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 Manavarya09/cost-guardian --skill cost-estimategit clone --depth 1 https://github.com/Manavarya09/cost-guardianWrote 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/manavarya09/cost-guardian/cost-estimate)<a href="https://agentmods.dev/skills/manavarya09/cost-guardian/cost-estimate"><img src="https://agentmods.dev/badge/skills/manavarya09/cost-guardian/cost-estimate/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/manavarya09/cost-guardian/cost-estimate"><img src="https://agentmods.dev/badge/skills/manavarya09/cost-guardian/cost-estimate.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 | $0.00057 | $0.00751 |
| Opus 5 | $0.00028 | $0.00376 |
| Sonnet 5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
cost-estimate 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Estimate
Estimate the cost of a coding task before execution, with multi-model comparison.
Process
- Analyze the task description from $ARGUMENTS
- Assess complexity by examining the codebase:
- Count files that will likely need reading (use Glob to find relevant files)
- Count files that will likely need editing
- Estimate number of tool calls needed
- Calculate estimated cost using these heuristics:
Cost Heuristics by Task Type
| Task Type | Typical Tool Calls | Est. Tokens |
|---|---|---|
| Bug fix (single file) | 5-10 | 5K-15K |
| Bug fix (multi-file) | 10-25 | 15K-40K |
| Small feature | 15-30 | 25K-60K |
| Medium feature | 30-60 | 60K-150K |
| Large feature | 60-120 | 150K-400K |
| Refactor (small) | 10-20 | 15K-30K |
| Refactor (large) | 40-80 | 80K-200K |
| Code review | 5-15 | 10K-30K |
- Show multi-model comparison using the estimated tokens:
node "${CLAUDE_SKILL_DIR}/../../scripts/pricing.js" compare <est_input_tokens> <est_output_tokens> <current_model>
- Check historical data for context:
node -e "
const store = require('${CLAUDE_SKILL_DIR}/../../scripts/store');
store.initDb();
const daily = store.getDailyBreakdown(30);
if (daily.length > 0) {
const avg = daily.reduce((s, d) => s + d.cost, 0) / daily.length;
console.log('Your avg daily spend: \$' + avg.toFixed(2) + ' (' + daily.length + ' days tracked)');
}
const total = store.getTotalEntries();
console.log('Total tracked tool calls: ' + total);
"
Output Format
Present the estimate clearly:
Cost Estimate: <task description>
Complexity: <Low/Medium/High>
Est. Reads: <N files>
Est. Edits: <N files>
Est. Tools: <N total tool calls>
Est. Tokens: <N total tokens>
Model Comparison:
Model Input Output Total
─────────────────────────────────────────────────────────────
Claude Haiku 4.5 $0.04 $0.20 $0.24
Claude Sonnet 4.6 $0.15 $0.75 $0.90 ← current
Claude Opus 4.6 $0.75 $3.75 $4.50
💡 Claude Haiku 4.5 would be 73% cheaper
Based on: <reasoning>
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.
- 12d ago First seen · 80 lines · 57 tokens per session scan A 989b3cc00d8f
cost-estimate is a skill published in the GitHub repository Manavarya09/cost-guardian (35 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 751 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 2026-08-30.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
grant-proposal-builder
Nonprofit and research grant proposal assembly with structured sections, budget templates, and evaluation alignment. Use when writing grant proposals, funding applications, or research funding requests.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
audio-production
Professional audio production for music, podcasts, and sound design. Use when working with audio recording, mixing, mastering, or sound design for any medium.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.