A command that reads Claude Code's local session logs and reports spending in US dollars by project and Git branch. Git branches are separate lines of development within a code project.

Use it to view today's, this week's, or this month's Claude Code spend, grouped by project and branch.

It shows usage costs without accessing API traffic or requiring an API key.

report — Command by RoninForge

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.

agentmods

npx agentmods add commands/roninforge/claude-code-cost/report

Clone the repo

git clone --depth 1 https://github.com/RoninForge/claude-code-cost

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 474 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00045	$0.00474
Opus 5	$0.00023	$0.00237
Sonnet 5	$0.00009	$0.00095
Haiku 4.5	$0.00005	$0.00047

Measured yesterday against content hash 7b8a8beedec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report 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 yesterday.

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.

commands/report.md · 26 lines

What it actually says

Run the bundled cost reader and show the user their Claude Code spend, grouped by project and git branch.

Run exactly this command with the Bash tool, passing the user's arguments through verbatim:

node "${CLAUDE_PLUGIN_ROOT}/scripts/cost.mjs" --mode report $ARGUMENTS

Then present the command's stdout to the user VERBATIM inside a fenced code block. Do not reformat the table, do not add columns, do not re-sort rows, and do not convert it to Markdown. Do not rank projects, editorialize, or add commentary about the numbers unless the user explicitly asks for analysis.

Notes for you (the model), not for the user:

The script reads only the local JSONL session logs under ~/.claude/projects. It never touches API traffic. If asked, you can state plainly: zero key, zero prompts, zero latency.
If budgetclaw is installed, the script uses it automatically (richer: persistent database plus budget caps). Otherwise it falls back to a self-contained reader. Pass --self to force the built-in reader.
A first non-flag argument is a case-insensitive substring filter on project or branch name (for example /claude-code-cost:report roninforge).
For spend over time use the sibling commands /claude-code-cost:by-day, /claude-code-cost:by-week, /claude-code-cost:by-month. For a per-project rollup with last-active dates, /claude-code-cost:by-project.
--json makes it emit a JSON array instead of the table.
If the output ends with a "Note:" line about unpriced models, keep it; it surfaces spend the price index could not value yet.
If the script prints "No Claude Code spend tracked yet." or "No Claude Code session logs found ...", relay that message as-is.

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.

yesterday First seen · 26 lines · 45 tokens per session scan A 7b8a8beedec6

Subscribe to this mod's changes

report is a command published in the GitHub repository RoninForge/claude-code-cost (2 stars, last pushed 25d ago), licensed MIT. It adds 45 tokens to every session and 474 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.

Backend and APIs Git and workflow anthropic claude-code claude-code-plugin cli cost-tracking developer-tools

report

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

release

dashboard

export

pricing

stats

branch