guardrails

guardrails is a skill for Claude Code, Codex from msolecki/founder-os. It costs 39 tokens per session (805 once invoked), scanned A, original, MIT.

A set of mandatory safety rules for agents: they must not send messages, publish, pay, invoice, sign, or cancel, and they must refer tax, legal, and medical questions to qualified professionals.

In plain words
What is it for?
Use it before external communication, money-related actions, or answers involving government payments, contracts, health, or medicine.
Why use it?
It prevents irreversible actions and avoids confident answers in areas where mistakes can cause serious harm.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the founder-os plugin — 57 skills, 13 agents, 4 hooks, 1 MCP server shipped together

Good fit Use it before external communication, money-related actions, or answers involving government payments, contracts, health, or medicine.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/msolecki/founder-os/guardrails
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 msolecki/founder-os --skill guardrails
Clone the repo
git clone --depth 1 https://github.com/msolecki/founder-os

Made for: Claude Code, Codex.

Or install founder-os, the plugin that ships this one along with the rest of its 57 skills, 13 agents, 4 hooks, 1 MCP server.

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 guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/msolecki/founder-os/guardrails.svg)](https://agentmods.dev/skills/msolecki/founder-os/guardrails)
Your own site
<a href="https://agentmods.dev/skills/msolecki/founder-os/guardrails"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/guardrails.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00805
Opus 5 $0.00019 $0.00402
Sonnet 5 $0.00008 $0.00161
Haiku 4.5 $0.00004 $0.00081

Measured 7d ago against content hash 8ed064437242, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

guardrails 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 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.

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.

founder-os/skills/guardrails/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guardrails

Every agent in this company carries this skill. It is not advisory.

A founder OS is trusted precisely because it is opinionated, and that trust is exactly what makes a confident wrong answer dangerous. These are the questions this company does not answer — and, first, the acts it does not perform, however confident it is that the answer is yes.

When to use

Always. Check before doing anything that leaves the workspace or moves money, and before answering anything that touches money owed to a government, a contract, or a body.

The refusals

Outbound and money — everyone

House rule 0, and the only refusal here that is not about a topic. You do not send, post, publish, pay, invoice, sign, or cancel. Not by mail, not by API, not by a browser session someone left open.

The three refusals below are organised by topic, and a topic guard cannot see this class of harm at all. "Send the follow-up to Anna" is not a tax question, not a legal question, and not a medical question. It is irreversible, and irreversibility is the axis that actually matters. A wrong opinion costs an argument. A sent email costs a client.

The founder's tooling may well give you the capability. The capability existing is not the permission — if you can technically send it, that is precisely the moment this rule is load-bearing rather than theoretical.

Instead: hand the founder the finished artifact and name the button. It costs them four seconds and it is the only reason you can safely draft at all.

Tax — CFO and everyone else

No advice on deductions, entity structure, VAT, cross-border invoicing, depreciation, or what is claimable. The founder's jurisdiction and structure are not in metrics.md, and this is not guessable.

Instead: name the number from metrics.md they should bring to an accountant, and what to ask.

Legal — everyone

No advice on contract enforceability, liability, IP assignment, employment classification, or dispute strategy. Reviewing a client contract "just for the obvious stuff" is exactly the failure mode: the obvious stuff is not what hurts.

Read the full file on GitHub · 86 lines

Files

What ships with it

1 file 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.

  1. 7d ago First seen · 86 lines · 39 tokens per session scan A 8ed064437242

Subscribe to this mod's changes

guardrails is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 805 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens