bostonaholic/skills

auditing-agent-token-usage

Audits recent Claude Code and Codex session logs for token and context cost: model routing, inherited subagent models, long sessions, compactions, oversized tool results, and unused MCP servers.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/bostonaholic/skills --skill auditing-agent-token-usage

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Auditing agent token usage

Run the deterministic audit, then explain its results. The script is the measurement; do not substitute your own log reading for it.

sh
"<skill-dir>/scripts/audit-token-usage.sh" <days>

<days> is a positive integer, default seven unless the user names another window. The script needs jq and reads Claude Code transcripts and Codex rollouts under the home directory. On a nonzero exit, relay stderr and stop.

Analyze

  • State the window and which sources had data. Claude Code sections, [1] to

[5], measure transcript proxies such as turn counts and character sizes. The Codex section, [6], uses recorded token counts.

  • Identify the largest evidenced costs: expensive model usage, inherited

subagent routing, long sessions, compactions, context re-reading, oversized tool results, and configured MCP servers absent from section [5].

  • Recommend only changes the output supports: at most three, ranked by

expected impact, each citing the count or percentage behind it.

  • Never present Claude Code proxy values as measured tokens.
  • When a source is absent or the script fails, report the missing data or

prerequisite. Do not infer its usage.

from this repository

More skills

All skills
bostonaholic
Community

auditing-complexity

Ranks where code complexity concentrates in a git repository (cyclomatic complexity, nesting, fan-out, mutable state) and scores CRAP change risk from a coverage file. Read-only. Use when the user says "find complexity hotspots", or when asked for complexity hotspots or change risk. Not for test value; use auditing-tests.

1h installs
1
GitHub stars
2
Updated
Nov 21
bostonaholic
Community

auditing-tests

Audits a test suite, or a named part, for low-value tests and marks each retain, fix, consolidate, or delete with verified removal evidence. Read-only. Use when the user says "audit the tests", or when asked to audit tests for redundant, junk, or low-value tests. Not for code complexity; use auditing-complexity.

1h installs
1
GitHub stars
2
Updated
Nov 21
bostonaholic
Community

being-extremely-fucking-brief

Keeps every reply to the user to three lines or fewer, with no preamble, restated question, recap, or closing offer. Use when the user says "be brief", or when about to reply to the user: load it before every reply in every session, including plain questions, recommendations, and comparisons, even when no other skill applies. Load it alongside any other skill that fits the request, never instead of one.

1h installs
1
GitHub stars
2
Updated
Nov 21
bostonaholic
Community

capturing-screenshots

Captures deterministic, visually verified screenshots of a running web or native app (named screens, states, viewports, dark mode) with a manifest. Use when the user says "take screenshots", or when asked for screenshots of an app or its screens. Not for attaching images to a PR; use attaching-pr-screenshots.

1h installs
1
GitHub stars
2
Updated
Nov 21