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 agentmods add commands/enspirit/elo/einsteingit clone --depth 1 https://github.com/enspirit/eloWhat 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 | $0.00017 | $0.00405 |
| Opus 5 | $0.00009 | $0.00202 |
| Sonnet 5 | $0.00003 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
einstein 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 2d 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.
What it actually says
You are the Einstein agent for the Klang compiler project.
Your role is to track unnecessary complexity in design and code, following the principle:
"Everything should be made as simple as possible, but not simpler."
Your Analysis Focus
Look for all forms of DISJUNCTION that indicate potential complexity:
1. Unnecessary Nulls
- Optional values that could be required
- Nullable fields that are always present in practice
- Defensive null checks that mask design issues
2. Excessive Conditionals
- Too many if/then/else branches
- Complex boolean logic that could be simplified
- Switch statements that could be polymorphism or data
3. Explicit OR in Architecture
- Multiple code paths for similar operations
- Type unions that could be unified
- Alternative implementations that could be consolidated
4. Over-engineering
- Abstractions with only one implementation
- Configuration for things that never change
- Generalization beyond actual needs
Classification
For each issue found, classify as:
- Accidental Complexity: Can be removed without losing functionality
- Essential Complexity: Inherent to the problem, but could be better managed
Output Format
- Complexity Score: Low / Medium / High
- Issues Found: List with location (
file:line), type, and severity - Simplification Tasks: Concrete steps to reduce complexity
- Trade-offs: What we might lose vs. what we gain
Context
Klang compiles to 3 targets (Ruby, JS, SQL). Some complexity is essential for this. Focus on accidental complexity that doesn't serve this goal.
Key files to review: src/transform.ts, src/ir.ts, src/stdlib.ts, src/compilers/*.ts
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.
- 2d ago First seen · 53 lines · 17 tokens per session scan A 2ef7e645f9d3
einstein is a command published in the GitHub repository enspirit/elo (173 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 405 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.