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.
git clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsnpx agentmods add skills/catpilotai/catpilot-ai-guardrails/supply-chainWrote 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/catpilotai/catpilot-ai-guardrails/supply-chain)<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.
<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>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 | $0.00099 | $0.04579 |
| Opus 5 | $0.00049 | $0.02289 |
| Sonnet 5 | $0.00020 | $0.00916 |
| Haiku 4.5 | $0.00010 | $0.00458 |
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 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.
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 How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
The failures this skill blocks share a common shape: the agent adds, recommends, or trusts code from a publisher that hasn't been verified, pinned, or scoped.
- A typosquatted package (
requetsinstead ofrequests,1odashinstead oflodash) ships a working API surface and a payload that runs at install time. - A floating GitHub Action tag (
uses: some-org/action@main) silently changes its source code overnight; the next CI run executes whatever the maintainer pushed last, with access to every secret the workflow can read. - A
curl ... | bashinstall pipes a script the developer never read into the shell. The script can do anything the shell can. - An unverified agent skill, MCP server, or VS Code extension runs with the IDE's full permissions — access to the file tree, the shell, paired credentials, the developer's chat history with the agent itself. In February 2026, 341 malicious skills were found on ClawHub alone.
- A
postinstallscript from a recently-published package executes duringnpm install— before any code review, before any test, before the developer has even read what the package does.
This skill applies the same query-then-modify discipline used elsewhere in the bundle: inspect first, pin always, prefer the verifiable source.
When to apply
Apply this skill before the agent runs, recommends, or commits any of the following:
- A new entry in
package.json,requirements.txt,pyproject.toml,Pipfile,Gemfile,go.mod,Cargo.toml,pom.xml,build.gradle,composer.json, or any other dependency manifest. - An install command —
npm install,pnpm add,yarn add,pip install,poetry add,bundle add,gem install,go install,cargo install,brew install,apt-get install,apk add. - A GitHub Actions workflow that consumes a third-party action
(
uses: <owner>/<action>@<ref>), or any CI provider equivalent (GitLabinclude:, CircleCI orbs, Buildkite plugins, Azure Pipelines tasks). - A
Dockerfileordocker-compose.ymlthat pulls a base image, installs OS packages, or downloads binaries inside the build (cross-referencesdocker-safety). - A
curl,wget, orInvoke-WebRequestcommand that pipes its output into a shell, language runtime, or installer. - Any agent skill, MCP server, IDE extension, OpenClaw skill, ClawHub install, or similar published-by-someone-else artifact the agent is about to install or run.
- Any post-install script (
postinstall,prepare,prepublish, pipsetup.py install-time code,pyproject.toml[tool.*]build hooks).
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 · 479 lines · 99 tokens per session scan C 0be65223b610
supply-chain is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 4,579 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…