token-budget-embeddings — Relevance Workflow
Wire a caller-supplied embedding function into semantic context selection, validate vector semantics, and plan cache and privacy boundaries.
$1
Works with the AI Agents you already use
token-budget-embeddings — Relevance Workflow
Example session with this skill installed
Use token-budget-embeddings-workflow to integrate this package and run its local fixture, keeping unverified provider behavior explicit.
- Read your context and instructions
- Compiled the token-budget-embeddings
Local synthetic fixture result from the published package: {"fixedVectorCosine":1,"note":"no embedding API used"}
Interpretation: Bring your own embedding function and any provider cost/credentials. Similarity is not factual correctness. Caches are unbounded and keyed partly by message id; stale ids and rejected promises need lifecycle handling. Source regression coverage is not a universal published-version guarantee.
Next validation: Use fixed local vectors: identical -> cosine 1, orthogonal -> 0. Check dimension mismatch, empty extractable text and zero vectors. Test concurrent distinct queries and repeated ids before sharing scorer instances. Evaluate retained task requirements, latency and cache growth on authorized samples.
Evidence scope: source version 0.1.5 suite passed 4 tests; published 0.1.4 was separately exercised with the included fixture. These are distinct baselines. Live provider/SDK/backend behavior was not tested, and no network service credential was needed for the example.
Connects securely to your tools. The creator never sees your data.
About this skill
Wire a caller-supplied embedding function into semantic context selection, validate vector semantics, and plan cache and privacy boundaries.
Original application-integration playbook covering setup, exact supported exports, migration, failure handling and local verification. This is a curated workflow package, not a new MCP server or automatic host-context control.
Verified source 0.1.5: 4 tests passed. The included local fixture also passed against published npm 0.1.4 tarball code using peer/dependency resolution from the reviewed monorepo, not an independent clean-consumer install. No live provider, embedding service or telemetry backend was contacted.
Limitations: Bring your own embedding function and any provider cost/credentials. Similarity is not factual correctness. Caches are unbounded and keyed partly by message id; stale ids and rejected promises need lifecycle handling. Source regression coverage is not a universal published-version guarantee.
The separate npm runtime remains free/open-source under MIT at https://github.com/shivam039/token-budget/tree/main/packages/token-budget-embeddings. MIT notice is preserved; this $1 purchase is for original curated workflow instructions, not exclusive runtime access. Provider/exporter services, if selected, are separately authorized and may charge. No runtime dependencies are bundled and no blanket dependency-security clearance is promised.
Bring your own embedding function and any provider cost/credentials. Similarity is not factual correctness. Caches are unbounded and keyed partly by message id; stale ids and rejected promises need lifecycle handling. Source regression coverage is not a universal published-version guarantee.
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 this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
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.
Trust & safety
Security scan
Security scan passed 19 days ago
Requires
Permissions
Allowed Hosts
Project-scoped setup, edits and synthetic local fixtures. No provider/exporter endpoint is configured by this skill. Any live data transmission or optional service use requires the authorized destination and scope; never include credentials in evidence.