A tool for reading and analysing recorded language-model token use across several AI coding-agent systems. It reports usage details such as input, output, cached, total tokens, and cost.

Use it to inspect usage statistics, group consumption by model or agent system, and audit token costs.

It helps explain where agent usage and spending come from when comparing sessions, models, or coding environments.

agent-usage — Skill for Claude Code and Codex by fmind/dot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add fmind/dot --skill agent-usage

Clone the repo

git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/agent-usage/github.svg)](https://agentmods.dev/skills/fmind/dot/agent-usage)

Your own site

<a href="https://agentmods.dev/skills/fmind/dot/agent-usage"><img src="https://agentmods.dev/badge/skills/fmind/dot/agent-usage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fmind/dot/agent-usage"><img src="https://agentmods.dev/badge/skills/fmind/dot/agent-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 496 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.00496
Opus 5.5	$0.00007	$0.00198
Sonnet 5.5	$0.00003	$0.00099
Haiku 4.5	$0.00002	$0.00050

Measured today against content hash b57238835ca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agent-usage/SKILL.md · 36 lines

What it actually says

Agent Usage

Analyze the shared usage archive with dot and DuckDB. Preserve the difference between recorded token usage, estimated cost, and the provider's actual bill.

Workflow

Let dot own sync and schemas: dot owns source synchronization and archive schemas; read queries.md for layout, fields, DuckDB queries, and exports.
Report completeness, protect data: state period, sources, and completeness; protect prompt and account data.

Quick total: dot agent stats --tokens-only (coverage dates and API equivalents). queries.md owns flags, pricing fields, and monthly periods. API equivalents are offline rate-card estimates, never the bill or verified savings.

Gotchas

Unknown is not free: absent prices are null/unknown, not zero; read cost_known_sessions and cost_complete before comparing cost.
Never add unlike measurements: measurement_kind separates provider-reported, estimated (Antigravity), and context-only (Grok fallback) tokens; statistics group them separately.
Subagents are sidechains: exclude sidechain records when counting sessions; their tokens join the parent.
Check accounting completeness: legacy_accounting_sessions and session_timestamp_sessions flag records needing recapture or approximate allocation; queries.md owns parser and per-harness details.
sync fails loud, reports warn: dot agent session sync records each failed session, continues, and exits 1 at the end; the sync before dot agent stats only warns on stderr.

Documentation

DuckDB JSON Functions
Companion skills: dot-cli (every dot command), duckdb (file-based SQL analysis).

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/queries.md 9.3 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed b57238835ca0
yesterday Changed · -3 tokens per session d50746a9f91e
3d ago Changed 355662e05c25
7d ago Changed 340e47f8a67b
10d ago Changed 2bfc01c7a444
12d ago Changed · -4 lines 49c0304f7cc9
14d ago Changed cc5e6736eb37
15d ago Changed · -3 lines · -1 tokens per session 1d45d2d4b4fb
17d ago Changed · +1 lines e306b52d9c6f
20d ago First seen · 42 lines · 21 tokens per session scan A b4265e656764

Subscribe to this mod's changes

agent-usage is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 496 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Analytics and metrics Building agents Claude Code ai-agents chezmoi dotfiles fish-shell mise

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

vibe

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…

sebastienrousseau/dotfiles · 137 tokens

agent-usage