A command that reads Claude Code's local session logs and summarizes spending in US dollars for each project, combining its Git branches. It also shows each project's most recent active date.

Use it to compare project spending for today, this week, and this month, ranked by monthly cost.

It provides a project-level cost view without accessing API traffic or needing an API key.

by-project — 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/by-project

Clone the repo

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

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 442 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	$0.00054	$0.00442
Opus 5	$0.00027	$0.00221
Sonnet 5	$0.00011	$0.00088
Haiku 4.5	$0.00005	$0.00044

Measured 2d ago against content hash fc2726f25e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

by-project 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 2d 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.

commands/by-project.md · 25 lines

What it actually says

Show the user their Claude Code spend rolled up per project, with each project's last active date.

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

node "${CLAUDE_PLUGIN_ROOT}/scripts/cost.mjs" --mode by-project $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 editorialize or add commentary about the numbers unless the user explicitly asks for analysis.

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

Output is a PROJECT TODAY WEEK MONTH LAST table, one row per project with its git branches merged together, ranked by month spend, with a TOTAL footer. LAST is the most recent day (UTC) that project had any spend.
The script reads only the local JSONL session logs under ~/.claude/projects. It never touches API traffic: zero key, zero prompts, zero latency. This view always reads the raw logs directly (it does not use budgetclaw, which has no last-active data).
A first non-flag argument is a case-insensitive substring filter on the project name, keeping only matching projects (for example /claude-code-cost:by-project roninforge).
--json makes it emit a JSON array of {project, today, week, month, lastActive} instead of the table.
If the output ends with a "Note:" line about unpriced models, keep it.
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.

2d ago First seen · 25 lines · 54 tokens per session scan A fc2726f25e18

Subscribe to this mod's changes

by-project is a command published in the GitHub repository RoninForge/claude-code-cost (2 stars, last pushed 25d ago), licensed MIT. It adds 54 tokens to every session and 442 once invoked, about $0.0003 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

by-project

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

branch

export

pricing

stats