials, or sessions. Tests use fixture source trees and
disposable DSH_HOME directories. End-to-end validation runs from the existing
NUC checkout, built on the NUC, using its installed official DSH CLI and a
disposable DSH_HOME. Do not transfer or validate a Web CLI packed on macOS.
Record the paths and results in the implementation report.
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 Changed · +13 lines · +164 tokens per session 1149b36941e9
- 2mo ago Changed · -10 tokens per session 146850ebd304
- 2mo ago Changed · +4 lines · +129 tokens per session e432da69b0b8
- 2mo ago First seen · 6 lines · 60 tokens per session scan A 30eff479d867
web AGENTS.md is an instructions file published in the GitHub repository GuionAI/web (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 343 tokens to every session, about $0.0014 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 2026-08-31.
web AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| web AGENTS.mdGuionAI/web | Instructions file | 1 | 1mo ago | Apache-2.0 | A | 343 | 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 | yesterday | 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 |