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.
npx agentmods add commands/aleksandarbisevac/claude-plugins/usagegit clone --depth 1 https://github.com/AleksandarBisevac/claude-pluginsWrote 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.
[](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/usage)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/usage"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/usage.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00038 | $0.01252 |
| Opus 5 | $0.00019 | $0.00626 |
| Sonnet 5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit:usage — where the tokens went
Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/usage/audit-usage.py" <manifestPath> --format md $ARGUMENTS
Print its stdout verbatim. Do NOT re-format, summarize, re-tabulate, or "improve" it — and do
NOT wrap it in a code fence. The output is already markdown (pipe tables, bullets); a fence
would disable the table rendering it exists for. The script renders its own final output for a
reason: a usage tool that spends a pile of tokens laying out its own tables every time you ask
what you spent is self-defeating. Reading the numbers back to the user costs roughly as much as
the report describes. Just show it. (A user-supplied --format ascii in the arguments wins over
the default above — argparse takes the last occurrence; print that verbatim too, fenced.)
The only thing worth adding is a single line of interpretation when something in the output is genuinely notable — a phase that cost several times its peers, a cache hit rate that collapsed, a model routed somewhere it shouldn't be. Otherwise say nothing.
Read-only: this never takes the audit lock and never touches the manifest. The one exception is
--backfill, which rewrites the monthly ledger files and takes its own usage.lock.
Arguments
Pass $ARGUMENTS through unchanged. Nothing here needs interpreting on your side.
| Flag | Effect |
|---|---|
--by phase|task|model|author|agent|day|month|hour|session|branch|attr |
one focused table instead of the dashboard |
--phase <id> --task <id> --model <name> --author <who> |
narrow the rows (--model/--author match on substring) |
--area <tag> |
only spend whose phase carries this area tag (untagged selects spend no area owns) |
--attr task|phase|window|unattributed |
filter by attribution precision |
--since 7d|2w|3m|YYYY-MM-DD, --until YYYY-MM-DD |
bound the window |
--top N |
cap TOP TASKS (default 10) |
--no-cost |
tokens only, no dollar figures |
--format md|ascii |
md (the default above) renders pipe tables for this chat surface; ascii is the fixed-width terminal shape for pipes, logs and CI |
--color auto|always|never |
ANSI color for humans at a real terminal (auto = TTY with NO_COLOR unset; this chat surface is a pipe, so it stays plain; md never colors) |
--json |
machine-readable, for CI |
--backfill |
re-read every transcript and rebuild the ledger |
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.
- 4d ago First seen · 75 lines · 38 tokens per session scan A 598948bdb574
usage is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 1,252 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
init
在既有專案初始化 Octopus——摸專案、檢查 OpenSpec CLI 與結構（缺則引導安裝）、盤點 change 狀態、建 Arena、出交接報告。每個專案跑一次。.
list
Show the project backlog (open items by default, sorted by priority then age). Ask for --all, --sort date or --priority high and Claude re-runs the engine with them.
prune
Delete old closed entries (status done/cancelled) left over from earlier plugin versions. Shows the list first; the deletion itself asks for your approval.
build
SDD 後半段（全自主）：驗 Locked → Builder 逐 task 實作（每條 task 隨行回報）→ 審查 → P1 自動退修（≤3 輪）→ 帶驗收報告回來，你只剩 merge 與 archive。中途不停下來等人。.
add
Add a task to the backlog manually. Use when the user explicitly asks to record something in the backlog.
cancel
Cancel a backlog task by id (the entry is deleted from the backlog).