meter SKILL.md skillA

meter from chteau/tokenforge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add chteau/tokenforge/meter@git:20261008.cd99252

Pins git:20261008.cd99252 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
chteau/tokenforge
Path
skills/meter/SKILL.md
Versions recorded
2
Latest version
git:20261008.cd99252, committed Oct 8, 2026
First version recorded
Oct 7, 2026
Size
959 bytes
Repository stars
6
License
MIT

Show token usage of recent Claude Code sessions and tforge worker runs (calls, average and peak context, cache, output). Use when asked how many tokens a session or build used, or to compare two approaches.

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

# meter

Run `tforge meter $ARGUMENTS`. The plugin puts it on PATH. If it is missing, use `node "${CLAUDE_SKILL_DIR}/../../bin/tforge" meter $ARGUMENTS`.

Report the table. Then explain the main cost driver in 1–2 lines, using these rules:
- Cost ≈ calls × average context. High `avg ctx` means the session should have been split with a handoff, or the work given to `tforge`.
- High `cache-w` compared with `cache-r` means the cache was broken often. Typical causes: switching models, editing CLAUDE.md mid-session, or long pauses.
- `input-equiv` weighs each column by its relative price, so compare runs on that column.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add chteau/tokenforge/meter@sha256:bbfdc7025ba1780f

The line at the top of this page pins the label git:20261008.cd99252, 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_nbt6tc7vmdczwcxc.svg)](https://markdownregistry.com/a/art_nbt6tc7vmdczwcxc)

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

Versions

The registry has recorded 2 versions of this file, between Oct 7, 2026 and Oct 8, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261008.cd99252 latest2026-10-08 cd99252 959 BA view · diff
git:20261007.bd935772026-10-07 bd93577 928 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 (959 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

chteau/tokenforge · 6 stars · license MIT · pushed 2026-10-12 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_nbt6tc7vmdczwcxc
GET https://markdownregistry.com/api/v1/resolve?ref=chteau/tokenforge/meter
GET https://markdownregistry.com/api/v1/blob/bbfdc7025ba1780fa159681c922c246a586699dbc68c85949c24af2377242e29

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 chteau/tokenforge

dashboard SKILL.md skill
chteau/tokenforge · skills/dashboard/SKILL.md · Open the local tokenforge dashboard (token usage, limits and reset times, sessions, code map).
git:20261008.757e3bc · audit A · 6 stars
forge SKILL.md skill
chteau/tokenforge · skills/forge/SKILL.md · Plan-then-workers build (tforge) for large multi-file apps; not for edits or features in existing code.
git:20261012.e1f2858 · audit A · 6 stars
handoff SKILL.md skill
chteau/tokenforge · skills/handoff/SKILL.md · Save this session's working state to .forge/HANDOFF.md so the user can /clear and continue with a small context. Use…
git:20261008.cd99252 · audit A · 6 stars
lean SKILL.md skill
chteau/tokenforge · skills/lean/SKILL.md · Turn tokenforge's lean tool set on or off (hides Workflow, Monitor, Cron and other agent-orchestration tools from…
git:20261008.cd99252 · audit A · 6 stars
proxy SKILL.md skill
chteau/tokenforge · skills/proxy/SKILL.md · Turn tokenforge's local proxy on or off for Claude Code (it compresses old tool results and prunes stale context before…
git:20261011.dc7aee2 · audit A · 6 stars
terse SKILL.md skill
chteau/tokenforge · skills/terse/SKILL.md · Switch tokenforge's terse reply style (full, lite, off) or show it.
git:20261007.8685dcf · audit A · 6 stars

Every file in chteau/tokenforge

Other files named meter

meter SKILL.md skill
snowflake-labs/cocoplus · .cortex/skills/cocometer/meter/SKILL.md · Show CocoMeter report for the current session: tools called, SQL statements executed, writes performed, estimated token…
v1.0.0 · audit A · 724 stars

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