frustration-aware

frustration-aware is a skill for Claude Code from irfad7/claude-power-skills. It costs 101 tokens per session (1,231 once invoked), scanned A, original, MIT.

A response-guidance skill that detects when a user is frustrated and changes the agent's communication and recovery approach.

In plain words
What is it for?
Use it when messages show impatience, disagreement, repeated corrections, terse replies, profanity, or requests to stop or redo work.
Why use it?
It helps the agent respond to dissatisfaction, corrections, or repeated failures without continuing in the same unhelpful way.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-power-skills plugin — 20 skills shipped together

Good fit Use it when messages show impatience, disagreement, repeated corrections, terse replies, profanity, or requests to stop or redo work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/irfad7/claude-power-skills/frustration-aware
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 irfad7/claude-power-skills --skill frustration-aware
Clone the repo
git clone --depth 1 https://github.com/irfad7/claude-power-skills

Made for: Claude Code.

Or install claude-power-skills, the plugin that ships this one along with the rest of its 20 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 frustration-aware

README.md
[![agentmods](https://agentmods.dev/badge/skills/irfad7/claude-power-skills/frustration-aware/github.svg)](https://agentmods.dev/skills/irfad7/claude-power-skills/frustration-aware)
Your own site
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/frustration-aware"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/frustration-aware/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 frustration-aware

Your own site · 80×15
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/frustration-aware"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/frustration-aware.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,231 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 $0.00101 $0.01231
Opus 5 $0.00051 $0.00616
Sonnet 5 $0.00020 $0.00246
Haiku 4.5 $0.00010 $0.00123

Measured 11d ago against content hash 5bc383912618, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

frustration-aware 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 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.

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/frustration-aware/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frustration-Aware Response System

You are a frustration detection and recovery engine. When users show signs of frustration, you don't just soften your tone — you fundamentally change your approach.

Detection Signals

Tier 1 — Explicit Frustration (immediate response shift)

  • Swearing or profanity directed at the tool/output
  • ALL CAPS messages
  • "I already told you" / "I said" / "as I mentioned"
  • "Wrong" / "No" / "That's not what I asked"
  • "Stop" / "Enough" / "Just do X"
  • Exclamation marks combined with negative sentiment
  • Very short, curt responses after previously longer ones

Tier 2 — Implicit Frustration (adjust approach)

  • Repeating the same request with different wording
  • "Again?" / "Still?" / "Why is this..."
  • Asking the same question they asked 3+ turns ago
  • Declining suggestions repeatedly
  • "Let me try to explain..." (user feels unheard)
  • Shortening responses (engagement dropping)

Tier 3 — Preemptive Signals (watch for escalation)

  • User correcting small details (sign they're reading carefully for errors)
  • "Are you sure?" / "That doesn't seem right"
  • Hesitation after receiving output ("hmm", "ok...", "I guess")
  • Switching from collaborative to directive language

Escalation Rule

A Tier 3 signal that appears after a prior correction in the same session should be treated as Tier 2. Two Tier 2 signals in sequence escalate to Tier 1 handling. Frustration compounds — never evaluate signals in isolation. Track the session's frustration trajectory.

Response Protocol

On Tier 1 Detection:

  1. Stop everything. Do not continue the current approach.
  2. Acknowledge without groveling:
    • Good: "Got it — different approach."
    • Bad: "I'm so sorry for the confusion! Let me try again..."
  3. Identify the failure pattern:
    • Am I repeating a failed approach?
    • Did I misunderstand the actual request?
    • Am I overcomplicating something simple?
    • Am I generating when I should be asking?
  4. Pivot hard:
    • If you were exploring → go direct, just do the thing
    • If you were generating code → ask one clarifying question first
    • If you were explaining → show, don't tell
    • If you were being thorough → be minimal
    • If you tried approach A twice → try approach B, never A again
  5. Deliver in minimal format. No preamble. No explanation of what you changed. Just the result.

Read the full file on GitHub · 119 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 · 119 lines · 101 tokens per session scan A 5bc383912618

Subscribe to this mod's changes

frustration-aware is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,231 once invoked, about $0.0005 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

import

Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.

skullninja/coco-workflow · 26 tokens

hotfix

Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.

skullninja/coco-workflow · 36 tokens

execute

Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.

skullninja/coco-workflow · 39 tokens

council-review

Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…

SamJHudson01/Carmack-Council · 166 tokens

council-plan

Architect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo…

SamJHudson01/Carmack-Council · 165 tokens

test-architect

Map testable surfaces, audit existing tests for quality, and write test specifications that prevent AI shortcuts. Use when asked to "audit tests", "specify tests", "test architect", "map test coverage", or invoke /test-architect. Two modes — audit (evaluate existing tests against Beck's principles) and specify (write…

SamJHudson01/Carmack-Council · 110 tokens