token-coach SKILL.md skillA

token-coach from alexgreensh/token-optimizer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add alexgreensh/token-optimizer/token-coach@git:20261019.5e18db5

Pins git:20261019.5e18db5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
alexgreensh/token-optimizer
Path
skills/token-coach/SKILL.md
Versions recorded
10
Latest version
git:20261019.5e18db5, committed Oct 19, 2026
First version recorded
Jul 31, 2026
Size
10,578 bytes
Repository stars
2,651
License
a license file GitHub does not identify

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.

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

# Token Coach

A coaching conversation about where the user's tokens go and what to change, grounded in numbers measured on their machine. The deliverable is a short, prioritised action plan the user agrees with. For a full audit that edits their setup, hand over to `token-optimizer`.

Token Optimizer's own skills (`token-optimizer`, `token-coach`, `token-dashboard`, `fleet-auditor`, `resume-checkpoint`) are the measurement layer, so leave them out of every unused-skill, archive or consolidation suggestion, however rarely they run.

## 1. Collect the data

Run exactly this first. It finds the newest installed copy, so a stale plugin cache never answers:

```bash
RUNTIME="${TOKEN_OPTIMIZER_RUNTIME:-}"
if [ -z "$RUNTIME" ]; then
  if [ -n "$CLAUDE_PLUGIN_ROOT" ] || [ -n "$CLAUDE_PLUGIN_DATA" ]; then
    RUNTIME="claude"
  elif [ -n "$OPENCODE" ] || [ -n "$OPENCODE_BIN" ] || [ -n "$OPENCODE_CONFIG_DIR" ] || [ -n "$OPENCODE_CONFIG" ]; then
    RUNTIME="opencode"
  elif [ -n "$CODEX_HOME" ]; then
    RUNTIME="codex"
  # Explicit config-dir env of another harness: same tier as Python's
  # detect_runtime() (above CLAUDECODE, which every Claude Code child inherits).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add alexgreensh/token-optimizer/token-coach@sha256:2b503df4e0f94797

The line at the top of this page pins the label git:20261019.5e18db5, 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_s7l2tccu2lzze4jx.svg)](https://markdownregistry.com/a/art_s7l2tccu2lzze4jx)

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

Versions

The registry has recorded 10 versions of this file, between Jul 31, 2026 and Oct 19, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20261019.5e18db5 latest2026-10-19 5e18db5 10,578 BA view · diff
git:20261010.adb019a2026-10-10 adb019a 10,026 BA view · diff
git:20261010.d86aacb2026-10-10 d86aacb 9,182 BA view · diff
git:20261010.f3ea29b2026-10-10 f3ea29b 9,070 BA view · diff
git:20261010.c9d9a6f2026-10-10 c9d9a6f 9,083 BA view · diff
git:20260905.29c95812026-09-05 29c9581 12,857 BA view · diff
git:20260808.ff5dedb2026-08-08 ff5dedb 12,894 BA view · diff
git:20260731.82b2efc2026-07-31 82b2efc 12,767 BA view · diff
git:20260731.1652f372026-07-31 1652f37 13,033 BA view · diff
git:20260731.b8cc61d2026-07-31 b8cc61d 12,417 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 (10578 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

alexgreensh/token-optimizer · 2,651 stars · license a license file GitHub does not identify · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_s7l2tccu2lzze4jx
GET https://markdownregistry.com/api/v1/resolve?ref=alexgreensh/token-optimizer/token-coach
GET https://markdownregistry.com/api/v1/blob/2b503df4e0f9479777a8602985c72a53f1efb7cdcd6105d6979e8a1ab3af0f37

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 alexgreensh/token-optimizer

fleet-auditor SKILL.md skill
alexgreensh/token-optimizer · cowork/token-optimizer/skills/fleet-auditor/SKILL.md · Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings. Use when…
git:20261019.c063470 · audit A · 2,651 stars
resume-checkpoint SKILL.md skill
alexgreensh/token-optimizer · cowork/token-optimizer/skills/resume-checkpoint/SKILL.md · Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Use when the user is continuing prior work…
git:20261010.9f146e0 · audit A · 2,651 stars
token-coach SKILL.md skill
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-coach/SKILL.md · Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing…
git:20261019.5e18db5 · audit A · 2,651 stars
token-dashboard SKILL.md skill
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-dashboard/SKILL.md · Answers what a past session cost ("the Garden session yesterday", a session id) with a priced number, and opens the…
git:20261020.7299960 · audit A · 2,651 stars
token-optimizer SKILL.md skill
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
git:20261010.f756a67 · audit A · 2,651 stars
token-optimizer-output SKILL.md skill
alexgreensh/token-optimizer · devin/SKILL.md · Explicitly filter private captured command output using Token Optimizer. Works on its own or as the manual fallback to…
git:20261014.2d28beb · audit A · 2,651 stars
token-optimizer SKILL.md skill
alexgreensh/token-optimizer · openclaw/skills/token-optimizer/SKILL.md · Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities
git:20260316.25fde7b · audit A · 2,651 stars
fleet-auditor SKILL.md skill
alexgreensh/token-optimizer · plugins/token-optimizer/skills/fleet-auditor/SKILL.md · Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings. Use when…
git:20261019.c063470 · audit A · 2,651 stars
resume-checkpoint SKILL.md skill
alexgreensh/token-optimizer · plugins/token-optimizer/skills/resume-checkpoint/SKILL.md · Pulls a prior session's checkpoint as fenced, scrubbed recovery context. Use when the user is continuing prior work…
git:20261010.d43ebe5 · audit A · 2,651 stars
token-coach SKILL.md skill
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-coach/SKILL.md · Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing…
git:20261019.5e18db5 · audit A · 2,651 stars
token-dashboard SKILL.md skill
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-dashboard/SKILL.md · Answers what a past session cost ("the Garden session yesterday", a session id) with a priced number, and opens the…
git:20261020.7299960 · audit A · 2,651 stars
token-optimizer SKILL.md skill
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-optimizer/SKILL.md · Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the…
git:20261010.f756a67 · audit A · 2,651 stars

Every file in alexgreensh/token-optimizer

Other files named token-coach

token-coach SKILL.md skill
alexgreensh/token-optimizer · plugins/token-optimizer/skills/token-coach/SKILL.md · Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing…
git:20261019.5e18db5 · audit A · 2,651 stars
token-coach SKILL.md skill
alexgreensh/token-optimizer · cowork/token-optimizer/skills/token-coach/SKILL.md · Coaches a token-efficient Claude Code or Codex setup from the user's own usage data. Use when planning a build, fixing…
git:20261019.5e18db5 · audit A · 2,651 stars

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