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-scope-index-keeps-existing.sh
View on GitHub#!/usr/bin/env bash
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: Netresearch DTT GmbH
# Regression test: a directory that already carries an AGENTS.md must appear in
# the root scope index, even when detect-scopes.sh has no rule for that
# directory name.
#
# The bug: the index was built purely from detected scopes. detect-scopes.sh
# knows a fixed set of directory names, so a hand-authored scoped file
# elsewhere (TYPO3 `Configuration/`, for one) was silently dropped from the
# root index on `--update`. An agent reading the root then never learns the
# file exists, which defeats the precedence rule the index exists to serve —
# and nothing reports the omission.
set -uo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SCRIPTS_DIR="$(dirname "$SCRIPT_DIR")"
DETECT="$SCRIPTS_DIR/detect-scopes.sh"
WORK="$(mktemp -d)"
trap 'rm -rf "$WORK"' EXIT
fail() { echo "❌ FAIL: $1"; exit 1; }
pass() { echo "✅ PASS: $1"; }
# A PHP project with a scoped AGENTS.md in a directory the detector has no
# rule for, plus one it does recognise.
mkdir -p "$WORK/proj/Configuration" "$WORK/proj/Classes"
cat > "$WORK/proj/composer.json" <<'JSON'
{"name": "acme/thing", "require": {"php": "^8.2"}}
JSON
for i in 1 2 3 4 5 6; do
echo "<?php" > "$WORK/proj/Classes/File$i.php"
echo "services:" > "$WORK/proj/Configuration/Services$i.yaml"
done
cat > "$WORK/proj/Configuration/AGENTS.md" <<'MD'
# Configuration
## Overview
DI services, TCA and backend routes for this extension.
MD
echo "# root" > "$WORK/proj/AGENTS.md"
SCOPES=$(cd "$WORK/proj" && bash "$DETECT" . 2>/dev/null)
printf '%s' "$SCOPES" | jq -e '.scopes[] | select(.path == "Configuration")' >/dev/null 2>&1 \
|| fail "a directory with its own AGENTS.md was not reported as a scope"
pass "an existing scoped AGENTS.md is reported even without a detection rule"
# The root file itself must never be listed as a scope of itself.
if printf '%s' "$SCOPES" | jq -e '.scopes[] | select(.path == "." or .path == "AGENTS.md")' >/dev/null 2>&1; then
fail "the root AGENTS.md was reported as its own scope"
fi
pass "the root AGENTS.md is not listed as a scope"
# A recognised directory keeps its specific type rather than being relabelled.
got=$(printf '%s' "$SCOPES" | jq -r '.scopes[] | select(.path == "Classes") | .type')
[ "$got" != "existing" ] && [ -n "$got" ] \
|| fail "a detected scope lost its type (got '$got')"
pass "a detected scope keeps its own type"
echo "All scope-index existing-file regression 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: 470k | 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 |