netresearch/agent-rules-skill / skills/agent-rules
agent-rules
FlaggedUse when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
scripts/tests/test-verification-sidecar.sh
View on GitHub#!/usr/bin/env bash
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: Netresearch DTT GmbH
# verify-commands.sh records its results in .agents/command-verification.json
# inside the analysed project. The file is valid JSON whatever the documented
# commands contain, and it is written inside the project only: a symlinked
# sidecar file is replaced, a symlinked .agents directory is not written to.
set -uo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SCRIPTS_DIR="$(dirname "$SCRIPT_DIR")"
VERIFY="$SCRIPTS_DIR/verify-commands.sh"
WORK="$(mktemp -d)"
trap 'rm -rf "$WORK"' EXIT
fail() { echo "❌ FAIL: $1"; exit 1; }
pass() { echo "✅ PASS: $1"; }
# Two documented commands that exist on any host: one plain, one carrying a
# tab and double quotes.
write_agents() {
# shellcheck disable=SC2016 # backticks are markdown, not substitution
printf '# Fixture\n\n## Commands\n\n| Command | Purpose |\n|---|---|\n| `ls -la` | list |\n| `ls\t"a b"` | quoted |\n' > "$1/AGENTS.md"
}
# --- Test 1: the sidecar is valid JSON and names both commands
FX="$WORK/plain"
mkdir -p "$FX"
write_agents "$FX"
(cd "$FX" && bash "$VERIFY" . >/dev/null 2>&1) || fail "verify-commands.sh errored"
jq -e . "$FX/.agents/command-verification.json" >/dev/null 2>&1 \
|| fail "the sidecar is not valid JSON: $(cat "$FX/.agents/command-verification.json")"
jq -e '.commands | has("ls -la") and has("ls\t\"a b\"")' "$FX/.agents/command-verification.json" >/dev/null \
|| fail "the sidecar does not hold both commands"
pass "the sidecar is valid JSON for a command with a tab and quotes"
# --- Test 2: a symlinked sidecar file is replaced, its target left alone
FX="$WORK/file-link"
mkdir -p "$FX/.agents"
write_agents "$FX"
printf 'keep\n' > "$WORK/outside.txt"
ln -s ../../outside.txt "$FX/.agents/command-verification.json"
(cd "$FX" && bash "$VERIFY" . >/dev/null 2>&1) || fail "verify-commands.sh errored"
[ "$(cat "$WORK/outside.txt")" = keep ] || fail "the sidecar was written through a symlink"
{ [ -f "$FX/.agents/command-verification.json" ] && [ ! -L "$FX/.agents/command-verification.json" ]; } \
|| fail "the symlinked sidecar was not replaced by a regular file"
pass "a symlinked sidecar is replaced, not written through"
# --- Test 3: a symlinked .agents directory is not written to
FX="$WORK/dir-link"
mkdir -p "$FX" "$WORK/outside-dir"
write_agents "$FX"
ln -s ../outside-dir "$FX/.agents"
(cd "$FX" && bash "$VERIFY" . >/dev/null 2>&1) || fail "verify-commands.sh errored"
[ -z "$(ls -A "$WORK/outside-dir")" ] || fail "a file was written into the symlinked .agents directory"
pass "nothing is written through a symlinked .agents directory"
echo ""
echo "All verification sidecar tests passed."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |