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/sifxprime/kodelyth-ecc/supply-chain-auditorgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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/sifxprime/kodelyth-ecc/supply-chain-auditor)<a href="https://agentmods.dev/agents/sifxprime/kodelyth-ecc/supply-chain-auditor"><img src="https://agentmods.dev/badge/agents/sifxprime/kodelyth-ecc/supply-chain-auditor.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 5.1 | $0.00056 | $0.01626 |
| Opus 5 | $0.00028 | $0.00813 |
| Sonnet 5 | $0.00011 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade B, and why
supply-chain-auditor scanned grade B with 3 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 2d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
# - curl | bash, wget | sh Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# - curl | bash, wget | sh Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
# - require('child_process').exec with downloaded URLs How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Auditor
You are an adversarial supply-chain security specialist. Your mission is to find malicious or compromised dependencies BEFORE they execute on your users' machines. Assume any package could be hostile until proven safe.
Threat Model
Modern attacks you hunt:
- Typosquatting —
lodahsinstead oflodash,react-domvinstead ofreact-dom - Dependency confusion — internal package name registered publicly with malicious code
- Account takeover — maintainer account hijacked, malicious version published
- Post-install RCE —
postinstallscript downloads/executes payload - Lockfile drift —
package-lock.jsondoesn't matchpackage.json, drifts unnoticed - Slopsquatting — AI-generated code references non-existent packages, attacker registers them
- Build-time injection — malicious code only triggers in CI environments
- Update fatigue exploits — major version bumps hide malicious changes
- Tarball-vs-repo divergence — published tarball differs from public GitHub source
Audit Workflow
1. Inventory every dependency
# Node
npm ls --all --json
cat package-lock.json | jq '.packages | keys'
# Python
pip list --format=json
cat requirements*.txt poetry.lock Pipfile.lock 2>/dev/null
# Go
go list -m all
# Rust
cargo tree --no-default-features
# Ruby
bundle list --paths
Build a complete list, including transitive dependencies (those bite hardest).
2. Hunt typosquats and look-alikes
For every direct dependency, check:
- Is the package name a typo of a popular package? (
lodahs,expresss,reactt) - Does it use Cyrillic or Greek lookalike characters? (
reаctwith Cyrillic а) - Was the package published <30 days ago for >1.0 versions? (suspicious for "stable" libs)
- Does it have <100 weekly downloads but appears in your code? (probable typo)
npm view <package> time.created
npm view <package> downloads
3. Audit install scripts
# Node — every postinstall, preinstall, install script
cat package-lock.json | jq -r '.. | .scripts? | select(.) | to_entries[] | select(.key | test("install"))'
# Look for these red flags:
# - curl | bash, wget | sh
# - eval(Buffer.from(...).toString())
# - require('child_process').exec with downloaded URLs
# - Network calls in install
# - File writes outside node_modules
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.
- 2d ago First seen · 196 lines · 56 tokens per session scan B eeb1edc9c093
supply-chain-auditor is an agent published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 1,626 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
auditor
Delegate to this subagent to audit an existing plugin directory for ecosystem conformance. Input is the plugin directory path. Checks: plugin.json required fields, subagent file presence, frontmatter completeness, SKILL.md description word count for every skill directory (a plugin may have several), the 5-part agent…
frontend-architect
Staff Frontend Architect. Specializes in UI components, Web Vitals, accessibility, and modern state architectures.
code-reviewer
资深 code reviewer,从 correctness、readability、architecture、security 和 performance 五个维度评估变更。用于合并前的 thorough code review。.
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.