risks

risks is a skill for Claude Code, Codex from danielrmay/claudity. It costs 14 tokens per session (2,791 once invoked), scanned A, original, MIT.

A workflow for brainstorming possible failure modes with specialist analysis agents and human input. A failure mode is a specific way a system, feature, or process could go wrong.

In plain words
What is it for?
Use it to explore technical, human, social, security, adversarial, operational, and cascading failures during system planning.
Why use it?
It helps teams build a shared list of risks before grouping, prioritizing, and analyzing them, while requiring a clear problem statement first.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claudity plugin — 6 skills, 6 agents, 1 MCP server shipped together

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 skills/danielrmay/claudity/risks
Any agent
npx skills add danielrmay/claudity --skill risks
Clone the repo
git clone --depth 1 https://github.com/danielrmay/claudity

Made for: Claude Code, Codex.

Or install claudity, the plugin that ships this one along with the rest of its 6 skills, 6 agents, 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 risks

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrmay/claudity/risks.svg)](https://agentmods.dev/skills/danielrmay/claudity/risks)
Your own site
<a href="https://agentmods.dev/skills/danielrmay/claudity/risks"><img src="https://agentmods.dev/badge/skills/danielrmay/claudity/risks.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,791 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 $0.00014 $0.02791
Opus 5 $0.00007 $0.01396
Sonnet 5 $0.00003 $0.00558
Haiku 4.5 $0.00001 $0.00279

Measured 4d ago against content hash 9a17c8ffe3a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

risks 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 4d 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.

skills/risks/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This pipeline requires a protocol directory with at least a real problem statement — if that's missing, say so and route through Claudity's start skill (problem clarification) first. If the brainstorming mailbox already has pending items, offer failure-analysis instead (the status script's Process Availability section shows which phase is recommended). If the user named a focus area when invoking this skill, honor it; follow the guide below from the beginning.

Failure Brainstorming

This process generates raw failure modes through direct analysis, specialist thinker subagents, and human contributions. Raw failures accumulate in a pool until they're ready for analysis and grouping.

Overview

The goal of failure brainstorming is breadth: come up with as many things as possible that could go wrong. This is the creative, divergent phase — don't filter, don't group, don't worry about duplicates. That's what failure analysis is for.

Brainstorming can happen over time. Multiple runs can contribute, humans can add their own insights, and the pool grows until someone decides it's ready for analysis. This process can be run multiple times, each run adding to the same pool.

Tools Available

You have MCP tools (from the clarity-agent server) for recording your findings. Always use these — do not write files directly. The tools own placement, naming, and format; hand-written files end up in the wrong location and are invisible to the pipeline.

record_failure

Record a failure mode to the brainstorming mailbox: call the record_failure tool with title ("Short title of what goes wrong") and description ("1-3 sentences: what fails, how, who is harmed").

Read the full file on GitHub · 218 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. 4d ago First seen · 218 lines · 14 tokens per session scan A 9a17c8ffe3a2

Subscribe to this mod's changes

risks is a skill published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,791 once invoked, about $0.0001 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.