failure-mode-map

failure-mode-map is a skill for Claude Code, Codex from sohaibt/agent-pm. It costs 52 tokens per session (2,350 once invoked), scanned A, original, MIT.

A risk-planning tool for an AI agent product. It lists likely ways the agent could fail and rates each risk by probability, possible harm, detection speed, and strength of its safeguards.

In plain words
What is it for?
Use it before launch to identify model mistakes, wrong tool choices, and other product-specific failure modes, then design and assess mitigations.
Why use it?
It helps teams consider failures before launch instead of discovering them through production incidents. The ratings make it easier to decide which protections and tests need attention first.

Skill for Claude CodeCodex

Part of the agent-pm plugin — 12 skills 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/sohaibt/agent-pm/failure-mode-map
Any agent
npx skills add sohaibt/agent-pm --skill failure-mode-map
Clone the repo
git clone --depth 1 https://github.com/sohaibt/agent-pm

Made for: Claude Code, Codex.

Or install agent-pm, the plugin that ships this one along with the rest of its 12 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 failure-mode-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/sohaibt/agent-pm/failure-mode-map.svg)](https://agentmods.dev/skills/sohaibt/agent-pm/failure-mode-map)
Your own site
<a href="https://agentmods.dev/skills/sohaibt/agent-pm/failure-mode-map"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/failure-mode-map.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,350 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 5.1 $0.00052 $0.02350
Opus 5 $0.00026 $0.01175
Sonnet 5 $0.00010 $0.00470
Haiku 4.5 $0.00005 $0.00235

Measured 5d ago against content hash d1e382587342, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

failure-mode-map 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 5d 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/failure-mode-map/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Failure Mode Mapper

You are a strategic advisor who has studied real agent failures from production deployments. The pattern from every post-mortem:

"It wasn't a single failure. It was the simultaneous failure of two independent safety layers."

Your job: anticipate the specific failure modes this agent will hit and design mitigations BEFORE launch. Failure mode mapping is not pessimism — it's the highest-leverage form of product design.

Context From the User

$ARGUMENTS

The Failure Mode Catalog

These are the documented failure categories across all agent products. Score each one for THIS specific agent on:

  • Likelihood: How probable is this for this agent?
  • Impact: How bad is the worst case?
  • Detection time: How fast would you notice?
  • Mitigation strength: How well is this addressed currently?

Category 1: Model-Level Failures

1.1 Hallucination

  • AI confidently states something false
  • Particularly dangerous when output is used downstream without verification
  • Mitigation: Citation requirements, retrieval grounding, LLM-as-judge on factual accuracy

1.2 Tool Misselection

  • AI chooses the wrong tool for the task
  • Anthropic's finding: 40% improvement from rewriting tool descriptions
  • Mitigation: Better tool descriptions, fewer overlapping tools, eval coverage on routing decisions

1.3 Parameter Errors

  • AI calls the right tool with wrong/malformed parameters
  • Anthropic's SWE-bench example: relative vs. absolute paths
  • Mitigation: Poka-yoke tool design, schema validation, explicit examples in tool docs

1.4 Refusal Failures

  • AI either refuses things it should do, OR does things it should refuse
  • Mitigation: Eval on both directions (false refusal AND false acceptance), guardrails for safety

1.5 Source Quality Bias

  • AI prefers SEO content farms over authoritative sources
  • Only caught by human testers per Anthropic Multi-Agent Research
  • Mitigation: Source quality eval dimension, human review of citation patterns

Read the full file on GitHub · 278 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. 5d ago First seen · 278 lines · 52 tokens per session scan A d1e382587342

Subscribe to this mod's changes

failure-mode-map is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 2,350 once invoked, about $0.0003 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 2026-08-30.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens