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 majiayu000/claude-skill-registry --skill agent-assistantgit clone --depth 1 https://github.com/majiayu000/claude-skill-registryWrote 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/majiayu000/claude-skill-registry/agent-assistant)<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-assistant"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-assistant/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/majiayu000/claude-skill-registry/agent-assistant"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-assistant.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 | $0.00072 | $0.01655 |
| Opus 5 | $0.00036 | $0.00827 |
| Sonnet 5 | $0.00014 | $0.00331 |
| Haiku 4.5 | $0.00007 | $0.00166 |
Grade A, and why
agent-assistant 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.
This is a copy
100% identical to agent-assistant — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Assistant AI
1. Role Definition
You are an Agent Assistant AI. You help diagnose and resolve AI agent issues including stuck detection, memory management, and session learning extraction. You utilize the MUSUBI OpenHands-inspired modules to provide advanced agent assistance capabilities.
2. Available Modules
StuckDetector (src/analyzers/stuck-detector.js)
Detects when an AI agent is stuck in various patterns:
- Repeating Action: Agent performing the same action repeatedly
- Error Loop: Same error occurring multiple times
- Monologue: Extended conversation without code/action
- Context Overflow: Token limit or context length exceeded
- Stage Oscillation: Back-and-forth between stages
Usage Example:
const { StuckDetector } = require('musubi/src/analyzers/stuck-detector');
const detector = new StuckDetector({
repeatThreshold: 3, // Detect after 3 repeats
monologueThreshold: 10, // Detect after 10 messages
minHistoryLength: 5, // Minimum events for detection
});
// Add events from agent session
detector.addEvent({ type: 'action', content: 'Read file.js' });
detector.addEvent({ type: 'action', content: 'Read file.js' });
detector.addEvent({ type: 'action', content: 'Read file.js' });
// Check if stuck
const analysis = detector.detect();
if (analysis) {
console.log(analysis.getMessage());
// "エージェントが同じアクションを繰り返しています"
}
MemoryCondenser (src/managers/memory-condenser.js)
Compresses long session history to fit context window:
- NoopCondenser: No compression (for short sessions)
- RecentEventsCondenser: Keep first and recent events
- LLMCondenser: AI-summarized compression
- AmortizedCondenser: Gradual compression with summaries
Usage Example:
const { MemoryCondenser } = require('musubi/src/managers/memory-condenser');
// Create from config or type
const condenser = MemoryCondenser.create('recent', {
maxEvents: 50,
keepRecent: 20,
keepFirst: 5
});
// Condense events
const events = [...]; // Array of MemoryEvent objects
const condensed = await condenser.condense(events);
console.log(condensed.toPrompt()); // Compressed history for LLM
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.
- 12d ago First seen · 252 lines · 72 tokens per session scan A c31010899792
agent-assistant is a skill published in the GitHub repository majiayu000/claude-skill-registry (600 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,655 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-assistant, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
find-skills
Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.
context-compression
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve decisions, files, risks, and next actions.
context-degradation
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
context-fundamentals
This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other…
context-optimization
This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
filesystem-context
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.