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.
mdr add wicked-sick-ltd/token-usage/report@git:20261023.09c2a71Pins git:20261023.09c2a71 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
skills/report/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261023.09c2a71, committed Oct 23, 2026
- First version recorded
- Oct 3, 2026
- Size
- 14,551 bytes
- Repository stars
- 3
- License
- MIT
Generate a per-activity breakdown of Claude Code, Cowork, Codex, Cursor, Google Antigravity, Gemini CLI, or GitHub Copilot CLI token usage and estimated API cost for the current or a past session, attributing usage to slash commands (Claude Code, Antigravity), skills (Cowork, Antigravity), or Cursor composer generations, including subagent rollups, per-agent-type and per-model breakdowns, cross-session history with burn rate, compare mode, budget nudge status, and rule-based spend insights.…
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-usage report Select the runtime for this host: `claude` (Claude Code/Cowork), `codex`, `cursor`, `gemini` (Google Antigravity / Gemini CLI), or `copilot` (GitHub Copilot CLI). Pass that value explicitly to every MCP tool and add `--runtime <host>` to every CLI command below when outside Claude. Use `python` on Windows and `python3` on macOS/Linux. Never silently report another host's data. Produce a per-activity token-usage breakdown: slash commands (Claude Code, Antigravity), skills (Cowork, Antigravity), or composer activities (Cursor), plus subagent rollups and API-equivalent cost estimates. Also handles cross-session history and transcript comparison. Gemini reads native Antigravity `transcript.jsonl` and Gemini CLI recordings. Copilot uses its capture extension and saved shutdown totals; uncaptured totals cannot be attributed to individual commands. Report `measurement` and warnings, and never present activity-only counters as zero spend. ## Prefer the MCP tools when present If this session exposes MCP tools from the **token-usage** server (`session_cost`, `history`, `insights`, `diff`, `top_consumers`), call them instead of shelling out. …
Read the whole file at its exact version.
How to install
mdr add wicked-sick-ltd/token-usage/report@sha256:b4a0d08ce046a290The line at the top of this page pins the label git:20261023.09c2a71, 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.
[](https://markdownregistry.com/a/art_75dbcqggbggdff5t)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 3, 2026 and Oct 23, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.09c2a71 latest | 2026-10-23 | 09c2a71 | 14,551 B | A | view · diff |
| git:20261021.39cbb73 | 2026-10-21 | 39cbb73 | 14,088 B | A | view · diff |
| git:20261018.fe99854 | 2026-10-18 | fe99854 | 13,150 B | A | view · diff |
| git:20261005.ae989e2 | 2026-10-05 | ae989e2 | 13,011 B | A | view · diff |
| git:20261003.eed6939 | 2026-10-03 | eed6939 | 12,364 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14551 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
wicked-sick-ltd/token-usage · 3 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_75dbcqggbggdff5t GET https://markdownregistry.com/api/v1/resolve?ref=wicked-sick-ltd/token-usage/report GET https://markdownregistry.com/api/v1/blob/b4a0d08ce046a2908f11b25e36e48287fe5c6530351ae67e303394086cf12db5
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
Every file in wicked-sick-ltd/token-usage