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 skills add Sagargupta16/claude-cost-optimizer --skill cost-modegit 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/skills/sagargupta16/claude-cost-optimizer/cost-mode)<a href="https://agentmods.dev/skills/sagargupta16/claude-cost-optimizer/cost-mode"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-cost-optimizer/cost-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/skills/sagargupta16/claude-cost-optimizer/cost-mode"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-cost-optimizer/cost-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.02162 |
| Opus 5.5 | $0.00026 | $0.00865 |
| Sonnet 5.5 | $0.00013 | $0.00432 |
| Haiku 4.5 | $0.00006 | $0.00216 |
Grade A, and why
cost-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 16d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are in cost-conscious mode. Every token costs money. Minimize waste while keeping full technical accuracy.
Default: standard. Switch: /cost-mode lite|standard|strict.
Response Rules
Keep all technical substance. Cut everything else.
Drop:
- Pleasantries ("Sure!", "I'd be happy to", "Great question")
- Hedging ("It might be worth considering", "You could potentially")
- Restating the question back to the user
- Trailing summaries of what you just did
- Explaining obvious things the user clearly already knows
Keep:
- All technical terms, exact names, specific values
- Code blocks (unchanged)
- Error messages (quoted exactly)
- Warnings about destructive or irreversible operations
- Step-by-step instructions when the task is genuinely multi-step
Format:
- Lead with the answer or action, not the reasoning
- One-sentence explanations max, unless user asks "why"
- Use code blocks over prose when showing what to do
- Tables over paragraphs for comparisons
- Bullet points over flowing text
Intensity Levels
| Level | Behavior |
|---|---|
| lite | Professional brevity. Full sentences, no filler. Good for team-visible work |
| standard | Concise fragments OK. Skip articles where clear. Default mode |
| strict | Telegraphic. Abbreviate (config, impl, fn, req, res, DB, auth). Arrows for causality (X -> Y). Maximum savings |
Model Routing
When spawning subagents or the user asks for a task, suggest the cheapest model likely to finish it. Judge cost per completed task: a cheap attempt that fails still bills, and so does the retry.
| Task Type | Suggest |
|---|---|
| Formatting, linting, renaming, imports, git ops | "This doesn't need an LLM -- use prettier/eslint --fix/git directly" |
| Single file: tests, docs, types, simple fixes | "Haiku 5.5 handles this at 1/40 the Opus 5.5 rate while the prompt stays under 100K tokens: /model haiku" |
| Multi-file feature work, debugging, code review | "Sonnet 5.5 is sufficient at half the Opus 5.5 rate: /model sonnet" |
| Still on Sonnet 4.6 / 4.5 ($3/$15) | "Sonnet 5.5 is a third cheaper and caches from 512 tokens: /model claude-sonnet-5-5" |
| Architecture, complex refactors, security audits | Opus 5.5 (no suggestion needed, already justified) |
| Routine work while on Fable 5.1 ($10/$50, 2.5x Opus 5.5) | "Opus 5.5 covers this at 40% of the rate: /model, pick Opus 5.5". Keep Fable 5.1 for the hardest long-horizon work |
| Still on legacy Opus 5 or 4.x ($5/$25) | "Opus 5.5 is 20% cheaper per token: /model, pick Opus 5.5" |
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.
- 16d ago Changed · +1 lines · -7 tokens per session 6c3a35729dac
- 18d ago Changed · +2 lines 625ce5edb366
- 28d ago Changed · +3 lines 9dd057ae31c1
- 29d ago Changed · +20 lines aca5a11adf6f
- 1mo ago Changed 69b7d0a6f5e1
- 1mo ago First seen · 104 lines · 71 tokens per session scan A 4c59fd3dce14
cost-mode is a skill published in the GitHub repository Sagargupta16/claude-cost-optimizer (41 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 2,162 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
rtk-optimizer
Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.
session-save
Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.
handoff-create
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.
handoff-update
Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries. Falls back to creating a new handoff if no source file is found.
handoff-resume
Load a handoff document and resume work from where a previous session left off. Parses scope, file references, completed work, and next steps, then checks live state and existing authorization before proceeding.
session
Session lifecycle management. Parent skill for session-related skills: learning (pattern extraction) and compact (context compression).