prempti-falco-rules

prempti-falco-rules is a skill for Claude Code from falcosecurity/prempti. It costs 123 tokens per session (5,639 once invoked), scanned D, original, Apache-2.0.

A rule-writing guide for Prempti, a control layer that watches what AI coding agents do. It helps define whether a tool call—such as a command, file access, or MCP request—is allowed, blocked, or requires confirmation.

In plain words
What is it for?
Use it to create, change, or debug rules that allow, deny, or ask about agent actions such as running shell commands, reading or writing files, and making MCP calls.
Why use it?
It helps prevent coding agents from performing unsafe or unwanted actions without clear control. It also provides explanations when an action is blocked or needs approval.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/myproject/.

Good fit Use it to create, change, or debug rules that allow, deny, or ask about agent actions such as running shell commands, reading or writing files, and making MCP calls.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin prempti-falco-rules/plugin install prempti-falco-rules after adding the marketplace above.

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 prempti-falco-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/falcosecurity/prempti/prempti-falco-rules/github.svg)](https://agentmods.dev/skills/falcosecurity/prempti/prempti-falco-rules)
Your own site
<a href="https://agentmods.dev/skills/falcosecurity/prempti/prempti-falco-rules"><img src="https://agentmods.dev/badge/skills/falcosecurity/prempti/prempti-falco-rules/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.

agentmods 80×15 button for prempti-falco-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/falcosecurity/prempti/prempti-falco-rules"><img src="https://agentmods.dev/badge/skills/falcosecurity/prempti/prempti-falco-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,639 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 4 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.05639
Opus 5 $0.00062 $0.02819
Sonnet 5 $0.00025 $0.01128
Haiku 4.5 $0.00012 $0.00564

Measured 11d ago against content hash 1219c9e3f7dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

prempti-falco-rules scanned grade D with 4 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 11d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Falco blocked running sudo because elevated privileges are not permitted

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

7. **Self-protection** — block agent attempts to disable Prempti: every `premptictl` invocation, platform service-stop alternatives (systemctl / launchctl / taskkill / pkill), writes under the install prefix, and writes

Recursive force deletehighDestructive command

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

| `contains` | `tool.input_command contains "rm -rf"` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `regex` | `tool.input_command regex "curl.*\|.*sh"` — RE2 regular expression |
skills/prempti-falco-rules/SKILL.md · 451 lines

How it starts

The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prempti Falco Rules Author

Write custom Falco rules that govern what AI coding agents can do at runtime. These rules intercept tool calls (shell commands, file writes/reads, MCP calls) and enforce allow/deny/ask verdicts before execution.

Context: How This System Works

Prempti intercepts every tool call a coding agent makes. Each call becomes a Falco event with structured fields. Your rules evaluate these events and decide the verdict:

  • deny — block the tool call entirely (the agent sees an explanation)
  • ask — prompt the user for confirmation (they see your output message directly)
  • allow — no tag needed; tool calls that match no deny/ask rule are allowed

The agent sees the verdict reason as: "Rule Name: <your output message> | For AI Agents: ... | correlation=<id>". For deny verdicts, the LLM reformulates this for the user. For ask verdicts, the user reads your output message directly in a permission prompt — so write it for a human audience.

Available Fields

Every tool call event exposes these fields for conditions and output:

Field Type Description
correlation.id u64 Unique event ID (always > 0, auto-included in output_fields)
agent.name string Agent identifier (e.g., claude_code)
agent.os string Host OS: linux, macos, windows, or unknown
agent.pid u64 PID of the agent process that invoked the hook (auto-included in output_fields). 0 when the platform lookup fails.
agent.hook_event_name string Hook lifecycle point (e.g., PreToolUse)
agent.session_id string Session identifier
agent.model string Model identifier (Codex-only; empty for Claude Code)
agent.turn_id string Turn identifier within a session (Codex-only; empty for Claude Code)
agent.cwd string Working directory as reported by the agent
agent.real_cwd string Working directory resolved to absolute canonical path
agent.real_cwd_prefix string Resolved working directory with one trailing /; use for path containment checks
tool.name string Tool name: Bash, Write, Edit, Read, Glob, Grep, Agent, etc.
tool.use_id string Unique identifier for this tool call
tool.input string Full tool input as JSON
tool.input_command string Shell command (Bash tool only, empty otherwise)
tool.file_path string Target file path, raw (Write/Edit/Read only)
tool.file_name string Final component of the target path before symlink resolution
tool.real_file_path string Target file path resolved to absolute canonical path (Write/Edit/Read only)
tool.patch_op string Codex apply_patch operation: Add, Update, Delete, or Move (empty otherwise)
agent.permission_mode string Session permission mode: default, acceptEdits, plan, bypassPermissions (Codex also emits dontAsk)
agent.transcript_path string Session transcript file path (empty when the agent reports null)

Read the full file on GitHub · 451 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. 11d ago First seen · 451 lines · 123 tokens per session scan D 1219c9e3f7dc

Subscribe to this mod's changes

prempti-falco-rules is a skill published in the GitHub repository falcosecurity/prempti (204 stars, last pushed 9d ago), licensed Apache-2.0. It adds 123 tokens to every session and 5,639 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens