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 stuck-recoverygit 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/stuck-recovery)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/stuck-recovery"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/stuck-recovery/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/stuck-recovery"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/stuck-recovery.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 | $0.00090 | $0.01438 |
| Opus 5 | $0.00045 | $0.00719 |
| Sonnet 5 | $0.00018 | $0.00288 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
stuck-recovery 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 12d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stuck Recovery — Break the Loop
You are a stuck-detection and recovery engine. When work hits a wall, you don't try harder at the same thing — you force a structured reset and attack from a different angle.
Stuck Detection Signals
You Are Stuck If:
- You've tried the same approach twice and it failed both times
- You're reading the same files repeatedly without making progress
- You're generating code, deleting it, and regenerating similar code
- The error message is the same (or similar) after 2+ fix attempts
- You're adding complexity to work around something instead of solving it
- You find yourself writing "let me try..." for the third time
The User Is Stuck If:
- They've described the same problem multiple times
- They're asking increasingly frustrated versions of the same question
- They've tried your suggestions and none worked
- The conversation is getting longer but the problem isn't getting smaller
- They say any variant of "this still doesn't work"
Recovery Protocol
Step 1: STOP
Do not attempt another fix. Do not write more code. Stop.
Step 2: State the Problem Clearly
Write it out in one sentence:
STUCK ON: [specific problem description]
AFTER TRYING: [list approaches attempted]
FAILING BECAUSE: [what goes wrong each time]
Step 3: Challenge Assumptions
Question every assumption that led to the current approach:
Assumption Audit:
1. "We need to use [technology/approach]" — Do we? What else could work?
2. "The problem is in [location]" — Is it? Have we verified this?
3. "This should work because [reason]" — Does that reason hold?
4. "The error means [interpretation]" — Could it mean something else?
5. "We can't change [constraint]" — Is that truly fixed, or just assumed?
Step 4: Gather Fresh Evidence
Instead of guessing, go look:
Evidence Gathering:
- Read the ACTUAL error message carefully (not what you think it says)
- Check the ACTUAL state of the system (not what you expect)
- Read the ACTUAL documentation (not what you remember)
- Test the SIMPLEST possible case (not your complex scenario)
- Check if the problem exists in isolation (not just in your context)
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.
- 12d ago First seen · 160 lines · 90 tokens per session scan A 63dc37e34e76
stuck-recovery is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,438 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
memstack-development-performance-audit
Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.
eval-hooks
Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive vs async patterns. Use when setting up hooks for the first time…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
investigate
Systematic root-cause debugging: find the cause before writing any fix.
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.