agentguard

Local-first safety guidance for AgentGuard, a tool that checks and records how AI agents operate in a code project. It uses the project’s settings and stores activity traces on your computer.

In plain words
What is it for?
Use it to initialise AgentGuard locally, run its diagnostic and quick-start commands, and create reports from agent activity traces.
Why use it?
It helps keep an initial integration private and avoids adding hosted services or API keys before they are needed. It also provides checks and reports for the recorded activity.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/bmdhodl/agent47/agentguard
Clone the repo
git clone --depth 1 https://github.com/bmdhodl/agent47

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 140 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash c8d44705c879, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

proof/skillpack/all/.cursor/rules/agentguard.mdc · 19 lines

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:
    1. agentguard doctor
    2. agentguard quickstart --framework raw --write
    3. python agentguard_raw_quickstart.py
    4. agentguard report .agentguard/traces.jsonl
Changes

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.

  1. yesterday First seen · 19 lines · 0 tokens per session scan A c8d44705c879

Subscribe to this mod's changes

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.