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 rules/bmdhodl/agent47/agentguardgit clone --depth 1 https://github.com/bmdhodl/agent47What 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 | $0.00000 | $0.00140 |
| Opus 5 | $0.00000 | $0.00070 |
| Sonnet 5 | $0.00000 | $0.00028 |
| Haiku 4.5 | $0.00000 | $0.00014 |
Grade A, and why
agentguard 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.
What it actually says
When integrating AgentGuard:
- keep the first run local
- honor the repo's
.agentguard.json - keep traces in
.agentguard/traces.jsonl - prefer
agentguard.init(local_only=True) - do not add API keys or hosted settings in the first PR
- verify with:
agentguard doctoragentguard quickstart --framework raw --writepython agentguard_raw_quickstart.pyagentguard report .agentguard/traces.jsonl
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 · 19 lines · 0 tokens per session scan A c8d44705c879
agentguard is a cursor rule published in the GitHub repository bmdhodl/agent47 (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 140 tokens. 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.
Other cursor rules, from other repositories
selectools-testing
Testing conventions and patterns for selectools.
selectools-agent-core
Rules for working with the agent core loop in selectools.
selectools-development
Selectools development conventions, testing requirements, and release process.
selectools-docs
Documentation standards for selectools docs and MkDocs site.
selectools-providers
Rules for working with LLM provider adapters in selectools.
cursorrules
When working with AI agents in this project, use Authensor for safety.