agent-instinct-system

agent-instinct-system is a skill for Claude Code from itallstartedwithaidea/agent-skills. It costs 36 tokens per session (2,174 once invoked), scanned C, original, MIT.

A safety layer for coding agents that runs checks before code changes, tool calls, or generated output.

In plain words
What is it for?
Use it to add automatic safety checks around file deletion, budget-sensitive API actions, and other potentially damaging agent operations.
Why use it?
It helps prevent protected files from being changed, destructive actions from running without confirmation, and unsafe operations from exceeding set limits.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the claude-mythos-skills plugin — 10 skills shipped together , and of all-skills

Good fit Use it to add automatic safety checks around file deletion, budget-sensitive API…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itallstartedwithaidea/agent-skills/agent-instinct-system
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.

Any agent
npx skills add itallstartedwithaidea/agent-skills --skill agent-instinct-system
Clone the repo
git clone --depth 1 https://github.com/itallstartedwithaidea/agent-skills

Made for: Claude Code.

Or install claude-mythos-skills, the plugin that ships this one along with the rest of its 10 skills.

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.

agentmods badge for agent-instinct-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/agent-instinct-system.svg)](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/agent-instinct-system)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/agent-instinct-system"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/agent-instinct-system.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.02174
Opus 5 $0.00018 $0.01087
Sonnet 5 $0.00007 $0.00435
Haiku 4.5 $0.00004 $0.00217

Measured 7d ago against content hash f71c81b9a720, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

agent-instinct-system scanned grade C with 1 finding 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

const destructive = ["rm -rf", "DROP TABLE", "DELETE FROM", "git push --force"];
skills/claude-mythos/agent-instinct-system/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instinct System

Part of Agent Skills™ by googleadsagent.ai™

Description

The Agent Instinct System implements pre-cognitive reflexes — automatic safety checks and validations that fire before every code change, tool call, or output generation. Just as biological reflexes protect organisms from harm faster than conscious thought, agent instincts protect codebases and systems from damage faster than deliberate reasoning. These instincts operate below the level of task-specific logic, forming a universal safety layer that activates regardless of what the agent is doing.

Developed for the Buddy™ agent at googleadsagent.ai™, where a single incorrect Google Ads API call could burn through a client's entire monthly budget, the instinct system enforces invariants that must never be violated. Budget caps are checked before bid modifications. Destructive operations require confirmation signals. File deletions are validated against protection lists. These checks happen automatically, without the agent needing to "remember" to perform them.

The instinct system is organized into three tiers: reflexes (instant, zero-cost checks like "is this file in the protected list"), gates (lightweight validations like "does this change pass the linter"), and assessments (more expensive checks like "does this modification align with the stated task"). Each tier adds latency but catches increasingly subtle issues.

Use When

  • Agents operate on production systems where mistakes have real consequences
  • You need defense-in-depth beyond what a single verification step provides
  • Multiple agents or team members work on the same codebase simultaneously
  • The agent handles destructive operations (deletions, deployments, API mutations)
  • Compliance requirements mandate pre-action validation for AI-generated changes
  • You want to prevent entire categories of mistakes rather than catching them after the fact

Read the full file on GitHub · 217 lines

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. 7d ago First seen · 217 lines · 36 tokens per session scan C f71c81b9a720

Subscribe to this mod's changes

agent-instinct-system is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 2,174 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.