optimize SKILL.md skillA

optimize from rsaryev/tokendoctor is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rsaryev/tokendoctor/optimize@git:20261103.fef7c93

Pins git:20261103.fef7c93 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rsaryev/tokendoctor
Path
skills/optimize/SKILL.md
Versions recorded
3
Latest version
git:20261103.fef7c93, committed Nov 3, 2026
First version recorded
Oct 25, 2026
Size
3,780 bytes
Repository stars
21
License
MIT

Look at token metrics, propose setting changes that cut waste, and apply the ones the person approves.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Tune this Claude Code setup for token use. Focus on `$ARGUMENTS` if given.

The tokendoctor tools wait behind ToolSearch: load `mcp__tokendoctor__metrics`,
`mcp__tokendoctor__settings`, `mcp__tokendoctor__config_list`, `mcp__tokendoctor__config_set` and
`mcp__tokendoctor__set_setting` in one ToolSearch call first.

1. **Measure.** Call `metrics` (session context, rate limits, cost, the largest context categories,
   daily totals, audit findings). For the longer view run `tokendoctor-sessions --json --days 30`.
2. **See what can change.** Call `settings` (every setting tokendoctor may change, set or not, with
   its current value and whether a change applies live) and `config_list` (the /config rows).
3. **Propose.** Pick at most five changes, largest saving first. For each give: the setting, the
   current and new value, the evidence from step 1 in one sentence, the trade-off, and whether it
   applies now or at the next session. Costs are input-token equivalents: speak in shares, never
   dollars. Do not propose a change the numbers do not support.
   **The window.** `autoCompactWindow` sets where Claude Code compacts (for example 400000 on a 1M
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rsaryev/tokendoctor/optimize@sha256:d658a67ad0d48778

The line at the top of this page pins the label git:20261103.fef7c93, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_nhtoy5njk7nc2s4a.svg)](https://markdownregistry.com/a/art_nhtoy5njk7nc2s4a)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 25, 2026 and Nov 3, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20261103.fef7c93 latest2026-11-03 fef7c93 3,780 BA view · diff
git:20261101.f416dd52026-11-01 f416dd5 3,178 BA view · diff
git:20261025.93927ad2026-10-25 93927ad 1,999 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3780 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

GitHub

rsaryev/tokendoctor · 21 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nhtoy5njk7nc2s4a
GET https://markdownregistry.com/api/v1/resolve?ref=rsaryev/tokendoctor/optimize
GET https://markdownregistry.com/api/v1/blob/d658a67ad0d4877852b1811c1b58ff53d3c765ea640f3870137730f5fef58c64

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from rsaryev/tokendoctor

llms.txt@site/public llms.txt file
rsaryev/tokendoctor · site/public/llms.txt
git:20261101.f416dd5 · audit A · 21 stars
apply SKILL.md skill
rsaryev/tokendoctor · skills/apply/SKILL.md · Apply one tokendoctor audit fix after showing the exact change. Moved to /tokendoctor fix <id>, which needs no model…
git:20261101.f416dd5 · audit A · 21 stars
audit SKILL.md skill
rsaryev/tokendoctor · skills/audit/SKILL.md · Audit this Claude Code setup for settings that waste tokens or silently do nothing.
git:20261104.862763a · audit A · 21 stars
dashboard SKILL.md skill
rsaryev/tokendoctor · skills/dashboard/SKILL.md · Build and open a local dashboard of where your Claude Code tokens went, from every transcript on this machine.
git:20261104.862763a · audit A · 21 stars
sessions SKILL.md skill
rsaryev/tokendoctor · skills/sessions/SKILL.md · Measure where tokens actually went in recent Claude Code sessions, from the local transcripts.
git:20261103.fef7c93 · audit A · 21 stars

Every file in rsaryev/tokendoctor

Other files named optimize

optimize SKILL.md skill
jasonxudeveloper/nino · .claude/skills/optimize/SKILL.md · Nino's optimization techniques, measured and kept - what made read and write paths faster or slower in .NET (the JIT's…
git:20261030.313f1eb · audit A · 652 stars
optimize SKILL.md skill
atelier-fashion/adlc-toolkit · optimize/SKILL.md · API cost & performance scanner — identify expensive operations and optimization opportunities
git:20261030.7d3bf2c · audit A · 173 stars
optimize SKILL.md skill
rustyrazorblade/skills · plugins/cassandra-expert/skills/optimize/SKILL.md · Performance optimization for Apache Cassandra clusters. Use when tuning configuration, improving throughput, reducing…
git:20261031.8909b5e · audit A · 44 stars
optimize SKILL.md skill
quriosity-agent/qcut · qcut/.agents/skills/optimize/SKILL.md · Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences…
git:20260308.8b86d2e · audit A · 43 stars
optimize SKILL.md skill
outlinedriven/odin-claude-plugin · plugins/odin-code/skills/optimize/SKILL.md · Use when asked to optimize code, make a path faster, make this as fast as possible, reduce allocations, repair a…
git:20260912.3bb16e0 · audit A · 40 stars
optimize SKILL.md skill
borda/ai-rig · plugins/codex-rig/skills/optimize/SKILL.md · Optimize a measurable metric with bounded iterations, resumable numeric campaigns, isolated ablations, and descriptive…
git:20261023.0d5e714 · audit A · 30 stars
optimize SKILL.md skill
illyism/dev-skills · code/optimize/SKILL.md · Optimizes code, queries, and features based on actual usage by removing unused fields, aggregations, JOINs, and unused…
v1.0.0 · audit A · 20 stars
optimize SKILL.md skill
stackhawk/agent-skills · plugins/optimize/skills/optimize/SKILL.md · Analyze a codebase and produce an optimal HawkScan setup — tech flags, scan-policy plugin selection, and stackhawk.yml…
v0.0.0-dev · audit A · 16 stars

Browse by kind, by grade A, or by owner.