AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Context Budget

skill-zedarvates-botte-secrete-context-budget · by zedarvates

Pick the optimal set of skills/docs to load for a task under a token budget — an exact 0/1 knapsack (maximize relevance while summed token cost stays under budget), not an LLM "decide what's relevant" call. Deterministic, stdlib, 0 cloud tokens. Cuts the always-on context cost (loading the whole skill catalog every turn). Use when you want to load only the most relevant context within a budget, o…

↗ Website ↗ Repository
— No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-zedarvates-botte-secrete-context-budget

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Context Budget? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

context_budget — optimal context under a token budget

The OR-Tools principle applied to the agent's always-on cost: choosing which skills/docs to load is a 0/1 knapsack — maximize total relevance while the summed token cost stays under a budget. That's an exact deterministic solver (stdlib DP), so it costs 0 tokens and beats the greedy "take the top matches until full" heuristic.

python -m skills.context_budget.cli "optimize slow postgres queries and add tests" --budget 3000
python -m skills.context_budget.cli "" --budget 4000 --json

How it selects

  1. Rank — score every skill against the task lexically ([[skill_finder]],

0 tokens), with each skill's token cost.

  1. Knapsack — knapsack(items, budget) finds the subset that maximizes

summed relevance subject to Σ tokens ≤ budget (exact DP, token costs scaled to bound the table). Optimal, not greedy.

  1. Frame — report the chosen set, tokens used, relevance captured, and the

saving vs loading the whole catalog.

On this repo a typical task loads ~4 skills (~2k tok) instead of the whole ~36-skill catalog (~15k tok) — an ~85% cut in always-on context for that task.

The knapsack(items, budget) engine is generic (takes Item(name, kind, tokens, relevance)), so docs ([[docssteward]]) or any context source plug in the same way. Exposed via [[llmmcp]] as context_budget. Related: [[skill_finder]] (ranking), [[metrics]] (measures the always-on cost this cuts).

First of the deterministic "solver" hybridizations (OR-Tools-inspired): exact combinatorial optimization replacing LLM reasoning for structured decisions.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML