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.
npx skills add irfad7/claude-power-skills --skill frustration-awaregit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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.
[](https://agentmods.dev/skills/irfad7/claude-power-skills/frustration-aware)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Stop everything. Do not continue the current approach.
- Acknowledge without groveling:
- Good: "Got it — different approach."
- Bad: "I'm so sorry for the confusion! Let me try again..."
- 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?
- 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
- Deliver in minimal format. No preamble. No explanation of what you changed. Just the result.
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.
- 11d ago First seen · 119 lines · 101 tokens per session scan A 5bc383912618
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.
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.
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.
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.
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)…
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…
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…