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 Jerry0022/dotclaude --skill auto-frustratedgit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/auto-frustrated)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-frustrated"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-frustrated/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/jerry0022/dotclaude/auto-frustrated"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-frustrated.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 | $0.00056 | $0.02246 |
| Opus 5.5 | $0.00022 | $0.00898 |
| Sonnet 5.5 | $0.00011 | $0.00449 |
| Haiku 4.5 | $0.00006 | $0.00225 |
Grade A, and why
auto-frustrated 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frustrated analysis
Find out why repeated attempts at $ARGUMENTS (or the target the session kept
iterating on) miss the goal, and propose a plan with reasons. This skill
changes nothing in the app. Specs: docs/superpowers/specs/2026-10-25-frustrated-mode-*.md;
user-facing summary: {PLUGIN_ROOT}/deep-knowledge/frustrated-mode.md.
Entry points: the slash command, or the alpha detector hook
(prompt.frustrated.detect) after the user said yes to its offer
(Read {PLUGIN_ROOT}/skills/auto-frustrated/SKILL.md), or the do-run Q4
option "Erst analysieren". All three are the same explicit start.
Step 0 — Gate
node "{PLUGIN_ROOT}/scripts/feature-flag.js" check frustrated-mode
Exit 126 → say in one line that this analysis is not available on this channel, and stop. Nothing else of this skill runs.
Step 1 — Intake and arm (no questions)
-
Target: the args, else the area the conversation iterated on most, else the densest recent
git logchurn. Name the derived target as an assumption in the report. -
Write the loop hypothesis (one paragraph, sealed): "what I believed the problem was during the failed attempts". Only the synthesizer sees it.
-
Arm the read-only guard and build the brief:
node "{PLUGIN_ROOT}/scripts/frustrated-guard.js" arm --target "<target>" node "{PLUGIN_ROOT}/scripts/frustrated-brief.js" --out "<scratchpad or temp>/frustrated-brief.json"From now on the guard
pre.frustrated.readonlydenies every change to the app's source and config, for the main thread and every analyst. Allowed: reading, git read commands, running tests / lint / typecheck (never--fix), writing into the temp dir / scratchpad,.claude/state, snapshots, coverage and caches, concept pages, and the plugin scripts named here. A deny is information, not an obstacle: record the change as a plan step instead. Under ultracode, too: this analysis runs its fixed roles as Agent spawns, never a Workflow.
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.
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 · 173 lines · 56 tokens per session scan A 28881574e2f1
auto-frustrated is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 56 tokens to every session and 2,246 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-26.
auto-frustrated compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| auto-frustratedJerry0022/dotclaude | Skill | 6 | 11d ago | MIT | A | 56 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |