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 orcasecurity/orca-skills --skill orca-supply-chain-exposuregit clone --depth 1 https://github.com/orcasecurity/orca-skillsWrote 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/orcasecurity/orca-skills/orca-supply-chain-exposure)<a href="https://agentmods.dev/skills/orcasecurity/orca-skills/orca-supply-chain-exposure"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-supply-chain-exposure/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/orcasecurity/orca-skills/orca-supply-chain-exposure"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-supply-chain-exposure.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 | $0.00115 | $0.02699 |
| Opus 5 | $0.00057 | $0.01350 |
| Sonnet 5 | $0.00023 | $0.00540 |
| Haiku 4.5 | $0.00012 | $0.00270 |
Grade A, and why
orca-supply-chain-exposure 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orca Supply Chain Exposure Skill
Answers the question: "From this list of suspect packages, which are we actually running, where, and at what version?"
Replaces a manual sweep of inventory + SBOM queries with a single parallel check. Optimized for the moment after an MDR / vendor / news advisory lands and the team needs an exposure answer in minutes.
Usage
/orca-supply-chain-exposure @antv/util @antv/g2 @antv/g6
/orca-supply-chain-exposure log4j-core 2.14.1
/orca-supply-chain-exposure xz-utils 5.6.0,5.6.1
Or natural language:
- "are we exposed to the @antv npm attack?"
- "check these packages: react-devtools 4.28.0, axios 0.21.0"
- "any assets with xz-utils 5.6.x?"
- "supply chain check on this IOC list"
The user may paste a bullet list, a comma-separated list, or a table. Parse it.
Processing Logic
Step 1: Parse the package list
Build a normalized list of (package_name, suspected_versions[]). If the user only gave package names with no versions, treat any version found in the environment as a positive hit and rely on Orca's CVE data to confirm vulnerability.
Step 2: Run parallel exposure queries
For each package, run two queries in parallel:
Query A: Direct inventory lookup
discovery_search:
search_phrase: "assets with package <name>"
limit: 50
Query B: CVE-driven lookup (catches assets where Orca already flags the package as vulnerable)
discovery_search:
search_phrase: "assets with vulnerable <name> package"
limit: 50
Batching rule: Run all packages' Query A and Query B in parallel — one tool-call batch per package isn't enough, batch across packages. For 20 packages, that's 40 parallel discovery_search calls in one message.
Step 3: Match version ranges
For each asset returned, extract the installed version from the discovery_search response and compare against the user's suspected version list:
- Vulnerable Match: installed version is in the suspected range.
- Below Range: installed version is older than the vulnerable range (not affected).
- Above Range: installed version is newer (patched or unrelated).
- Unknown Version: discovery_search didn't return a version — flag and recommend a manual SBOM check in Orca UI.
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 · 294 lines · 115 tokens per session scan A 61d16509732f
orca-supply-chain-exposure is a skill published in the GitHub repository orcasecurity/orca-skills (50 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 2,699 once invoked, about $0.0006 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
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…