Borrowing it
Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/commands/cost-compare.mdgit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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/design-and-deliver/claude-code-autoconfig/cost-compare)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/cost-compare"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/cost-compare/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.
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/cost-compare"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/cost-compare.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00452 |
| Opus 5.5 | $0.00000 | $0.00181 |
| Sonnet 5.5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
cost-compare scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Cost Compare
Print the session-vs-fresh cost readout: live context (the per-turn re-read), fresh-session cold-start cost, and a verdict. Only the forward-looking figures appear — session total is sunk cost and deliberately omitted (/usage-report owns spend detail). All figures come deterministically from the repo's token-guard meter — no analysis of your own.
Step 1: Run the report
node "$HOME/.claude/hooks/statusline-cost.js" --report "$HOME/.claude/projects/<project-slug>/<session_id>.jsonl"
Pass your OWN session's transcript when you know your session id (it appears in paths given to you at session start, e.g. the terminal-title file name). If you don't know it, run without the argument — the script picks the newest transcript for the current project. With parallel sessions on one repo the newest may belong to a sibling; the report's first line names the session id it metered, so a mismatch is visible.
Step 2: Display
Relay the output verbatim as markdown, NOT in a code block — a code block would suppress
the bold. Keep every line's text exactly as printed, with one formatting touch: render
each bullet's leading label in bold — **current session**, **new session**,
**verdict**, **rationale** — and let the * bullet lines render as list items
as-is. Add nothing — the verdict + rationale pair is the interpretation. If it reports
the repo has no token-guard meter, relay that one line as-is.
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.
- 1mo ago Changed 0010d4aeac12
- 2mo ago First seen · 34 lines · 0 tokens per session scan A 78385d587041
cost-compare is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 452 tokens. 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
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
cancel-ralph
Cancel active Ralph Wiggum loop.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
session-log
Explain where session history lives now that the toolkit keeps no session log.