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/arcjet/arcjet-js/agents-mdgit clone --depth 1 https://github.com/arcjet/arcjet-jsWhat 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 | $0.00351 | $0.00351 |
| Opus 5 | $0.00176 | $0.00176 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
arcjet-js 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 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.
What it actually says
Agent guidance
Examples live in arcjet/examples
Do not add application examples under examples/ in this repository.
Examples were removed from this SDK in
#6217. New and remaining
examples belong in arcjet/examples.
The current migration PR is
arcjet/examples#193 — add
Guard / adapter demos there (or a follow-up on that repo), not here.
That includes:
- Framework apps (
nextjs-*,express-*, …) - Guard integration demos (
nextjs-ai-agent,eve-agent,mastra-agent)
Follow arcjet/examples CONTRIBUTING.md and its canonical example pattern
(package.json metadata, templated README, Dockerfile, compose.yaml,
devcontainer, LICENSE). Pin Arcjet packages to published versions. Standalone
AI examples that need a model key stay out of the default compose/CI matrix.
Do not restore .github/workflows/reusable-examples.yml or re-add an
examples CI job in this repo for new work.
README and skill links should point at
https://github.com/arcjet/examples/tree/main/examples/<name>, not at a
path under this repository.
Integration work: review before a PR
For Guard vendor integrations and other integration work, keep going on a branch and push it. Do not open a pull request until David confirms after reviewing the code. The final report must include the exact branch name, commit SHA, and a concise diff summary.
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 · 37 lines · 351 tokens per session scan A fd7477c2a0b0
arcjet-js AGENTS.md is an instructions file published in the GitHub repository arcjet/arcjet-js (681 stars, last pushed 3d ago), licensed Apache-2.0. It adds 351 tokens to every session, about $0.0018 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
Agent-Security-Regression-Harness AGENTS.md
Instructions for OWASP/Agent-Security-Regression-Harness, covering ai agent guide: owasp agent security regression harness, project overview, architecture, contribution workflow and what needs doing.
ziran CLAUDE.md
Instructions for taoq-ai/ziran, covering ziran development guidelines, active technologies, project structure, commands and code style.
ai-appsec AGENTS.md
Instructions for subodhkc/ai-appsec, covering agents.md — haiec agent security mcp (phase -1 → phase 18), 1. workspace layout, 2. architectural principles (apply to every phase), 3. hard constraints (never violate) and 4. phase discipline.
cyvisguard CLAUDE.md
Instructions for flankerhqd/cyvisguard: See AGENTS.md for repo orientation, commands, conventions, and the honesty invariants to preserve when touching demo/scenario code.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
llm-safe-haven AGENTS.md
Instructions for pleasedodisturb/llm-safe-haven, covering agents.md, what this file is (and isn't), why this shape (d-08), working agreements and current state.