agentmods.dev

supply-chain

supply-chain is a skill for Claude Code from catpilotai/catpilot-ai-guardrails. It costs 99 tokens per session (5,072 once invoked), scanned C, original, MIT.

A software supply-chain safety review that checks outside packages, GitHub Actions, install commands, agent add-ons, and servers before they are trusted.

In plain words
What is it for?
Use it to detect lookalike package names, unpinned dependencies and actions, install scripts piped from the internet, and add-ons from unknown publishers.
Why use it?
It helps prevent unverified or changeable third-party code from running on developer machines, build systems, or production servers.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Codex; built for openclaw.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash /tmp/install.sh.

Part of the catpilot-guardrails plugin — 25 skills shipped together

not rated 2repo changed 1mo ago C scan 99 tokens original MIT

Good fit Use it to detect lookalike package names, unpinned dependencies and actions, install scripts piped from the internet, and add-ons from unknown publishers.

Compare 6 skills from other repositories ↓
View source ↗ catpilotai/catpilot-ai-guardrails catpilot.ai
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrails
agentmods
npx agentmods add skills/catpilotai/catpilot-ai-guardrails/supply-chain

Made for: Claude Code.

Or install catpilot-guardrails, the plugin that ships this one along with the rest of its 25 skills.

Wrote 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.

agentmods badge for supply-chain

README.md
[![agentmods](https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/supply-chain/github.svg)](https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/supply-chain)
Your own site
<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/supply-chain"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/supply-chain/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.

agentmods 80×15 button for supply-chain

Your own site · 80×15
<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/supply-chain"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/supply-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00099 $0.05072
Opus 5.5 $0.00040 $0.02029
Sonnet 5.5 $0.00020 $0.01014
Haiku 4.5 $0.00010 $0.00507

Measured 1mo ago against content hash d6022b176174, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

supply-chain scanned grade C with 2 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 1mo 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 codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

description: Block typosquats, unpinned dependencies, floating GitHub Actions tags, `curl | bash` installs, unverified agent skills/MCP servers, and post-install scripts from unknown publishers before they reach a develo

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Block typosquats, unpinned dependencies, floating GitHub Actions tags, `curl | bash` installs, unverified agent skills/MCP servers, and post-install scripts from unknown publishers before they reach a develo
src/skills/core/supply-chain/SKILL.md · 503 lines

How it starts

The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baseline

Applies when: Adding a dependency to a manifest or running an install command, referencing a third-party CI action, building a Dockerfile/compose that pulls images or binaries, piping curl/wget output into a shell, or installing an agent skill, MCP server, or IDE extension.

Always:

  • Install from a lockfile (npm ci, pip install --require-hashes, poetry install --no-update, bundle install --frozen, cargo build --locked), never a bare install that re-resolves.
  • Pin third-party CI references (actions, orbs, plugins, reusable workflows) to a full commit SHA, not a mutable tag.
  • Before adding a dependency, verify its spelling against the canonical upstream name, its publisher/namespace, its provenance/attestation, and its download/maintenance history.
  • Replace curl | bash-style pipe-to-shell installs with download, hash-verify, inspect, then run; prefer the project's package-manager distribution.
  • Review a package's install/build-hook scripts before installing; refuse ones that download external artifacts or touch ~/.ssh, ~/.aws, or similar credential paths.
  • Vet any third-party agent skill, MCP server, or IDE extension as code: read the source, check the permission scope, and reject obfuscated or "ClickFix" install instructions.

Never:

  • npm install/yarn add/pip install <pkg> (unpinned, no lockfile) in CI.
  • A GitHub Actions third-party reference pinned to a tag or branch (@main, @v1) instead of a commit SHA.
  • Silently substituting a similar-looking package when a typosquat or namespace check fails.
  • curl ... | bash, wget -qO- ... | sh, or iwr ... | iex piped installs.
  • Installing an agent skill or extension with a "ClickFix" instruction, an obfuscated/base64 payload, or a typosquatted publisher name.

Open the full component before acting: it has the examples, the remediation steps, and the detection patterns.

Why

Modern applications execute orders of magnitude more code from external publishers than from the developer who wrote the project. A typical Node service pulls in 1,000+ transitive npm packages on first install; a typical Python service depends on a wheel built by a maintainer the developer has never met; a typical CI pipeline executes third-party GitHub Actions that have access to repository secrets and GITHUB_TOKEN.

Read the full file on GitHub · 503 lines

Changes

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.

  1. 1mo ago Changed · +24 lines d6022b176174
  2. 2mo ago First seen · 479 lines · 99 tokens per session scan C 0be65223b610

Subscribe to this mod's changes

supply-chain is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed 8d ago), licensed MIT. It adds 99 tokens to every session and 5,072 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AI SafetyClaude CodeSecurityagent-harnessagent-skillsai-agentschatgpt
Related

supply-chain compared with skills from other repositories

supply-chain next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
supply-chaincatpilotai/catpilot-ai-guardrailsSkill28d agoMITC99Claude Code
dcf-modelNousResearch/hermes-agentSkill262ktodayMITA14Claude Code, Codex
baoyu-article-illustratorNousResearch/hermes-agentSkill262ktodayMITA18Claude Code, Codex
flash-attentionNousResearch/hermes-agentSkill262ktodayMITA14Claude Code, Codex
subagent-driven-developmentNousResearch/hermes-agentSkill262ktodayMITA17Claude Code, Codex
mcporterNousResearch/hermes-agentSkill262ktodayMITA16Claude Code, Codex
mem0-vercel-ai-sdkmem0ai/mem0Skill69kyesterdayApache-2.0A146Claude Code, Codex