Claude Code Cost & Context Pack
Three local-first skills that attack the same problem from different angles: your AI coding sessions cost more than they should.
-
lean-context
Compresses code before the model reads it. AST-aware Python pruning, low-token repo skeletons, git diff summaries, and a token-budget guard. 30-50% fewer tokens on typical read-heavy sessions. -
Token-Guard
Cuts agent input-token cost and stops runaway loops with cache-aware compaction, non-destructive offload, and deterministic loop guards. -
data-pipeline-agent
Turns any API or CSV into a ready-to-query SQLite database in minutes, with zero-config schema inference and type validation. Keeps the data work local.
Why bundle them
Individually, each saves tokens or time. Together they cover the full cost surface of an agent workflow: what the model reads (lean-context), what it re-sends (Token-Guard), and what it has to wrangle before it can help (data-pipeline-agent).
All three are read-only or local, require no hosted account, and install by dropping a SKILL.md folder into your agent. Python 3.8+.
30-day refund.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 3 skills unlock instantly in your library.
What's included
3 skillsCut Claude Code and Cursor token costs by 30-50% with AST-aware context compression, skeleton extraction, and budget guards.
Cut agent input-token cost up to 80% and hard-stop runaway loops with cache-aware compaction, non-destructive offload, and deterministic loop guards.
Turn any API or CSV into a ready-to-query SQLite database in minutes. Zero-config schema inference, type validation, and optional RAG vectors.
See it in action
lean-context
Example session with this skill installed
I need to understand the structure of the core engine in this repo, but the files are huge. Help me map it out without hitting context limits.
- Read your context and instructions
- Compiled the lean-context
I have scanned the repository and generated a compressed map of the core engine. I filtered out all build artifacts and pruned Python files to their signatures to stay within your token budget.
Repository Context Summary
| File Path | Original (Tokens) | Compressed (Tokens) | % Saved |
|---|---|---|---|
engine/core.py | 1,840 | 420 | 77% |
engine/utils/math.py | 950 | 180 | 81% |
engine/handlers/events.py | 1,200 | 310 | 74% |
| Total | 3,990 | 910 | 77% |
# engine/core.py (Compressed AST View)
class ExecutionEngine:
"""Main orchestrator for task execution."""
def __init__(self, config: dict): ...
def register_handler(self, name: str, handler: Callable):
"""Registers a new event handler to the engine."""
...
def run_sync(self, task_id: str) -> Result:
"""Executes a task synchronously and returns the Result object."""
...
class Result:
def __init__(self, status: str, data: Any): ...
.
└── engine/
├── __init__.py
├── core.py
├── handlers/
│ ├── __init__.py
│ └── events.py
└── utils/
├── __init__.py
└── math.py
Next steps
- Would you like me to expand the full body of a specific method in
core.py? - I can perform a
lean-contextdiff if you have pending changes to these files. - Type
show me the structureat any time to refresh this map.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.