What is agt-security?

A security skill for validating agent sandboxes, checking process hygiene, verifying budgets, and rotating the HMAC key used by a local control system. HMAC is a method for checking that messages were created by a trusted sender and were not changed.

It is for checking sandbox isolation, verifying restricted environment behavior, inspecting container use, and rotating the session HMAC key.

It helps detect unsafe execution boundaries and maintain the secret key used to authenticate messages between local agents or services.

agt-security — Skill for Claude Code by richfrem/agent-plugins-skills

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

agentmods

npx agentmods add skills/richfrem/agent-plugins-skills/agt-security

Made for: Claude Code.

Or install cli-agents, the plugin that ships this one along with the rest of its 11 skills, 13 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/agt-security/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/agt-security)

Your own site

<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/agt-security"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/agt-security/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/agt-security"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/agt-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 546 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.00546
Opus 5.5	$0.00012	$0.00218
Sonnet 5.5	$0.00006	$0.00109
Haiku 4.5	$0.00003	$0.00055

Measured 18d ago against content hash 2ea0459852e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agt-security 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 18d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/agt_ops.py, scripts/path_security.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/cli-agents/skills/agt-security/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Group Theory Security (agt-security)

Manages local execution sandboxes, verifies process hygiene limits, and rotates cryptographic HMAC bus keys under Agentic Group Theory (AGT).

Critical Constraints
Quick start
Workflow
Verification
References

Critical Constraints

Environment Hygiene: Ensure banned execution variables (PYTHONPATH, PYTHONHOME, LD_PRELOAD, DYLD_LIBRARY_PATH) are scrubbed before subprocess launch.
Path Containment: Ensure filesystem operations outside declared root boundaries raise explicit PermissionError exceptions.
Key Permission Enforcement: HMAC session keys must be created exclusively with 0600 permissions inside protected secret storage (context/exploration/.secrets/).
Zero Key Leakage: Never print, log, or leak raw HMAC key bytes to stdout, telemetry, or conversational outputs.

Quick start

# Verify sandbox hygiene and path containment
python3 plugins/cli-agents/scripts/agt_ops.py verify-sandbox

# Rotate local HMAC session signing key
python3 plugins/cli-agents/scripts/agt_ops.py rotate-key

Workflow

Phase 1: Environment Hygiene Check: Run agt_ops.py verify-sandbox to verify environment variable sanitization in subprocess runners.
Phase 2: Boundary Containment Verification: Confirm that path containment rules trigger PermissionError when accessing out-of-bounds directories.
Phase 3: Cryptographic Key Rotation: Execute agt_ops.py rotate-key to generate a 32-byte cryptographically secure HMAC session key with 0600 mode.
Phase 4: Permission Verification: Verify file mode permissions on session_hmac.key to ensure unauthorized read access is prevented.

Verification

# Run sandbox verification
python3 plugins/cli-agents/scripts/agt_ops.py verify-sandbox

# Audit skill compliance
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/cli-agents/skills/agt-security --mode source

Read the full file on GitHub · 56 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

18d ago Changed · +18 lines 2ea0459852e9
1mo ago First seen · 38 lines · 30 tokens per session scan A 8a3bded974b0

Subscribe to this mod's changes

agt-security is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 546 once invoked, about $0.0001 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 2026-09-03.

Security agent-evaluation agent-orchestration agentic-control-plane agentic-os agentic-workflows ai-agent-governance

agt-security

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agentic Group Theory Security (agt-security)

Contents

Critical Constraints

Quick start

Workflow

Verification

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

autoprompt

autoprompt

ap-route-analyst

ap-roadmap-author

ap-depth-prober

ap-fresh-verifier