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 Varnan-Tech/opendirectory --skill pricing-findergit clone --depth 1 https://github.com/Varnan-Tech/opendirectoryWrote 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/varnan-tech/opendirectory/pricing-finder)<a href="https://agentmods.dev/skills/varnan-tech/opendirectory/pricing-finder"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/pricing-finder/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/varnan-tech/opendirectory/pricing-finder"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/pricing-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 96 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Tool Misuse · line 743 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 96 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 96 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00108 | $0.07203 |
| Opus 5.5 | $0.00043 | $0.02881 |
| Sonnet 5.5 | $0.00022 | $0.01441 |
| Haiku 4.5 | $0.00011 | $0.00720 |
Grade A, and why
pricing-finder scanned grade A with 1 finding 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 27d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.parse import urlparse How it starts
The opening of the file, as written. The whole thing — 748 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pricing Finder
Tell it your product URL or description. It finds 5 competitors, fetches their actual pricing pages, and returns a complete pricing intelligence report: dominant model in your space, benchmark price table, feature gate analysis, positioning map, and a concrete pricing recommendation for your product.
Zero required API keys. Runs entirely on free pip dependencies. Optional API keys improve quality.
Zero-hallucination policy: Every price point, tier name, and feature gate in the output must trace to fetched pricing page content or a DuckDuckGo search snippet. This applies to:
- Competitor prices: extracted verbatim from fetched page content only
- "Contact Sales": recorded as-is, never estimated or replaced with a number
- Tier names: copied exactly from the page, not paraphrased
- Feature lists: extracted from page content, not inferred from product knowledge
- Positioning observations: derived from the benchmark table data only
Common Mistakes
| The agent will want to... | Why that's wrong |
|---|---|
| Fill in "Contact Sales" with an estimated price | Never estimate enterprise pricing. Record it as "Contact Sales" exactly. |
| Use training knowledge for competitor prices | Every price must trace to fetched page content or a search snippet. |
| Skip the competitor confirmation step | Always show discovered competitors and wait for confirmation. Wrong competitors = wrong benchmarks. |
| Recommend a price without referencing benchmark data | Every price recommendation must cite a specific number from the benchmark table. |
| Mark a page as high quality when content < 500 chars | < 500 chars means the page was not fetched -- mark data_quality as 'low' and use search snippet fallback. |
| Use em dashes in output | Replace all em dashes with hyphens. |
Read Reference Files Before Each Run
cat references/pricing-models.md
cat references/extraction-guide.md
cat references/positioning-guide.md
Step 1: Setup Check
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago Changed · -1 lines 12bdf46a9ef8
- 2mo ago First seen · 749 lines · 108 tokens per session scan A b76e37334e3e
pricing-finder is a skill published in the GitHub repository Varnan-Tech/opendirectory (693 stars, last pushed 20d ago), licensed MIT. It adds 108 tokens to every session and 7,203 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
pricing-finder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pricing-finderVarnan-Tech/opendirectory | Skill | 693 | 20d ago | MIT | A | 108 | Claude Code |
| content-styleAtlasOmnia/donna-starter | Skill | 138 | 11d ago | MIT | A | 37 | Claude Code, Codex |
| coding-worktree-recoveryAtlasOmnia/donna-starter | Skill | 138 | 11d ago | MIT | A | 56 | Claude Code, Codex |
| macos-storage-managementAtlasOmnia/donna-starter | Skill | 138 | 11d ago | MIT | A | 22 | Claude Code, Codex |
| hermes-mnemosyneAtlasOmnia/donna-starter | Skill | 138 | 11d ago | MIT | A | 30 | Claude Code, Codex |
| skill-auditorAtlasOmnia/donna-starter | Skill | 138 | 11d ago | MIT | A | 64 | Claude Code, Codex |
| marketplace-purchase-vettingAtlasOmnia/donna-starter | Skill | 138 | 11d ago | MIT | A | 72 | Claude Code, Codex |