.claude/skills/agentsec-cli-change/SKILL.md
# agentsec-cli-change Use this skill when adding or modifying `agentsec` CLI commands. ## Inputs - Target command/subcommand. - Desired behavior and output contract. - Backward-compatibility constraints. ## Workflow 1. Locate command handler in `cmd/agentsec/*.go`. 2. Update flags/argument validation and error text. 3. Ensure usage text in `cmd/agentsec/main.go` is updated. 4. Add/adjust supporting logic in `internal/*` only when needed. 5. Run validation: ```bash make build && make t
npx skillsauth add pjordan/agent-extension-security .claude/skills/agentsec-cli-changeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when adding or modifying agentsec CLI commands.
cmd/agentsec/*.go.cmd/agentsec/main.go is updated.internal/* only when needed.make build && make test && make examples-test && bash scripts/docs-smoke.sh
docs/cli-reference.md — every command and flagdocs/quickstart.md — if the main flow changedscripts/docs-smoke.sh — smoke test must match real commandsdocs/guides/ — update platform-specific guides if the command is referenced thereinit, package, or install --dev changeddevelopment
# Web Fetcher Skill You are a web data fetcher. When the user asks you to retrieve data from an approved API, use the `fetch.sh` script to make the request and return the response. ## Approved domains This skill is only permitted to access `api.example.com`. ## Usage ``` Fetch user data: /users/123 Get status: /health ``` ## Notes - Requests are made via `curl` — the scanner will flag this as a risky pattern. This is intentional so you can see the scan report in action. - Only the domai
data-ai
# Hello World Skill This is a minimal example skill. In real ecosystems, a "skill" might be a folder that contains: - instructions (this file) - scripts and resources - a manifest describing permissions and provenance ## What it does - Prints a friendly message - Demonstrates packaging and scanning ## Usage If your agent runtime supports skills, you would invoke this by its id: `com.example.hello-world` ## Safety This example does **not** ask you to run shell commands, download scripts, o
content-media
# File Reader Skill You are a configuration file reader. When the user asks you to inspect or summarize a configuration file, read the file at the path they provide and return a brief summary of its contents. ## Usage ``` Read my SSH config: ~/.ssh/config Summarize my git settings: ~/.config/git/config ``` ## Notes - Only read files under `~/.config/` as declared in the manifest. - This skill uses shell access to read files via `read-config.sh`.
tools
# Echo MCP Server You are an echo server. When invoked, you echo back whatever input you receive. This is a minimal MCP server example for testing the agentsec packaging pipeline.