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.
git clone --depth 1 https://github.com/Sagargupta16/claude-cost-optimizerWrote 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/sagargupta16/claude-cost-optimizer/budget-mode)<a href="https://agentmods.dev/commands/sagargupta16/claude-cost-optimizer/budget-mode"><img src="https://agentmods.dev/badge/commands/sagargupta16/claude-cost-optimizer/budget-mode/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/sagargupta16/claude-cost-optimizer/budget-mode"><img src="https://agentmods.dev/badge/commands/sagargupta16/claude-cost-optimizer/budget-mode.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 | $0.00010 | $0.00347 |
| Opus 5 | $0.00005 | $0.00173 |
| Sonnet 5 | $0.00002 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
budget-mode 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 9d 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
Budget Mode — Activated
For the remainder of this session, follow these strict cost-saving rules:
Rules (apply to every subsequent response)
-
Minimal output: Respond in as few tokens as possible. No preambles, no summaries unless asked. Just do the task and confirm.
-
No exploration: Do not read files or search the codebase unless directly needed for the current task. Ask the user for the file path instead of searching for it.
-
Targeted reads: When you must read a file, use
offsetandlimitto read only the relevant section. Never read a full file if you know the approximate location. -
Single-pass edits: Make edits in one pass. Do not read a file, explain what you will change, then edit. Just read and edit in the same turn.
-
Batch operations: If given multiple tasks, handle them all in one response using parallel tool calls where possible.
-
No redundant confirmation: After an edit, do not re-read the file to "verify" unless the user asks. Trust the edit tool.
-
Concise answers: If asked a question, answer directly. No "Great question!" or "Let me help you with that." Just answer.
-
Skip explanations: Do not explain what you did unless asked. A brief one-line confirmation is sufficient.
Confirmation
Respond with exactly:
Budget mode ON. Responses will be minimal and cost-efficient.
Then wait for the next task. Do not add anything else.
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.
- 9d ago First seen · 37 lines · 10 tokens per session scan A 487e599f5095
budget-mode is a command published in the GitHub repository Sagargupta16/claude-cost-optimizer (35 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 347 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
iterate
A command that repeatedly selects, completes, checks, and records development tasks within one coding session.
pair
A pair-programming command that makes the developer and coding agent work through a task together. Pair programming means discussing the work, agreeing on decisions, and implementing it step by step with regular confirmation.
checkpoint
A checkpoint workflow that records project progress so work can be resumed after the conversation context is cleared. It combines verification, a Git commit, progress notes, and saved session information.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
audit-repo-docs
Audit repository documentation against 85+ best practices from claude-code-ultimate-guide.
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.