Updated 4d ago
by alexgreensh
token-optimizer
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
2.9k GitHub stars (2,878)
+381 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | +4 |
| Sep 28 | +17 |
| Sep 29 | +41 |
| Sep 30 | +14 |
| Oct 1 | +1 |
| Oct 2 | +9 |
| Oct 3 | +9 |
| Oct 4 | +3 |
| Oct 5 | +7 |
| Oct 6 | +9 |
| Oct 7 | +8 |
| Oct 8 | +8 |
| Oct 9 | +8 |
| Oct 10 | +5 |
| Oct 11 | +7 |
| Oct 12 | +4 |
| Oct 13 | +6 |
| Oct 14 | +12 |
| Oct 15 | +9 |
| Oct 16 | +7 |
| Oct 17 | +13 |
| Oct 18 | +4 |
| Oct 19 | +8 |
| Oct 20 | +5 |
| Oct 21 | +12 |
| Oct 22 | +7 |
| Oct 23 | +24 |
| Oct 24 | +25 |
| Oct 25 | +20 |
| Oct 26 | +15 |
| Oct 27 | +27 |
| Oct 28 | +26 |
| Oct 29 | +15 |
| Oct 30 | +28 |
| Oct 31 | +14 |
| Nov 1 | +5 |
| Nov 2 | +12 |
| Nov 3 | +21 |
| Nov 4 | +9 |
| Nov 5 | +17 |
- 6 skills (6 skills found in its SKILL.md files)
- 225 forks (225 forks)
- 4d ago last update (Last updated 4d ago)
Install
Skills CLI
npx skills add alexgreensh/token-optimizer
Asks which skills and agents to install. Just one: npx skills add alexgreensh/token-optimizer --skill token-optimizer-output — add -g for every project.
Claude Code
git clone https://github.com/alexgreensh/token-optimizercp -r "token-optimizer/devin" ~/.claude/skills/
Copies the token-optimizer-output skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add alexgreensh/token-optimizer
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
token-optimizer-output
Explicitly filter private captured command output using Token Optimizer. Works on its own or as the manual fallback to automatic mode. No provider accounting.
devin/SKILL.md on GitHub (opens in a new tab) -
fleet-auditor
Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings. Use when running several agent systems or suspecting idle heartbeats burn tokens.
skills/fleet-auditor/ on GitHub (opens in a new tab)SKILL.md -
resume-checkpoint
Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Use when the user is continuing prior work; skip it on a fresh, unrelated task.
skills/resume-checkpoint/ on GitHub (opens in a new tab)SKILL.md -
token-coach
Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing a slow or costly setup, or deciding which workflow steps need a model.
skills/token-coach/ on GitHub (opens in a new tab)SKILL.md -
token-dashboard
Answers what a past session cost ("the Garden session yesterday", a session id) with a priced number, and opens the Token Optimizer dashboard when asked to see it.
skills/token-dashboard/ on GitHub (opens in a new tab)SKILL.md -
token-optimizer
Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the saving. Use when context feels tight, sessions degrade, or costs climb.
skills/token-optimizer/ on GitHub (opens in a new tab)SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.