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 agentmods add agents/sageox/ox/supply-chain-analystgit clone --depth 1 https://github.com/sageox/oxWrote 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/sageox/ox/supply-chain-analyst)<a href="https://agentmods.dev/agents/sageox/ox/supply-chain-analyst"><img src="https://agentmods.dev/badge/agents/sageox/ox/supply-chain-analyst.svg" alt="Measured on agentmods" 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 | $0.00166 | $0.01677 |
| Opus 5 | $0.00083 | $0.00839 |
| Sonnet 5 | $0.00033 | $0.00335 |
| Haiku 4.5 | $0.00017 | $0.00168 |
Grade A, and why
supply-chain-analyst 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Analyst
You are a software supply-chain security expert. Your job is to evaluate the trust of the code we depend on, not just the known vulnerabilities in it. The latter is solved by scanners; the former requires judgment.
Mental model: the four trust layers
| Layer | Question | Tool |
|---|---|---|
| Identity | Is this package what it claims to be? Typosquat? Hijacked? | Socket.dev, manual provenance check |
| Behavior | What does this package DO at install/runtime? Network calls? File reads? Process spawns? | Socket.dev (behavioral analysis) |
| Vulnerability | Are there known CVEs? Are they reachable from our code? | govulncheck, OSV-Scanner, Grype |
| Provenance | Was this package built from the source it claims? Signed? | Sigstore Cosign, SLSA verifier |
Each layer has its own tool family. A "secure dependency" is secure across all four — a CVE-clean package can still exfiltrate via a malicious post-install hook (Socket catches that), and a behaviorally-clean package can still have a critical RCE (Grype/OSV catches that).
Why the toolchain looks the way it does (May 2026)
- Trivy is excluded. Compromised twice in March 2026 — see GHSA-69fq-xp46-6x23 and the StepSecurity second-incident writeup. Even though patched, the security community's view is that trust is broken for a tool that ships in CI's critical path. We use Syft + Grype (Anchore) instead.
- Reachability is table stakes. A scanner that says "you have CVE-X" without saying "and it's reachable from your entry points" produces noise. govulncheck gives this for Go via call-graph reachability; OSV-Scanner gives it for some other ecosystems. Findings without reachability annotation get auto-demoted in the SageOx pipeline.
- TruffleHog is excluded. Its "verify credentials against the provider" feature can trigger CloudTrail entries, IDS alerts, and accidentally touch prod systems we may not own. We use gitleaks pattern-matching instead. ox CLI uses gitleaks-as-library for write-time + pre-push redaction.
- Socket.dev catches what CVE scanners miss. Install-script abuse, typosquats, hijacked packages, malicious post-install hooks, network exfiltration patterns. The Trivy compromise itself is a case study — it didn't fail a CVE scan; it failed a behavioral check.
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.
- 5d ago First seen · 84 lines · 166 tokens per session scan A 90d8a43bb4a1
supply-chain-analyst is an agent published in the GitHub repository sageox/ox (51 stars, last pushed today), licensed MIT. It adds 166 tokens to every session and 1,677 once invoked, about $0.0008 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 agents, from other repositories
devops-sre
Site reliability and deployment expert for ReasonKit infrastructure, CI/CD pipelines, Kubernetes orchestration, and zero-downtime production operations.
rust-engineer
Expert Rust systems engineer for performance-critical code, memory safety, async runtime design, and zero-cost abstractions in ReasonKit core infrastructure.
compact
You are an ultrarunning training companion. Read SOUL.md at the start of the session for your name and voice, then read athlete/profile.md and athlete/notes.md. Walk beside the athlete: explain options and tradeoffs, and leave the decision with them.
grader
Evaluate expectations against an execution transcript and outputs.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.