report SKILL.md skillA

report from wicked-sick-ltd/token-usage is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wicked-sick-ltd/token-usage/report@git:20261001.19e5534

Pins git:20261001.19e5534 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wicked-sick-ltd/token-usage
Path
codex-skills/report/SKILL.md
Versions recorded
1
Latest version
git:20261001.19e5534, committed Oct 1, 2026
Size
2,487 bytes
Repository stars
3
License
MIT

Report Codex token usage, expensive turns or skills, models, session comparisons, usage history, budget insights, live usage, dashboards and aggregate exports. Use when asked where tokens went, what a session cost, or to compare agent usage.

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

Use the bundled token-usage MCP server with `runtime: "codex"`. Its tools are
`session_cost`, `history`, `insights`, `diff`, and `top_consumers`; discover their
actual names in this session. Prefer an explicit `session_id` from CODEX_THREAD_ID
or a rollout path. Say when discovery picked the latest session instead.

If MCP is unavailable, run the bundled `scripts/token_usage.py` with Python 3.9+
(`python` on Windows, `python3` on macOS/Linux). Resolve the installed plugin root
from this file; do not assume PLUGIN_ROOT is set in an interactive shell.

```text
python <plugin>/scripts/token_usage.py report --runtime codex <rollout.jsonl> --models --agents
python <plugin>/scripts/token_usage.py history --runtime codex --since 7d --by project
python <plugin>/scripts/token_usage.py insights --runtime codex <rollout.jsonl>
python <plugin>/scripts/token_usage.py top_consumers --runtime codex --since 30d
python <plugin>/scripts/token_usage.py json --runtime codex --diff <old.jsonl> <new.jsonl>
python <plugin>/scripts/token_usage.py live --runtime codex <rollout.jsonl>
python <plugin>/scripts/token_usage.py dashboard --runtime codex --output usage.html
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wicked-sick-ltd/token-usage/report@sha256:fbff505c660ce590

The line at the top of this page pins the label git:20261001.19e5534, 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_vulac55j5vwlkeah.svg)](https://markdownregistry.com/a/art_vulac55j5vwlkeah)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 1, 2026.

versioncommittedcommitsizeaudit
git:20261001.19e5534 latest2026-10-01 19e5534 2,487 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 (2487 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

wicked-sick-ltd/token-usage · 3 stars · license MIT · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vulac55j5vwlkeah
GET https://markdownregistry.com/api/v1/resolve?ref=wicked-sick-ltd/token-usage/report
GET https://markdownregistry.com/api/v1/blob/fbff505c660ce5907ba0bb8f350b65cab7a4e6693d05866e08a054fa37583317

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 wicked-sick-ltd/token-usage

AGENTS.md AGENTS.md file
wicked-sick-ltd/token-usage · AGENTS.md
git:20261023.09c2a71 · audit A · 3 stars
CLAUDE.md CLAUDE.md file
wicked-sick-ltd/token-usage · CLAUDE.md
git:20260920.2352121 · audit B · 3 stars
report SKILL.md skill
wicked-sick-ltd/token-usage · skills/report/SKILL.md · Generate a per-activity breakdown of Claude Code, Cowork, Codex, Cursor, Google Antigravity, Gemini CLI, or GitHub…
git:20261023.09c2a71 · audit A · 3 stars

Every file in wicked-sick-ltd/token-usage

Other files named report

report SKILL.md skill
parcha-ai/agentrun · packages/pi-vision/skills/report/SKILL.md · End a run with your own report, one self-contained, script-free HTML page, report/index.html, that answers in the shape…
git:20261020.198f48c · audit B · 433 stars
report SKILL.md skill
devcodex-labs/devcodex · content/skills/report/SKILL.md · 生成并写入工作流执行报告。适用于 dev/fix/analyze/audit/self-fix(chat 豁免)。
git:20261021.9117d5c · audit A · 432 stars
report SKILL.md skill
adriannoes/awesome-agentic-ai · cursor-claude-codex/skills/alirezarezvani-skills/playwright-pro/skills/report/SKILL.md · Generate test report. Use when user says "test report", "results summary", "test status", "show results", "test…
git:20260611.ff4cc7c · audit A · 96 stars
report SKILL.md skill
vbcherepanov/total-agent-memory · skills/report/SKILL.md · Activity report from total-agent-memory for a project and period. Use when the user types /report or asks "report for…
git:20260928.fe95daf · audit A · 75 stars
report SKILL.md skill
skillberry-ai/cap-evolve · skills/phases/report/SKILL.md · Summarize a run for a human — baseline val → best val → sealed test, the winning candidate, iterations spent, and…
git:20260822.57eed81 · audit A · 69 stars
report SKILL.md skill
renzrollon/interlock · skills/report/SKILL.md · Read the indicator report over Interlock's three recorded corpora — outcome records, run trajectories, review metrics —…
git:20260904.96ef819 · audit A · 60 stars
report SKILL.md skill
anantys-oss/koan · koan/skills/core/report/SKILL.md · Weekly/monthly PR activity report (per-project + global)
v1.0.0 · audit A · 48 stars
report SKILL.md skill
jantichy/claude · skills/report/SKILL.md · Skill se použije, když uživatel zadá "/report", nebo chce z dat (CSV, JSON, export z GA4 nebo BigQuery, tabulka) udělat…
git:20261027.e929c77 · audit B · 45 stars

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