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 DaizeDong/buy-me-a-car --skill orchestratorgit clone --depth 1 https://github.com/DaizeDong/buy-me-a-carWrote 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/daizedong/buy-me-a-car/orchestrator)<a href="https://agentmods.dev/skills/daizedong/buy-me-a-car/orchestrator"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/orchestrator/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/daizedong/buy-me-a-car/orchestrator"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Agent Snooping · line 80 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 384 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00067 | $0.10371 |
| Opus 5 | $0.00034 | $0.05185 |
| Sonnet 5 | $0.00013 | $0.02074 |
| Haiku 4.5 | $0.00007 | $0.01037 |
Grade A, and why
buy-me-a-car 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 11d 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 — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buy Me a Car
Caveat: this skill is one author's playbook + 5-scenario stress test. Verify state fees / CPO terms / EV credits / dealer practices against current sources before quoting numbers to a dealer or making financial decisions. Not tax, legal, or financial advice. Caveat (cont): This is a 0.2.0 alpha release. Sub-skills handle narrow tasks; this orchestrator runs the full pipeline.
End-to-end pre-purchase workflow for new and used cars. Tuned for Subaru/Honda/Toyota/Mazda SUVs in the NJ tri-state area but the structure generalizes.
When To Use
Scope, in one line: this skill runs the purchase end to end for a new or used car. Multi-site
inventory search, mass dealer outreach, Gmail reply monitoring on a cron, OTD negotiation with
market-data anchors, CARFAX and service-record PDF analysis, and decision dossiers for test
drives. That sentence used to live in the frontmatter description, which is loaded into every
turn's system prompt whether or not the skill fires; it lives here instead because this file is
loaded on invocation, when the list is actually useful. The description now carries trigger
phrases only, and only as many as the 180-char cap holds: the 17 phrases are 246 chars before
separators. Complete list: README.md § orchestrator.
- Buyer wants to evaluate inventory across multiple dealers / sites
- Buyer wants written OTD by email before stepping on a lot
- Buyer needs a market-data-backed anchor for a counter-offer
- Buyer wants a CARFAX, service-record, or dealer-proposal PDF analyzed
- Buyer is comparing 2-4 final candidates and needs a decision dossier
- Buyer is mid-cycle and needs replies drafted to dealer emails
When NOT To Use
- Purchase is already closed (paperwork signed), direct user to a delivery checklist instead
- Pure mechanical-repair, EV-charging, lease-return, or insurance questions
- "Just tell me what car to buy" with no constraints, go back to Phase 1 and gather requirements first
- Quick price-check that does NOT require dealer outreach, answer directly with
references/deal_data_sources.mdFirecrawl pipeline only
What ships with it
50 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.
- assets/_feedback_protocol.md 1.3 KB
- assets/criteria_template.md 3.8 KB
- assets/dealer_reply_template.md 16 KB
- assets/dossier_config_template.yaml 6.5 KB
- assets/dossier_template_cn.html 8.9 KB
- assets/dossier_template_es.html 10 KB
- assets/dossier_template.html 9.2 KB
- assets/feedback_log.md 5.9 KB
- assets/negotiation_prep_template.md 6.2 KB
- assets/tracker_template.md 1.9 KB
- README.md 2.7 KB
- references/_data_sources.md 17 KB
- references/_state_stub_template.md 5.2 KB
- references/acura_cpo_program.md 14 KB
- references/cron_monitoring.md 19 KB
- references/deal_data_sources.md 45 KB
- references/email_format_rules.md 5.7 KB
- references/ev_buyer_playbook.md 22 KB
- references/ford_bluecert_program.md 18 KB
- references/genesis_cpo_program.md 17 KB
- references/glossary_es.md 6.9 KB
- references/gm_cpo_program.md 16 KB
- references/gotchas.md 24 KB
- references/honda_cpo_program.md 11 KB
- references/hyundai_cpo_program.md 16 KB
- references/kia_cpo_program.md 15 KB
- references/lease_playbook.md 31 KB
- references/lexus_cpo_program.md 19 KB
- references/mazda_cpo_program.md 14 KB
- references/negotiation_playbook.md 19 KB
- references/outbound_email_sop.md 8.8 KB
- references/outreach_strategy.md 8.5 KB
- references/payment_methods.md 21 KB
- references/pdf_review_checklist.md 25 KB
- references/phases.md 39 KB
- references/pivot_protocol.md 5.1 KB
- references/ppi_booking.md 7.6 KB
- references/private_party_playbook.md 15 KB
- references/state_fees.md 132 KB
- references/stellantis_cpo_program.md 15 KB
- references/subaru_cpo_program.md 5.2 KB
- references/toyota_cpo_program.md 17 KB
- references/trade_in.md 30 KB
- references/vertical_playbooks.md 44 KB
- scripts/check_freshness.py 6.7 KB runs code
- scripts/generate_dossier.py 17 KB runs code
- scripts/html_to_pdf.sh 1.9 KB runs code
- scripts/mileage_adjustment.py 2.4 KB runs code
- scripts/otd_calculator.py 5.5 KB runs code
- scripts/render_state_data.py 4.3 KB runs code
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.
- 11d ago First seen · 406 lines · 67 tokens per session scan A f6d0745f5ad3
buy-me-a-car is a skill published in the GitHub repository DaizeDong/buy-me-a-car (5 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 10,371 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 2026-08-31.
Other skills, from other repositories
pricing-and-packaging
Sets price, structures packages and tiers, and designs the monetization surfaces that carry them — upgrade paths, paywalls, and offer construction. Use this to set or change pricing, design or restructure tiers, choose a pricing metric, build an offer, design upgrade prompts and paywalls, or evaluate whether a pricing…
mcp-playbook
Deep reference / playbook for correctly driving the crevideo-reach MCP — TikTok Shop affiliate (分销) and product-listing work: tool map (89 tools), the affiliate create flow, product onboarding, TC automation-wrapper vs direct entity, Open Collaboration (OC), read-side tool choice, filter schema, ID-space gotchas…
payments-polar
A reference for adding Polar payments to a product, covering Polar as the seller of record, payment types, checkout, webhooks, and customer access.
appdirect
Every documented AppDirect marketplace operation in one binary, plus offline sync and billing-reconciliation joins. Trigger phrases: reconcile appdirect billing, which appdirect payments failed this week, what changed in appdirect subscriptions, show my appdirect pipeline, appdirect company 360, use appdirect, run…
shopifyql
Write, debug, and explain ShopifyQL queries and Shopify Segment Query Language expressions. Use this skill whenever the user wants to query Shopify analytics data, build customer segments, write ShopifyQL for reports, explore sales/orders/products data via the Shopify Admin API, debug a ShopifyQL error, understand…
automotive-aftermarket
Expert skill in automotive accessory personalization platforms that enable customers to customize vehicles with bespoke parts including 3D-printed components, custom paint options, interior trim selections, and digitally designed accessories ordered through online configurators. Covers 25 topics across…