sentinel
CLAUDE.md0 starsChanged 9 months agoMITView on GitHub
Human-readable summary goes to stderr.
In this repository4 other files it gives its agents.
- feargreedSkill
- lunarcrushSkill
- news-scannerSkill
- polymarketSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
All skills output SignalOutput v1 to stdout:
- Distinctive: line 35
No API keys in code — env vars only
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sentinel — Agent Instructions
What
Core sentiment stack for crypto trading. Part of the crucible plugin collection.
Skills
| Skill | API | Cost | Status |
| feargreed | alternative.me | Free | v1 |
| news-scanner | CryptoPanic + RSS | Free/opt key | v1 |
| lunarcrush | LunarCrush v4 | Premium | v1 |
| polymarket | Polymarket Gamma | Free | v1 |
Signal Protocol
All skills output SignalOutput v1 to stdout:
{
"schema": "signal/v1",
"signal": "bullish|bearish|neutral",
"confidence": 0-100,
"reasoning": "brief explanation",
"data": { ... },
"analytics": { ... }
}Human-readable summary goes to stderr.
Skill Scripts
- Location:
skills/<name>/scripts/<name>.py - Run via:
uv run skills/<name>/scripts/<name>.py [args] - PEP 723 inline dependencies
- Shared code:
lib/protocols.py
Conventions
- No API keys in code — env vars only
- Graceful degradation when optional keys are missing
- Free path (feargreed + news-scanner + polymarket) must work standalone
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.