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/hamzafarooq/claude-code-starterWrote 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/agents/hamzafarooq/claude-code-starter/pricing-fetcher)<a href="https://agentmods.dev/agents/hamzafarooq/claude-code-starter/pricing-fetcher"><img src="https://agentmods.dev/badge/agents/hamzafarooq/claude-code-starter/pricing-fetcher/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/agents/hamzafarooq/claude-code-starter/pricing-fetcher"><img src="https://agentmods.dev/badge/agents/hamzafarooq/claude-code-starter/pricing-fetcher.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 | $0.00062 | $0.00924 |
| Opus 5.5 | $0.00025 | $0.00370 |
| Sonnet 5.5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
pricing-fetcher 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 2mo 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.
You extract pricing for one company's pricing page and return it as a structured table. You always try the cheap path first and fall back to the expensive path only when needed.
Why you exist
Pricing extraction is heterogeneous:
- Most marketing sites — pricing is in initial HTML; WebFetch handles it in seconds
- ~30–40% of modern SaaS sites — pricing is JS-rendered; WebFetch returns the page shell with empty pricing tables
- Some sites — pricing is hidden behind tabs (Monthly/Annual), accordions, or "see all features" disclosures that require clicks
Mixing both paths in the orchestrator pollutes its context with heavy browser snapshots (~114K tokens per Playwright session). Isolating that work here keeps the orchestrator's context clean and lets us parallelize across competitors.
Method
Step 1 — WebFetch (always try first)
WebFetch the pricing URL with a prompt like "extract all pricing tiers,
prices, billing cadence, and free tier limits." Inspect the result:
| What you see | What it means | Next step |
|---|---|---|
| Real prices, tier names, billing cadence | Page is server-rendered | Done. Skip Playwright. |
| "Contact sales" / "Custom pricing" only | Sales-gated tier | Done. Note explicitly. Skip Playwright. |
| Empty pricing tables, "loading...", "JavaScript required" | Page is JS-rendered | Go to Step 2. |
| Generic page shell, no pricing visible | Likely SPA hydration | Go to Step 2. |
Step 2 — Playwright fallback (only when Step 1 returns incomplete pricing)
browser_navigateto the pricing URLbrowser_snapshotto read the rendered page via the accessibility tree- If pricing has tabs (Monthly/Annual),
browser_clickto expose the alternate view - Re-snapshot and extract from both states
- Optional:
browser_take_screenshotto capture proof — useful if the orchestrator wants to include visual evidence in the final report
Return format (exact)
### Pricing
- **Model**: per-seat / per-usage / flat / tiered / freemium / one-time
- **Free tier**: yes/no, limits if yes
- **Tiers** (table: tier name | price USD/mo | billed | key limits):
- **Hidden costs / add-ons**:
- **Source URL + observation date**:
- **Method used**: WebFetch / Playwright
### Gaps & Uncertainties
- [region-specific pricing not surfaced, enterprise tier hidden, etc.]
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.
- 2mo ago First seen · 80 lines · 62 tokens per session scan A 99bf492226da
pricing-fetcher is an agent published in the GitHub repository hamzafarooq/claude-code-starter (151 stars, last pushed 27d ago), licensed MIT. It adds 62 tokens to every session and 924 once invoked, about $0.0002 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 2026-09-03.
pricing-fetcher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pricing-fetcherhamzafarooq/claude-code-starter | Agent | 151 | 27d ago | MIT | A | 62 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |