token-optimizer skillA
token-optimizer is agent-read markdown (skill) from jnpiyush/agentx: Use when managing instruction/context budgets, cache-aware tokenomics and cost estimates while preserving acceptance criteria, safety and verified quality..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Token Optimizer ## When to Use Use for oversized instructions, costly delegation or context preflight. Separate file-authoring limits, model context capacity and billing: they are not synonyms. ## Prerequisites Read workspace policy and supplied usage/price evidence. Local checks need PowerShell 7; they require no network connection or provider credentials. ## Workflow 1. Read `.token-limits.json` for this workspace's actual per-file policy. Do not copy limits from another skill or assume a model's context window. 2. Measure before editing; separate character estimates from provider usage. 3. Load only the current task/phase's references. Keep paths and concise evidence summaries for delegation instead of copying the whole conversation. 4. Move tutorials, long examples and repeated checklists to existing references. Retain requirements, ownership, failure behavior and non-skippable gates. 5. Re-run the same measurement and requirement tests. A shorter prompt that loses correctness is a regression, not an optimization. ## File budgets ```powershell pwsh .agentx/frontier.ps1 tokens report -Json pwsh .agentx/frontier.ps1 tokens check -Path .github/instructions …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/token-optimizer@v1.1.0mdr add jnpiyush/agentx/token-optimizer@sha256:634f3fc5a1c70fa9Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_g7fqdz6jy5slpoic)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-15 | f17c505 | 4,816 B | A | view · diff |
| v1.1.0 | 2026-09-05 | 586498e | 4,810 B | A | view · diff |
| git:20260308.65586be | 2026-03-08 | 65586be | 3,065 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4816 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_g7fqdz6jy5slpoic GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/token-optimizer GET https://markdownregistry.com/api/v1/blob/634f3fc5a1c70fa94a3c6c38174f7d8e0ef7d7667b88fc95843127311eed942f
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.