agent-supply-chain

Audit agent skills, MCP servers, plugins, hooks, prompts, permissions, pins, licenses, and content digests before activation.

Skill by Anders-planck

IndexedMIT

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/anders-planck-agent-supply-chain

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Audit agent skills, MCP servers, plugins, hooks, prompts, permissions, pins, licenses, and content digests before activation. Use when adding, updating, publishing, or reviewing any external agent capability or configuration bundle.

Use cases: security, writing, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/agent-supply-chain

What's inside

Skill name: agent-supply-chain
Description: Audit agent skills, MCP servers, plugins, hooks, prompts, permissions, pins, licenses, and content digests before activation. Use when adding, updating, publishing, or reviewing any external agent capability or configuration bundle.
License: MIT
Instructions: 19 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
openai.yaml · agents/

SKILL.md (first lines)

# Agent Supply Chain

## Workflow

1. Resolve the exact repository, commit, package version, subpath, and license.
2. Fetch into quarantine and verify content digests before copying.
3. Inspect prompts, scripts, hooks, network use, credentials, writes, and paths outside the project.
4. Run Agent Scan when available and preserve its findings.
5. Classify risk and require explicit opt-in for authenticated, high-risk, or side-effectful capabilities.
6. Record review date, provenance, permissions, and attribution in the lockfile.

## Guardrails

- Reject floating branches, tags, package versions, and GitHub Action references.
- Do not execute quarantined code to decide whether it is safe.
- Do not silently enable connectors that require authentication.
- Fail closed on digest mismatch or unsafe path traversal.

From Anders-planck/orditra, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Aug 12, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Anders-planck/orditra
Website: github.com/Anders-planck/orditra#readme
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Anders-planck

Cite this page

agent-supply-chain skill. Agent Mart. https://agentmart.dev/skills/anders-planck-agent-supply-chain (last updated 2026-10-24)